[go: up one dir, main page]

CN118137355A - Intelligent autonomous patrol system and method for transformer substation based on patrol path - Google Patents

Intelligent autonomous patrol system and method for transformer substation based on patrol path Download PDF

Info

Publication number
CN118137355A
CN118137355A CN202410083037.9A CN202410083037A CN118137355A CN 118137355 A CN118137355 A CN 118137355A CN 202410083037 A CN202410083037 A CN 202410083037A CN 118137355 A CN118137355 A CN 118137355A
Authority
CN
China
Prior art keywords
data
module
robot platform
information
equipment
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202410083037.9A
Other languages
Chinese (zh)
Inventor
陆金龙
蒿甜甜
曹婧
王康杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Huayun Information Technology Co Ltd
Original Assignee
Zhejiang Huayun Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhejiang Huayun Information Technology Co Ltd filed Critical Zhejiang Huayun Information Technology Co Ltd
Priority to CN202410083037.9A priority Critical patent/CN118137355A/en
Publication of CN118137355A publication Critical patent/CN118137355A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/24323—Tree-organised classifiers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/60—Protecting data
    • G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
    • G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
    • G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/20—Ensemble learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/0985—Hyperparameter optimisation; Meta-learning; Learning-to-learn
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • G06N5/045—Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02B—BOARDS, SUBSTATIONS OR SWITCHING ARRANGEMENTS FOR THE SUPPLY OR DISTRIBUTION OF ELECTRIC POWER
    • H02B3/00—Apparatus specially adapted for the manufacture, assembly, or maintenance of boards or switchgear
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2123/00—Data types
    • G06F2123/02—Data types in the time domain, e.g. time-series data

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Business, Economics & Management (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Medical Informatics (AREA)
  • Human Resources & Organizations (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Economics (AREA)
  • Multimedia (AREA)
  • Strategic Management (AREA)
  • Power Engineering (AREA)
  • Databases & Information Systems (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Bioethics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Computer Security & Cryptography (AREA)
  • Water Supply & Treatment (AREA)
  • Public Health (AREA)
  • Primary Health Care (AREA)
  • Human Computer Interaction (AREA)
  • Computer Hardware Design (AREA)

Abstract

The invention discloses an intelligent autonomous patrol system and method for a transformer substation based on a patrol path, which relate to the field of power transformation, and are low in patrol efficiency, poor in safety and easy to miss and misplug at present; the intelligent robot comprises a robot platform, an artificial intelligent module, a sensor, a communication module and a safety module; the robot platform comprises an environment information acquisition module, a path planning and decision module, a motion control and execution module, a sensor data acquisition and processing module, a data transmission and remote control module, a fault diagnosis and abnormality processing module and a task completion and return module; according to the technical scheme, personnel entering a potential dangerous area is reduced, the risk of industrial accident is reduced, and missed detection and false detection are avoided; the security module ensures the security and privacy of data, prevents unauthorized access and data leakage, improves the operation efficiency and security of the transformer substation, and powerfully ensures the reliability, accuracy and security of intelligent operation and maintenance of the power system.

Description

Intelligent autonomous patrol system and method for transformer substation based on patrol path
Technical Field
The invention relates to the field of power transformation, in particular to an intelligent autonomous patrol system of a transformer substation based on a patrol path.
Background
The existing problems of the traditional manual inspection of the transformer substation mainly comprise the following aspects: 1. the workload is large: substations typically have a large number of equipment that requires regular inspection and maintenance. The traditional manual inspection mode requires the staff to check each equipment one by one, so that the workload is very large, and time and manpower are consumed. 2. The efficiency is low: in the manual inspection process, the inspection efficiency is low due to the influence of environment, weather, human factors and the like, and the equipment faults or hidden dangers cannot be found in time. 3. Risk of missing detection: the condition of easy existence of omission is examined to artifical inspection, especially in the numerous, widely distributed transformer substation of equipment, is difficult to guarantee to patrol every time and can cover all equipment, and the inspection of missing some equipment is possible. 4. Potential safety hazard: in a transformer substation, some devices may have dangerous factors such as high voltage, high temperature, toxicity, harm and the like, and may have safety risks in the manual inspection process, so as to cause injury or accident to staff. 5. Insufficient data analysis: traditional manual inspection mainly depends on personal experience and judgment of staff, analysis of equipment operation data is not deep and accurate enough, and powerful data support cannot be provided for equipment maintenance and overhaul.
Disclosure of Invention
The technical problems to be solved and the technical task to be put forward in the invention are to perfect and improve the prior art scheme, and provide an intelligent autonomous patrol system of the transformer substation based on the patrol path so as to achieve the purpose of improving the operation efficiency and the safety. For this purpose, the present invention adopts the following technical scheme.
Intelligent autonomous patrol system of transformer substation based on patrol route includes:
Robot platform: the system comprises an environment information acquisition module, a path planning and decision module, a motion control and execution module, a sensor data acquisition and processing module, a data transmission and remote control module, a fault diagnosis and exception processing module and a task completion and return module; the robot platform acquires information of surrounding environment through an environment information module, and performs path planning and decision making according to the acquired environment information;
artificial intelligence module: the method is used for learning and optimizing the patrol path, identifying equipment faults and handling abnormal conditions; the learning result is fed back to the robot platform so that the robot platform performs corresponding path planning and decision making, fault diagnosis and abnormality processing;
a sensor: the robot platform acquires images, sounds and temperature information of the environment and equipment through the sensors, so that path planning and decision making and comprehensive detection and analysis of the equipment are performed;
and a communication module: the system comprises a robot, a remote control center, a data transmission and remote control module, a data acquisition module, a data analysis module and a data analysis module, wherein the robot is used for acquiring data of the robot, and the data is transmitted to the remote control center through the data transmission and remote control module to be subjected to remote analysis and processing, so that more accurate data support is provided for maintenance and overhaul of equipment;
And (3) a safety module: the robot data encryption system comprises a network security module and a data encryption module, and is used for guaranteeing the security and privacy of a robot and data and preventing data leakage and network attack.
According to the technical scheme, the artificial intelligent module is combined with the robot platform, so that the robot can learn and improve, and the patrol task can be better executed. For example, through a machine learning algorithm, a robot can recognize normal and abnormal conditions and adjust its behavior according to environmental changes. Robots are capable of self-navigation and movement in complex environments to reach a designated tour location. For example, using lidar and deep learning algorithms, the robot can accurately map the environment and find the best tour path. In addition, the technical scheme adopts various sensors, so that the robot can sense and identify various information in the surrounding environment, and the patrol task can be better executed. For example, using infrared sensors and image recognition techniques, the robot may detect the temperature and status of the device.
Because the system integrates the artificial intelligent module, the self-adaptive adjustment can be carried out according to actual requirements and scene changes; this means that the system can adapt quickly, whether a change in device layout or a new device is added, without extensive reconfiguration or programming. Traditional substation inspection is often performed manually, which is time consuming and labor intensive, and may present a security risk in certain dangerous or difficult to reach areas; the autonomous patrol system can work all-weather and continuously, thereby greatly reducing the dependence on human resources. The system can continuously record and analyze a large amount of data collected in the inspection process, and the data can be used for immediate fault diagnosis and exception handling and can be used for subsequent performance optimization and preventive maintenance. Through the autonomous inspection system, personnel can be reduced from entering a potential dangerous area, so that the risk of industrial accidents is reduced; meanwhile, the security module of the system ensures the security and privacy of the data and prevents unauthorized access and data disclosure. Compared with the traditional patrol method, the autonomous patrol system reduces frequent manual patrol. According to the technical scheme, the inspection efficiency and the inspection safety are effectively improved, missing inspection and false inspection are avoided, powerful data support is provided for equipment maintenance and overhaul, the operation efficiency and the operation safety of a transformer substation are improved, and the reliability, the accuracy and the safety of the intelligent operation and maintenance of the power system are powerfully ensured.
In order to adapt to the application scene of the transformer substation, a multi-sensor fusion mode, such as laser radar integration, ultrasonic sensors, infrared sensors and the like, can be utilized to improve the perception capability of the robot in a complex environment, and especially under low illumination, high noise or severe weather conditions. Advanced visual processing algorithms, such as semantic segmentation and depth estimation, are additionally employed to enhance understanding and navigation accuracy of the substation environment. The importance of the equipment, the fault history and environmental factors are considered when planning the path, and the high-risk area is preferentially patrolled.
As a preferable technical means: the environment information acquisition module comprises an acquisition unit, a transmission unit, an analysis and extraction unit and a processing and conversion unit; the acquisition unit acquires information acquired by the sensor, the transmission unit transmits the information acquired by the sensor to the analysis and extraction unit, the analysis and extraction unit processes and analyzes the received information, extracts information about environmental characteristics and equipment states, and the processing and conversion unit processes and converts the extracted information so as to facilitate subsequent path planning and decision-making; the sensor comprises a laser radar, a camera and an infrared sensor, and the acquired information comprises image, sound and temperature information.
Various information including images, sounds and temperatures can be acquired through different kinds of sensors such as a laser radar, a camera, an infrared sensor and the like; the fusion of the multi-source information can provide more comprehensive and accurate environment perception, and is helpful for improving the cognitive ability and the operation precision of the robot to the environment. The acquisition unit acquires sensor data in real time, the transmission unit rapidly transmits the data to the analysis and extraction unit, and the whole flow design ensures the real-time processing of information; this is particularly important for substation environments where a fast response is required, enabling the robot to make the correct decisions in time. The analysis and extraction unit processes and analyzes the received information, can extract the key information about the environmental characteristics and the equipment state, lightens the burden of operators and improves the autonomy and the intelligent level of the robot system. The extracted information is further processed and processed by the processing and converting unit, and can be converted into a format suitable for subsequent path planning and decision making, so that the robot platform can be more flexibly adapted to different task demands and environmental changes. In the special environment of the transformer substation, the real-time monitoring and early warning of the equipment state can be realized through a laser radar, an infrared sensor and the like, so that potential safety hazards can be found in time and corresponding measures can be taken, and the safe and stable operation of the transformer substation can be ensured.
As a preferable technical means: the path planning and decision module comprises a monitoring unit and a decision unit; the monitoring unit is connected with the acquired surrounding environment information module, recognizes obstacles and dangerous areas on the inspection path according to the acquired surrounding environment information, and matches fault signs in the image with known fault modes so as to recognize equipment faults and record conventional data; the decision unit determines an action path and an avoidance strategy of the robot according to the data of the monitoring unit by utilizing an intelligent algorithm; and sending the planned path to a motion control and execution module to control the motion of the robot platform. The monitoring unit can effectively acquire surrounding environment information and identify obstacles and dangerous areas on the patrol path, and the robot platform can safely and efficiently perform tasks in complex and changeable transformer substation environments. The monitoring unit can also match fault signs in the images with known fault modes to identify equipment faults, so that the robot platform can timely discover and report potential equipment problems, and the maintenance efficiency and safety of the transformer substation are improved. The decision unit utilizes the intelligent algorithm to determine the action path and obstacle avoidance strategy of the robot according to the data provided by the monitoring unit, so that the robot platform can quickly and accurately react when encountering an obstacle, and the optimal path is selected to continue executing the task. The robot platform can realize autonomous operation to a great extent by carrying out path planning and decision making through the intelligent algorithm, so that the dependence on manual operation is reduced, the operation cost is reduced, and the operation efficiency is improved. The whole path planning and decision making process has real-time performance, can rapidly respond to environmental changes, and ensures timeliness and effectiveness of the robot platform.
As a preferable technical means: the motion control and execution module comprises a driving unit, a monitoring unit and a decision unit; the driving unit controls the movement of the robot platform according to the received path planning instruction; the monitoring unit monitors the instruction information of the robot platform moving to the appointed position or executing the appointed action, the environment information monitored by the sensor in real time and the motion state information of the robot platform, and carries out information feedback; the decision unit adjusts the motion state of the robot platform according to the feedback information, so that the robot can accurately execute the path planning task. The driving unit precisely controls the movement of the robot platform according to the path planning instruction, so that the robot can move according to a preset path, and the accuracy and the reliability of the movement are improved. The monitoring unit monitors the motion state, the environment information and the execution instruction condition of the robot platform in real time, and feeds the information back to the decision unit in time, and the real-time monitoring and feedback mechanism is beneficial to finding and processing potential problems in time, so that the stable and safe operation of the robot platform is ensured. And the decision unit intelligently adjusts the motion state of the robot platform according to the feedback information provided by the monitoring unit. For example, when encountering an obstacle or an environmental change, the decision unit can quickly react to adjust the movement track or speed of the robot to ensure smooth execution of the path planning task. Through integrated drive, monitoring and decision function, motion control and execution module have realized high autonomy and intelligent, and robot platform can independently accomplish complicated route planning task under the condition that does not have manual intervention, has improved operating efficiency and automation level.
As a preferable technical means: the sensor data acquisition and processing module comprises an acquisition unit, a transmission unit, an analysis and extraction unit and a processing and conversion unit; the system comprises a collecting unit, a transmission unit, an analysis and extraction unit, a processing and conversion unit, a data processing and conversion unit and a data processing and conversion unit, wherein the collecting unit obtains information collected by a sensor, the transmission unit transmits the information collected by the sensor to the analysis and extraction unit, the analysis and extraction unit pre-processes the received information, performs characteristic extraction and processing on the data through a corresponding algorithm and model according to task requirements and sensor types, compares and analyzes the processed data with the existing data and knowledge, extracts information about equipment states and environmental characteristics, and processes and converts the extracted information so as to facilitate subsequent decision and action. The acquisition unit can acquire diversified information such as temperature, humidity, illumination, sound, images and the like from different types of sensors, and the diversified data acquisition capability enables the robot platform to more comprehensively sense the environment and the equipment state. The transmission unit ensures the rapid and stable transmission of the data from the sensor to the analysis and extraction unit, ensures the real-time performance of information processing, and the analysis and extraction unit adopts an efficient algorithm and model to preprocess, extract and process the characteristics of the data, so that a large amount of data can be processed in a short time. The analysis extraction unit not only carries out basic preprocessing on the data, but also carries out deep feature extraction and processing on the data through a corresponding algorithm and model according to task demands and sensor types, and the intelligent processing mode can extract more useful information about equipment states and environmental features. The processed data is compared and analyzed with the existing data and knowledge, so that the robot platform can better understand the current environment and equipment state, and the accuracy and effectiveness of decision and action of the robot platform are improved. The analysis extraction unit can select a proper algorithm and model according to specific requirements and data types to perform feature extraction and processing. For example, in processing image data, advanced features in the image may be extracted using deep learning algorithms and convolutional neural network models; while processing time series data, machine learning algorithms and recurrent neural network models may be used to capture timing dependencies in the data.
As a preferable technical means: the data transmission and remote control module transmits the acquired data to a remote control center through the Internet, and the remote control center stores the processed data in a database or cloud storage for subsequent inquiry and use; the remote control center can send control instructions to the robot platform through the Internet to adjust the running state and the task of the robot platform, and the robot platform receives the remote control instructions and adjusts the motion state, the action path and the parameters of the robot platform according to the instruction requirements.
Through the Internet, the remote control center can receive data acquired by the robot platform in real time, and process, analyze and store the data; and under the condition of not being in close contact with the scene, the working state, the environmental information and the task execution condition of the robot platform are remotely monitored and managed. The processed data are stored in a database or a cloud storage, so that the safety and long-term availability of the data are ensured; this data storage provides good data traceability, facilitating subsequent querying, analysis and use. The remote control center can send control instructions to the robot platform in real time through the Internet, and the running state and tasks of the robot platform are adjusted; the robot platform system has the advantages that an operator can flexibly adjust the action path, the motion state and the task parameters of the robot platform according to actual requirements and environmental changes. By remote control, the requirement of personnel entering a potential dangerous environment can be reduced, so that the safety of operation is improved; and meanwhile, the remote control center can comprehensively analyze the data acquired by the plurality of robot platforms, optimize task allocation and path planning, and improve the overall operation efficiency. Through centralized remote monitoring and management, the requirements of field personnel can be reduced, so that the operation cost is reduced.
As a preferable technical means: the fault diagnosis and abnormality processing module compares and analyzes the data acquired from the sensor data acquisition and processing module with the data in the normal state, judges whether the equipment has faults or abnormalities, triggers a processing mechanism if the faults or abnormalities are not detected, classifies and predicts the faults or abnormalities by utilizing the artificial intelligence module so as to provide more accurate diagnosis results and preventive maintenance suggestions, wherein the processing mechanism comprises alarming, recording fault information and/or adjusting a patrol path.
By comparing and analyzing the real-time data with the normal state data, abnormal signs can be detected before the faults occur, so that a processing mechanism is triggered, early warning and preventive maintenance are timely carried out, the occurrence of potential faults is avoided, and the reliability and the service life of equipment are improved. The processing mechanism comprises various modes such as alarming, fault information recording and/or inspection path adjustment, and the like, and proper processing measures can be selected according to the severity and influence range of faults, so that the effectiveness and adaptability of the robot platform in coping with different fault conditions are ensured. Timely finding and processing faults and abnormal conditions is helpful for enhancing the safety of the system; through preventive maintenance and a quick response mechanism, the influence of equipment faults on the system stability can be reduced, and the safe operation of key facilities such as a transformer substation is ensured. Powerful data support is provided for operation and maintenance decision making, and maintenance personnel can make reasonable maintenance plans according to diagnosis results and suggestions provided by the system, so that resource allocation is optimized.
As a preferable technical means: when the robot platform completes the inspection task according to the planned path, and detects that the inspection is completed or the robot platform reaches a designated position through a sensor, a task completion and return module is started, the task completion and return module automatically returns to a starting position or a parking point according to a preset path or a navigation point, and in the return process, the sensor detects an obstacle in the environment and automatically avoids the obstacle to avoid collision; when the robot platform returns to the starting position or the parking point, automatically stopping moving, and transmitting the task completion condition and the acquired data to a remote control center; after the remote control center receives the data, further data processing, storage and analysis are carried out so as to provide decision support and maintenance management, and for the condition requiring manual intervention, the remote control center receives the task completion notification and the abnormal condition report of the robot platform and carries out corresponding operation and maintenance, and the robot platform can automatically return to the starting position or the parking point according to a preset path or a navigation point without manual intervention, so that the automation degree of the system is greatly improved, and the labor cost is reduced. In the returning process, the robot platform detects obstacles in the environment through the sensor and has an automatic obstacle avoidance function, so that collision is effectively avoided, the intelligent obstacle avoidance capability ensures safe returning of the robot platform, and damage risk is reduced.
The invention provides an intelligent autonomous patrol method based on a patrol path, which comprises the following steps:
1) And (3) starting a system: when the system is started, initializing and self-checking are carried out to ensure that the robot platform sensor and the communication equipment work normally;
2) Acquiring environment information: the robot platform acquires information of surrounding environment including images, sound and temperature through a sensor;
3) Path planning and decision: based on the acquired environmental information, the robot platform performs path planning and decision making by using an artificial intelligence algorithm, and determines a patrol path and an action scheme;
4) Motion control and execution: according to the path planning and decision result, the robot platform controls the motion of the robot platform through a driving device, including movement, rotation and speed control;
5) Sensor data acquisition and processing: in the motion process, the robot platform collects equipment information including images, sound and temperature of equipment through a sensor; then, the collected data are processed and analyzed, and information about equipment states and environmental characteristics is extracted;
6) Data transmission and remote control: the robot platform transmits the acquired data to a remote server through an internet technology for centralized processing and analysis; meanwhile, the remote control center can adjust the running state and the task of the robot by sending an instruction;
7) Fault diagnosis and exception handling: based on the processed data, the system can perform fault diagnosis and exception handling; if the equipment fault or abnormal condition is detected, the system triggers a corresponding processing mechanism, wherein the processing mechanism comprises alarming and fault information recording;
8) Task completion and return: when the inspection task is completed, the robot platform returns to a designated position or a parking point, and the task completion condition and the acquired data are arranged and stored;
9) System maintenance and update: the system is regularly maintained and updated, including checking and repairing hardware devices, updating software programs and artificial intelligence algorithms.
The system is started to finish the task, the whole inspection process is highly automated, the robot platform can autonomously acquire environment information, plan paths, control motion, acquire and process data, the requirement of manual intervention is greatly reduced, meanwhile, an artificial intelligent algorithm is utilized for decision making and path planning, and the intelligent level of inspection is improved. The robot platform acquires all-round information of surrounding environment, including images, sounds, temperatures and the like, through a multi-sensor fusion technology, so that comprehensive perception of the environment is ensured, and more accurate decision making and planning of the robot platform are facilitated. Based on the environmental information acquired in real time, the robot platform can dynamically adjust the tour path and the action scheme to adapt to the change of the environment, and the dynamic adaptability and the flexibility ensure the efficient completion of the tour task. The robot platform has the capability of processing and analyzing the acquired data in real time, can extract key information about the state and environmental characteristics of the equipment, and simultaneously transmits the data to a remote server for centralized processing and analysis through the internet technology, so that the data processing capability is further enhanced. Through fault diagnosis and exception handling mechanism, the system can discover and process equipment faults or exception conditions in time, high reliability and safety of inspection tasks are ensured, in addition, a remote control center can monitor and adjust running states and tasks of the robot platform in real time, and reliability of the system is further improved. Smooth data transmission and remote control functions are realized between the remote control center and the robot platform, so that operators can remotely monitor and manage patrol tasks, and meanwhile, the system provides an intuitive user interface and a convenient operation mode, and human-computer interaction experience is improved.
As a preferable technical means: the robot platform performs fault diagnosis and exception handling based on a fault diagnosis and exception handling model trained by an artificial intelligence module, the artificial intelligence module training the fault diagnosis and exception handling model comprising the steps of:
701 Data collection and processing
And (3) data collection: collecting various data sources of substation equipment, including sensor data, equipment image data and equipment operation logs; the sensor data comprise current, voltage and temperature data of the equipment, and the equipment image data comprise infrared thermal images and visible light images;
Data preprocessing: preprocessing the collected data, including cleaning, denoising, standardization and normalization operations, so as to improve the quality of the data and the training effect of the model;
702 Feature extraction and engineering
Feature extraction: extracting characteristics related to equipment faults from the preprocessed data, wherein the characteristics comprise current fluctuation, temperature abnormality and abnormal areas in images;
Characteristic engineering: further processing and combining the extracted features according to domain knowledge and experience to generate a feature set;
703 Model construction and training
Constructing a convolutional neural network model for processing the equipment image data and identifying an abnormal region in the image;
Constructing a cyclic neural network or a long-term and short-term memory network model for processing time series data and monitoring the running state of equipment;
Classifying and predicting equipment faults based on the extracted features by using an ensemble learning algorithm; the integrated learning algorithm is a random forest or gradient lifting tree;
704 Dividing the processed data into a training set and a testing set;
training the constructed model by using a training set, and optimizing the performance of the model by adjusting the model parameters and the super parameters of the learning rate;
evaluating the model by using a cross verification technology, and selecting the optimal model parameter configuration to obtain a trained fault diagnosis and abnormality processing model;
705 Using the test set to evaluate the accuracy, recall rate and F1 score index of the system;
optimizing the model according to the evaluation result, including adjusting the model structure, increasing the feature dimension and optimizing the super-parameters;
False alarm and missing alarm in actual operation are used as feedback for continuously improving a model and a data acquisition strategy so as to update the model regularly and keep a good running state of the system;
When fault diagnosis and exception handling are required, the robot platform calls a trained fault diagnosis and exception handling model, transformer substation equipment data acquired in real time are accessed into the robot platform, the real-time data are subjected to feature extraction and engineering operation identical to those of the training stage, and the extracted features are input into the trained model for real-time fault analysis and prediction; and generating an equipment fault early warning signal according to the output result of the model and a preset threshold value, and timely notifying related personnel to process.
The method realizes multidimensional data fusion by collecting the sensor data, the equipment image data and the equipment operation log of the transformer substation equipment, and the comprehensive data collection provides a rich information basis for subsequent fault diagnosis. The quality and consistency of the data are ensured by cleaning, denoising, standardization and normalization of the collected data, so that the accuracy and stability of model training are improved. The method not only extracts the characteristics related to the equipment faults from the preprocessed data, but also performs characteristic engineering according to the field knowledge and experience, and further enhances the expression capability and the distinguishing degree of the characteristics. The convolutional neural network is adopted to process the image data, the cyclic neural network or the long-term and short-term memory network is adopted to process the time sequence data, and the integrated learning algorithm is adopted to classify and predict the equipment faults, so that the superior performance of the model in the process of processing complex data is ensured. The model is strictly verified and evaluated through the division of the training set and the testing set and the application of the cross verification technology, so that the reliability and generalization capability of the model in practical application are ensured. And continuously optimizing and updating the model according to the evaluation result of the test set and feedback in actual operation, so that the model can be always adapted to the change of the transformer substation environment and the new characteristics of the equipment. The robot platform can call the trained model to conduct real-time fault analysis and prediction, timely generate equipment fault early warning signals and inform relevant personnel to process, and the efficiency and safety of operation and maintenance of the transformer substation equipment are greatly improved. The trained model can be flexibly deployed on the robot platform, and is seamlessly integrated with other functional modules of the robot platform, so that intelligent substation equipment inspection and fault diagnosis are realized.
By constructing a Convolutional Neural Network (CNN) model, the method can efficiently process equipment image data, CNN has excellent performance in the field of image recognition, can automatically learn the characteristics in an image, and can accurately recognize abnormal areas in the image. The method can process time series data and effectively monitor the operation state of equipment by using a cyclic neural network (RNN) or long and short term memory network (LSTM) model, and the model can capture time dependence in the data, which is very useful for predicting equipment faults and abnormal behaviors. And the integrated learning algorithm, such as a random forest or gradient lifting tree, is adopted to classify and predict equipment faults based on the extracted features, and can synthesize the prediction results of a plurality of base models, thereby improving the accuracy and stability of the overall prediction. The method combines different types of models to process different forms of data (images, time series), and shows high flexibility. Meanwhile, as new data are continuously collected, the model can be continuously updated and optimized, and the performance of the model is kept. Although deep learning models (e.g., CNNs, RNNs) are sometimes referred to as "black box" models, ensemble learning algorithms (e.g., random forests) provide better model interpretability, enabling operators to more easily understand the fault classification and prediction results of the model output. By monitoring and predicting the state of the equipment in real time, the method is beneficial to realizing fault prevention and early diagnosis, reduces unexpected downtime, and improves the service efficiency and service life of the equipment.
The beneficial effects are that: according to the technical scheme, the inspection efficiency and the inspection safety are effectively improved, missing inspection and false inspection are avoided, powerful data support is provided for equipment maintenance and overhaul, the operation efficiency and the operation safety of a transformer substation are improved, and the reliability, the accuracy and the safety of the intelligent operation and maintenance of the power system are powerfully ensured.
Drawings
Fig. 1 is a flow chart of the present invention.
Fig. 2 is a flow chart of the traffic flow of the present invention.
Fig. 3 is a flow chart of the present invention for acquiring environmental information.
Fig. 4 is a path planning and decision flow chart of the present invention.
Fig. 5 is a flow chart of motion control and execution of the present invention.
FIG. 6 is a flow chart of sensor data acquisition and processing in accordance with the present invention.
Fig. 7 is a flow chart of data transmission and remote control according to the present invention.
FIG. 8 is a flow chart of fault diagnosis and exception handling in accordance with the present invention.
FIG. 9 is a task completion and return flow chart of the present invention.
Detailed Description
The technical scheme of the invention is further described in detail below with reference to the attached drawings.
Embodiment one:
as shown in fig. 1 and 2, the substation intelligent autonomous patrol system based on the patrol path includes:
1. Robot platform: the robot platform is a core of the whole technical scheme and comprises an environment information acquisition module, a path planning and decision module, a motion control and execution module, a sensor data acquisition and processing module, a data transmission and remote control module, a fault diagnosis and exception processing module and a task completion and return module; the robot platform acquires information of surrounding environment through an environment information module, and performs path planning and decision making according to the acquired environment information;
a. the environment information acquisition module is used for acquiring: as shown in fig. 3, the environment information acquisition module comprises an acquisition unit, a transmission unit, an analysis and extraction unit and a processing and conversion unit; the acquisition unit acquires information acquired by the sensor, the transmission unit transmits the information acquired by the sensor to the analysis and extraction unit, the analysis and extraction unit processes and analyzes the received information, extracts information about environmental characteristics and equipment states, and the processing and conversion unit processes and converts the extracted information so as to facilitate subsequent path planning and decision-making; the sensor comprises a laser radar, a camera and an infrared sensor, and the acquired information comprises image, sound and temperature information.
Various information including images, sounds and temperatures can be acquired through different kinds of sensors such as a laser radar, a camera, an infrared sensor and the like; the fusion of the multi-source information can provide more comprehensive and accurate environment perception, and is helpful for improving the cognitive ability and the operation precision of the robot to the environment. The acquisition unit acquires sensor data in real time, the transmission unit rapidly transmits the data to the analysis and extraction unit, and the whole flow design ensures the real-time processing of information; this is particularly important for substation environments where a fast response is required, enabling the robot to make the correct decisions in time. The analysis and extraction unit processes and analyzes the received information, can extract the key information about the environmental characteristics and the equipment state, lightens the burden of operators and improves the autonomy and the intelligent level of the robot system. The extracted information is further processed and processed by the processing and converting unit, and can be converted into a format suitable for subsequent path planning and decision making, so that the robot platform can be more flexibly adapted to different task demands and environmental changes. In the special environment of the transformer substation, the real-time monitoring and early warning of the equipment state can be realized through a laser radar, an infrared sensor and the like, so that potential safety hazards can be found in time and corresponding measures can be taken, and the safe and stable operation of the transformer substation can be ensured.
B. Path planning and decision module: as shown in fig. 4, the path planning and decision module includes a monitoring unit and a decision unit; the monitoring unit is connected with the acquired surrounding environment information module, recognizes obstacles and dangerous areas on the inspection path according to the acquired surrounding environment information, and matches fault signs in the image with known fault modes so as to recognize equipment faults and record conventional data; the decision unit determines an action path and an avoidance strategy of the robot according to the data of the monitoring unit by utilizing an intelligent algorithm; and sending the planned path to a motion control and execution module to control the motion of the robot platform. The monitoring unit can effectively acquire surrounding environment information and identify obstacles and dangerous areas on the patrol path, and the robot platform can safely and efficiently perform tasks in complex and changeable transformer substation environments. The monitoring unit can also match fault signs in the images with known fault modes to identify equipment faults, so that the robot platform can timely discover and report potential equipment problems, and the maintenance efficiency and safety of the transformer substation are improved. The decision unit utilizes the intelligent algorithm to determine the action path and obstacle avoidance strategy of the robot according to the data provided by the monitoring unit, so that the robot platform can quickly and accurately react when encountering an obstacle, and the optimal path is selected to continue executing the task. The robot platform can realize autonomous operation to a great extent by carrying out path planning and decision making through the intelligent algorithm, so that the dependence on manual operation is reduced, the operation cost is reduced, and the operation efficiency is improved. The whole path planning and decision making process has real-time performance, can rapidly respond to environmental changes, and ensures timeliness and effectiveness of the robot platform.
C. Motion control and execution module: as shown in fig. 5, the motion control and execution module includes a driving unit, a monitoring unit, and a decision unit; the driving unit controls the movement of the robot platform according to the received path planning instruction; the monitoring unit monitors the instruction information of the robot platform moving to the appointed position or executing the appointed action, the environment information monitored by the sensor in real time and the motion state information of the robot platform, and carries out information feedback; the decision unit adjusts the motion state of the robot platform according to the feedback information, so that the robot can accurately execute the path planning task. The driving unit precisely controls the movement of the robot platform according to the path planning instruction, so that the robot can move according to a preset path, and the accuracy and the reliability of the movement are improved. The monitoring unit monitors the motion state, the environment information and the execution instruction condition of the robot platform in real time, and feeds the information back to the decision unit in time, and the real-time monitoring and feedback mechanism is beneficial to finding and processing potential problems in time, so that the stable and safe operation of the robot platform is ensured. And the decision unit intelligently adjusts the motion state of the robot platform according to the feedback information provided by the monitoring unit. For example, when encountering an obstacle or an environmental change, the decision unit can quickly react to adjust the movement track or speed of the robot to ensure smooth execution of the path planning task. Through integrated drive, monitoring and decision function, motion control and execution module have realized high autonomy and intelligent, and robot platform can independently accomplish complicated route planning task under the condition that does not have manual intervention, has improved operating efficiency and automation level.
D. the sensor data acquisition and processing module: as shown in fig. 6, the sensor data acquisition and processing module comprises an acquisition unit, a transmission unit, an analysis and extraction unit and a processing and conversion unit; the system comprises a collecting unit, a transmission unit, an analysis and extraction unit, a processing and conversion unit, a data processing and conversion unit and a data processing and conversion unit, wherein the collecting unit obtains information collected by a sensor, the transmission unit transmits the information collected by the sensor to the analysis and extraction unit, the analysis and extraction unit pre-processes the received information, performs characteristic extraction and processing on the data through a corresponding algorithm and model according to task requirements and sensor types, compares and analyzes the processed data with the existing data and knowledge, extracts information about equipment states and environmental characteristics, and processes and converts the extracted information so as to facilitate subsequent decision and action. The acquisition unit can acquire diversified information such as temperature, humidity, illumination, sound, images and the like from different types of sensors, and the diversified data acquisition capability enables the robot platform to more comprehensively sense the environment and the equipment state. The transmission unit ensures the rapid and stable transmission of the data from the sensor to the analysis and extraction unit, ensures the real-time performance of information processing, and the analysis and extraction unit adopts an efficient algorithm and model to preprocess, extract and process the characteristics of the data, so that a large amount of data can be processed in a short time. The analysis extraction unit not only carries out basic preprocessing on the data, but also carries out deep feature extraction and processing on the data through a corresponding algorithm and model according to task demands and sensor types, and the intelligent processing mode can extract more useful information about equipment states and environmental features. The processed data is compared and analyzed with the existing data and knowledge, so that the robot platform can better understand the current environment and equipment state, and the accuracy and effectiveness of decision and action of the robot platform are improved. The analysis extraction unit can select a proper algorithm and model according to specific requirements and data types to perform feature extraction and processing. For example, in processing image data, advanced features in the image may be extracted using deep learning algorithms and convolutional neural network models; while processing time series data, machine learning algorithms and recurrent neural network models may be used to capture timing dependencies in the data.
E. And the data transmission and remote control module: as shown in fig. 7, the data transmission and remote control module transmits the collected data to a remote control center through the internet, and the remote control center stores the processed data in a database or cloud storage for subsequent query and use; the remote control center can send control instructions to the robot platform through the Internet to adjust the running state and the task of the robot platform, and the robot platform receives the remote control instructions and adjusts the motion state, the action path and the parameters of the robot platform according to the instruction requirements.
Through the Internet, the remote control center can receive data acquired by the robot platform in real time, and process, analyze and store the data; and under the condition of not being in close contact with the scene, the working state, the environmental information and the task execution condition of the robot platform are remotely monitored and managed. The processed data are stored in a database or a cloud storage, so that the safety and long-term availability of the data are ensured; this data storage provides good data traceability, facilitating subsequent querying, analysis and use. The remote control center can send control instructions to the robot platform in real time through the Internet, and the running state and tasks of the robot platform are adjusted; the robot platform system has the advantages that an operator can flexibly adjust the action path, the motion state and the task parameters of the robot platform according to actual requirements and environmental changes. By remote control, the requirement of personnel entering a potential dangerous environment can be reduced, so that the safety of operation is improved; and meanwhile, the remote control center can comprehensively analyze the data acquired by the plurality of robot platforms, optimize task allocation and path planning, and improve the overall operation efficiency. Through centralized remote monitoring and management, the requirements of field personnel can be reduced, so that the operation cost is reduced.
F. Fault diagnosis and exception handling module: as shown in fig. 8, the fault diagnosis and abnormality processing module compares and analyzes the data acquired from the sensor data acquisition and processing module with the data in the normal state, determines whether the equipment has a fault or abnormality, if no fault or abnormality is detected, triggers a processing mechanism, and classifies and predicts the fault or abnormality by using the artificial intelligence module to provide more accurate diagnosis results and preventive maintenance suggestions, wherein the processing mechanism includes alarming, recording fault information, and/or adjusting a patrol path.
By comparing and analyzing the real-time data with the normal state data, abnormal signs can be detected before the faults occur, so that a processing mechanism is triggered, early warning and preventive maintenance are timely carried out, the occurrence of potential faults is avoided, and the reliability and the service life of equipment are improved. The processing mechanism comprises various modes such as alarming, fault information recording and/or inspection path adjustment, and the like, and proper processing measures can be selected according to the severity and influence range of faults, so that the effectiveness and adaptability of the robot platform in coping with different fault conditions are ensured. Timely finding and processing faults and abnormal conditions is helpful for enhancing the safety of the system; through preventive maintenance and a quick response mechanism, the influence of equipment faults on the system stability can be reduced, and the safe operation of key facilities such as a transformer substation is ensured. Powerful data support is provided for operation and maintenance decision making, and maintenance personnel can make reasonable maintenance plans according to diagnosis results and suggestions provided by the system, so that resource allocation is optimized.
G. Task completion and return module: as shown in fig. 9, when the robot platform completes the tour task according to the planned path, and detects that the tour is completed or the tour reaches the designated position through the sensor, the task completion and return module is started, and the task completion and return module automatically returns to the starting position or the parking point according to the preset path or the navigation point, and in the return process, the sensor detects the obstacle in the environment and automatically avoids the obstacle to avoid collision; when the robot platform returns to the starting position or the parking point, automatically stopping moving, and transmitting the task completion condition and the acquired data to a remote control center; after the remote control center receives the data, further data processing, storage and analysis are carried out so as to provide decision support and maintenance management, and for the condition requiring manual intervention, the remote control center receives the task completion notification and the abnormal condition report of the robot platform and carries out corresponding operation and maintenance, and the robot platform can automatically return to the starting position or the parking point according to a preset path or a navigation point without manual intervention, so that the automation degree of the system is greatly improved, and the labor cost is reduced. In the returning process, the robot platform detects obstacles in the environment through the sensor and has an automatic obstacle avoidance function, so that collision is effectively avoided, the intelligent obstacle avoidance capability ensures safe returning of the robot platform, and damage risk is reduced.
2. Artificial intelligence module: the artificial intelligent module is a key for realizing intelligent autonomous patrol, and is used for learning and optimizing a patrol path, identifying equipment faults and processing abnormal conditions; the learning result is fed back to the robot platform so that the robot platform performs corresponding path planning and decision making, fault diagnosis and abnormality processing; algorithms of the artificial intelligence module may include machine learning, deep learning, image recognition, etc., by which the robot may learn how to recognize equipment failure, how to optimize tour paths, how to handle abnormal situations, etc
3. A sensor: the sensor is an important support for realizing intelligent autonomous patrol, the sensor comprises a visual sensor, a sound sensor and a temperature sensor, and the robot platform acquires the image, sound and temperature information of the environment and equipment through the sensor, so that path planning and decision making and comprehensive detection and analysis of the equipment are performed;
4. And a communication module: the communication module is an important means for realizing intelligent autonomous patrol, and comprises cloud computing, big data analysis and the like. The communication module adopts an internet technology, and can carry out remote analysis and processing on data acquired by the robot through the internet technology, so that more accurate data support is provided for maintenance and overhaul of equipment, and the communication module is used for transmitting the data acquired by the robot to a remote control center for remote analysis and processing through data transmission and a remote control module, so that more accurate data support is provided for the maintenance and overhaul of the equipment;
5. and (3) a safety module: the safety module is an important guarantee for realizing intelligent autonomous patrol, and comprises a network safety module and a data encryption module, and is used for guaranteeing the safety and privacy of a robot and data and preventing data leakage and network attack.
According to the technical scheme, the artificial intelligent module is combined with the robot platform, so that the robot can learn and improve, and the patrol task can be better executed. For example, through a machine learning algorithm, a robot can recognize normal and abnormal conditions and adjust its behavior according to environmental changes. Robots are capable of self-navigation and movement in complex environments to reach a designated tour location. For example, using lidar and deep learning algorithms, the robot can accurately map the environment and find the best tour path. In addition, the technical scheme adopts various sensors, so that the robot can sense and identify various information in the surrounding environment, and the patrol task can be better executed. For example, using infrared sensors and image recognition techniques, the robot may detect the temperature and status of the device.
Because the system integrates the artificial intelligent module, the self-adaptive adjustment can be carried out according to actual requirements and scene changes; this means that the system can adapt quickly, whether a change in device layout or a new device is added, without extensive reconfiguration or programming. Traditional substation inspection is often performed manually, which is time consuming and labor intensive, and may present a security risk in certain dangerous or difficult to reach areas; the autonomous patrol system can work all-weather and continuously, thereby greatly reducing the dependence on human resources. The system can continuously record and analyze a large amount of data collected in the inspection process, and the data can be used for immediate fault diagnosis and exception handling and can be used for subsequent performance optimization and preventive maintenance. Through the autonomous inspection system, personnel can be reduced from entering a potential dangerous area, so that the risk of industrial accidents is reduced; meanwhile, the security module of the system ensures the security and privacy of the data and prevents unauthorized access and data disclosure. Compared with the traditional patrol method, the autonomous patrol system reduces frequent manual patrol. According to the technical scheme, the inspection efficiency and the inspection safety are effectively improved, missing inspection and false inspection are avoided, powerful data support is provided for equipment maintenance and overhaul, the operation efficiency and the operation safety of a transformer substation are improved, and the reliability, the accuracy and the safety of the intelligent operation and maintenance of the power system are powerfully ensured.
In order to adapt to the application scene of the transformer substation, a multi-sensor fusion mode, such as laser radar integration, ultrasonic sensors, infrared sensors and the like, can be utilized to improve the perception capability of the robot in a complex environment, and especially under low illumination, high noise or severe weather conditions. Advanced visual processing algorithms, such as semantic segmentation and depth estimation, are additionally employed to enhance understanding and navigation accuracy of the substation environment. The importance of the equipment, the fault history and environmental factors are considered when planning the path, and the high-risk area is preferentially patrolled.
Embodiment two:
As shown in fig. 1, an intelligent autonomous patrol method based on a patrol path is provided, and the intelligent autonomous patrol method includes the following steps:
S1: and (3) starting a system: when the system is started, initializing and self-checking are carried out to ensure that the robot platform sensor and the communication equipment work normally;
s2: acquiring environment information: the robot platform acquires information of surrounding environment including images, sound and temperature through a sensor;
s3: path planning and decision: based on the acquired environmental information, the robot platform performs path planning and decision making by using an artificial intelligence algorithm, and determines a patrol path and an action scheme;
S4: motion control and execution: according to the path planning and decision result, the robot platform controls the motion of the robot platform through a driving device, including movement, rotation and speed control;
S5: sensor data acquisition and processing: in the motion process, the robot platform collects equipment information including images, sound and temperature of equipment through a sensor; then, the collected data are processed and analyzed, and information about equipment states and environmental characteristics is extracted;
S6: data transmission and remote control: the robot platform transmits the acquired data to a remote server through an internet technology for centralized processing and analysis; meanwhile, the remote control center can adjust the running state and the task of the robot by sending an instruction;
s7: fault diagnosis and exception handling: based on the processed data, the system can perform fault diagnosis and exception handling; if the equipment fault or abnormal condition is detected, the system triggers a corresponding processing mechanism, wherein the processing mechanism comprises alarming and fault information recording;
S8: task completion and return: when the inspection task is completed, the robot platform returns to a designated position or a parking point, and the task completion condition and the acquired data are arranged and stored;
s9: system maintenance and update: the system is regularly maintained and updated, including checking and repairing hardware devices, updating software programs and artificial intelligence algorithms.
The system is started to finish the task, the whole inspection process is highly automated, the robot platform can autonomously acquire environment information, plan paths, control motion, acquire and process data, the requirement of manual intervention is greatly reduced, meanwhile, an artificial intelligent algorithm is utilized for decision making and path planning, and the intelligent level of inspection is improved. The robot platform acquires all-round information of surrounding environment, including images, sounds, temperatures and the like, through a multi-sensor fusion technology, so that comprehensive perception of the environment is ensured, and more accurate decision making and planning of the robot platform are facilitated. Based on the environmental information acquired in real time, the robot platform can dynamically adjust the tour path and the action scheme to adapt to the change of the environment, and the dynamic adaptability and the flexibility ensure the efficient completion of the tour task. The robot platform has the capability of processing and analyzing the acquired data in real time, can extract key information about the state and environmental characteristics of the equipment, and simultaneously transmits the data to a remote server for centralized processing and analysis through the internet technology, so that the data processing capability is further enhanced. Through fault diagnosis and exception handling mechanism, the system can discover and process equipment faults or exception conditions in time, high reliability and safety of inspection tasks are ensured, in addition, a remote control center can monitor and adjust running states and tasks of the robot platform in real time, and reliability of the system is further improved. Smooth data transmission and remote control functions are realized between the remote control center and the robot platform, so that operators can remotely monitor and manage patrol tasks, and meanwhile, the system provides an intuitive user interface and a convenient operation mode, and human-computer interaction experience is improved.
The robot platform performs fault diagnosis and exception handling based on a fault diagnosis and exception handling model trained by an artificial intelligence module, the artificial intelligence module training the fault diagnosis and exception handling model comprising the steps of:
s701: data collection and processing
And (3) data collection: collecting various data sources of substation equipment, including sensor data, equipment image data and equipment operation logs; the sensor data comprise current, voltage and temperature data of the equipment, and the equipment image data comprise infrared thermal images and visible light images;
Data preprocessing: preprocessing the collected data, including cleaning, denoising, standardization and normalization operations, so as to improve the quality of the data and the training effect of the model;
S702: feature extraction and engineering
Feature extraction: extracting characteristics related to equipment faults from the preprocessed data, wherein the characteristics comprise current fluctuation, temperature abnormality and abnormal areas in images;
Characteristic engineering: further processing and combining the extracted features according to domain knowledge and experience to generate a feature set;
S703: model construction and training
Constructing a convolutional neural network model for processing the equipment image data and identifying an abnormal region in the image;
Constructing a cyclic neural network or a long-term and short-term memory network model for processing time series data and monitoring the running state of equipment;
Classifying and predicting equipment faults based on the extracted features by using an ensemble learning algorithm; the integrated learning algorithm is a random forest or gradient lifting tree;
s704: dividing the processed data into a training set and a testing set;
training the constructed model by using a training set, and optimizing the performance of the model by adjusting the model parameters and the super parameters of the learning rate;
evaluating the model by using a cross verification technology, and selecting the optimal model parameter configuration to obtain a trained fault diagnosis and abnormality processing model;
S705: evaluating the accuracy, recall rate and F1 score index of the system by using the test set;
optimizing the model according to the evaluation result, including adjusting the model structure, increasing the feature dimension and optimizing the super-parameters;
False alarm and missing alarm in actual operation are used as feedback for continuously improving a model and a data acquisition strategy so as to update the model regularly and keep a good running state of the system;
When fault diagnosis and exception handling are required, the robot platform calls a trained fault diagnosis and exception handling model, transformer substation equipment data acquired in real time are accessed into the robot platform, the real-time data are subjected to feature extraction and engineering operation identical to those of the training stage, and the extracted features are input into the trained model for real-time fault analysis and prediction; and generating an equipment fault early warning signal according to the output result of the model and a preset threshold value, and timely notifying related personnel to process.
The method realizes multidimensional data fusion by collecting the sensor data, the equipment image data and the equipment operation log of the transformer substation equipment, and the comprehensive data collection provides a rich information basis for subsequent fault diagnosis. The quality and consistency of the data are ensured by cleaning, denoising, standardization and normalization of the collected data, so that the accuracy and stability of model training are improved. The method not only extracts the characteristics related to the equipment faults from the preprocessed data, but also performs characteristic engineering according to the field knowledge and experience, and further enhances the expression capability and the distinguishing degree of the characteristics. The convolutional neural network is adopted to process the image data, the cyclic neural network or the long-term and short-term memory network is adopted to process the time sequence data, and the integrated learning algorithm is adopted to classify and predict the equipment faults, so that the superior performance of the model in the process of processing complex data is ensured. The model is strictly verified and evaluated through the division of the training set and the testing set and the application of the cross verification technology, so that the reliability and generalization capability of the model in practical application are ensured. And continuously optimizing and updating the model according to the evaluation result of the test set and feedback in actual operation, so that the model can be always adapted to the change of the transformer substation environment and the new characteristics of the equipment. The robot platform can call the trained model to conduct real-time fault analysis and prediction, timely generate equipment fault early warning signals and inform relevant personnel to process, and the efficiency and safety of operation and maintenance of the transformer substation equipment are greatly improved. The trained model can be flexibly deployed on the robot platform, and is seamlessly integrated with other functional modules of the robot platform, so that intelligent substation equipment inspection and fault diagnosis are realized.
By constructing a Convolutional Neural Network (CNN) model, the method can efficiently process equipment image data, CNN has excellent performance in the field of image recognition, can automatically learn the characteristics in an image, and can accurately recognize abnormal areas in the image. The method can process time series data and effectively monitor the operation state of equipment by using a cyclic neural network (RNN) or long and short term memory network (LSTM) model, and the model can capture time dependence in the data, which is very useful for predicting equipment faults and abnormal behaviors. And the integrated learning algorithm, such as a random forest or gradient lifting tree, is adopted to classify and predict equipment faults based on the extracted features, and can synthesize the prediction results of a plurality of base models, thereby improving the accuracy and stability of the overall prediction. The method combines different types of models to process different forms of data (images, time series), and shows high flexibility. Meanwhile, as new data are continuously collected, the model can be continuously updated and optimized, and the performance of the model is kept. Although deep learning models (e.g., CNNs, RNNs) are sometimes referred to as "black box" models, ensemble learning algorithms (e.g., random forests) provide better model interpretability, enabling operators to more easily understand the fault classification and prediction results of the model output. By monitoring and predicting the state of the equipment in real time, the method is beneficial to realizing fault prevention and early diagnosis, reduces unexpected downtime, and improves the service efficiency and service life of the equipment.
The intelligent autonomous patrol system and method of the transformer substation based on the patrol path are specific embodiments of the invention, have shown the essential characteristics and the progress of the invention, and can be subjected to equivalent modification in terms of shape and structure according to actual use requirements under the teaching of the invention, and are all within the protection scope of the scheme.

Claims (10)

1. Intelligent autonomous patrol system of transformer substation based on patrol route, characterized by including:
Robot platform: the system comprises an environment information acquisition module, a path planning and decision module, a motion control and execution module, a sensor data acquisition and processing module, a data transmission and remote control module, a fault diagnosis and exception processing module and a task completion and return module; the robot platform acquires information of surrounding environment through an environment information module, and performs path planning and decision making according to the acquired environment information;
artificial intelligence module: the method is used for learning and optimizing the patrol path, identifying equipment faults and handling abnormal conditions; the learning result is fed back to the robot platform so that the robot platform performs corresponding path planning and decision making, fault diagnosis and abnormality processing;
a sensor: the robot platform acquires images, sounds and temperature information of the environment and equipment through the sensors, so that path planning and decision making and comprehensive detection and analysis of the equipment are performed;
and a communication module: the system comprises a robot, a remote control center, a data transmission and remote control module, a data acquisition module, a data analysis module and a data analysis module, wherein the robot is used for acquiring data of the robot, and the data is transmitted to the remote control center through the data transmission and remote control module to be subjected to remote analysis and processing, so that more accurate data support is provided for maintenance and overhaul of equipment;
And (3) a safety module: the robot data encryption system comprises a network security module and a data encryption module, and is used for guaranteeing the security and privacy of a robot and data and preventing data leakage and network attack.
2. The patrol path-based intelligent autonomous patrol system of a substation according to claim 1, wherein: the environment information acquisition module comprises an acquisition unit, a transmission unit, an analysis and extraction unit and a processing and conversion unit; the acquisition unit acquires information acquired by the sensor, the transmission unit transmits the information acquired by the sensor to the analysis and extraction unit, the analysis and extraction unit processes and analyzes the received information, extracts information about environmental characteristics and equipment states, and the processing and conversion unit processes and converts the extracted information so as to facilitate subsequent path planning and decision-making; the sensor comprises a laser radar, a camera and an infrared sensor, and the acquired information comprises image, sound and temperature information.
3. The patrol path-based intelligent autonomous patrol system of a substation according to claim 2, wherein: the path planning and decision module comprises a monitoring unit and a decision unit; the monitoring unit is connected with the acquired surrounding environment information module, recognizes obstacles and dangerous areas on the inspection path according to the acquired surrounding environment information, and matches fault signs in the image with known fault modes so as to recognize equipment faults and record conventional data; the decision unit determines an action path and an avoidance strategy of the robot according to the data of the monitoring unit by utilizing an intelligent algorithm; and sending the planned path to a motion control and execution module to control the motion of the robot platform.
4. A patrol path-based substation intelligent autonomous patrol system according to claim 3, characterized in that: the motion control and execution module comprises a driving unit, a monitoring unit and a decision unit; the driving unit controls the movement of the robot platform according to the received path planning instruction; the monitoring unit monitors the instruction information of the robot platform moving to the appointed position or executing the appointed action, the environment information monitored by the sensor in real time and the motion state information of the robot platform, and carries out information feedback; the decision unit adjusts the motion state of the robot platform according to the feedback information, so that the robot can accurately execute the path planning task.
5. The patrol path-based intelligent autonomous patrol system of a substation according to claim 4, wherein: the sensor data acquisition and processing module comprises an acquisition unit, a transmission unit, an analysis and extraction unit and a processing and conversion unit; the system comprises a collecting unit, a transmission unit, an analysis and extraction unit, a processing and conversion unit, a data processing and conversion unit and a data processing and conversion unit, wherein the collecting unit obtains information collected by a sensor, the transmission unit transmits the information collected by the sensor to the analysis and extraction unit, the analysis and extraction unit pre-processes the received information, performs characteristic extraction and processing on the data through a corresponding algorithm and model according to task requirements and sensor types, compares and analyzes the processed data with the existing data and knowledge, extracts information about equipment states and environmental characteristics, and processes and converts the extracted information so as to facilitate subsequent decision and action.
6. The patrol path-based intelligent autonomous patrol system of a substation according to claim 5, wherein: the data transmission and remote control module transmits the acquired data to a remote control center through the Internet, and the remote control center stores the processed data in a database or cloud storage for subsequent inquiry and use; the remote control center can send control instructions to the robot platform through the Internet to adjust the running state and the task of the robot platform, and the robot platform receives the remote control instructions and adjusts the motion state, the action path and the parameters of the robot platform according to the instruction requirements.
7. The patrol path-based intelligent autonomous patrol system of a substation according to claim 6, wherein: the fault diagnosis and abnormality processing module compares and analyzes the data acquired from the sensor data acquisition and processing module with the data in the normal state, judges whether the equipment has faults or abnormalities, triggers a processing mechanism if the faults or abnormalities are not detected, classifies and predicts the faults or abnormalities by utilizing the artificial intelligence module so as to provide more accurate diagnosis results and preventive maintenance suggestions, wherein the processing mechanism comprises alarming, recording fault information and/or adjusting a patrol path.
8. The patrol path-based intelligent autonomous patrol system of a substation according to claim 7, wherein: when the robot platform completes the inspection task according to the planned path, and detects that the inspection is completed or the robot platform reaches a designated position through a sensor, a task completion and return module is started, the task completion and return module automatically returns to a starting position or a parking point according to a preset path or a navigation point, and in the return process, the sensor detects an obstacle in the environment and automatically avoids the obstacle to avoid collision; when the robot platform returns to the starting position or the parking point, automatically stopping moving, and transmitting the task completion condition and the acquired data to a remote control center; after the remote control center receives the data, further data processing, storage and analysis are carried out to provide decision support and maintenance management, and for the condition that manual intervention is needed, the remote control center receives a task completion notification and an abnormal condition report of the robot platform and carries out corresponding operation and maintenance.
9. An intelligent autonomous patrol method adopting the intelligent autonomous patrol system of the substation based on the patrol path as claimed in claim 1, which is characterized by comprising the following steps:
1) And (3) starting a system: when the system is started, initializing and self-checking are carried out to ensure that the robot platform sensor and the communication equipment work normally;
2) Acquiring environment information: the robot platform acquires information of surrounding environment including images, sound and temperature through a sensor;
3) Path planning and decision: based on the acquired environmental information, the robot platform performs path planning and decision making by using an artificial intelligence algorithm, and determines a patrol path and an action scheme;
4) Motion control and execution: according to the path planning and decision result, the robot platform controls the motion of the robot platform through a driving device, including movement, rotation and speed control;
5) Sensor data acquisition and processing: in the motion process, the robot platform collects equipment information including images, sound and temperature of equipment through a sensor; then, the collected data are processed and analyzed, and information about equipment states and environmental characteristics is extracted;
6) Data transmission and remote control: the robot platform transmits the acquired data to a remote server through an internet technology for centralized processing and analysis; meanwhile, the remote control center can adjust the running state and the task of the robot by sending an instruction;
7) Fault diagnosis and exception handling: based on the processed data, the system performs fault diagnosis and exception handling according to the artificial intelligence module; if the equipment fault or abnormal condition is detected, the system triggers a corresponding processing mechanism, wherein the processing mechanism comprises alarming and fault information recording;
8) Task completion and return: when the inspection task is completed, the robot platform returns to a designated position or a parking point, and the task completion condition and the acquired data are arranged and stored;
9) System maintenance and update: the system is regularly maintained and updated, including checking and repairing hardware devices, updating software programs and artificial intelligence algorithms.
10. The patrol path-based intelligent autonomous patrol system of a substation according to claim 9, wherein: the robot platform performs fault diagnosis and exception handling based on a fault diagnosis and exception handling model trained by an artificial intelligence module, the artificial intelligence module training the fault diagnosis and exception handling model comprising the steps of:
701 Data collection and processing;
And (3) data collection: collecting various data sources of substation equipment, including sensor data, equipment image data and equipment operation logs; the sensor data comprise current, voltage and temperature data of the equipment, and the equipment image data comprise infrared thermal images and visible light images;
Data preprocessing: preprocessing the collected data, including cleaning, denoising, standardization and normalization operations, so as to improve the quality of the data and the training effect of the model;
702 Feature extraction and engineering;
feature extraction: extracting characteristics related to equipment faults from the preprocessed data, wherein the characteristics comprise current fluctuation, temperature abnormality and abnormal areas in images;
Characteristic engineering: further processing and combining the extracted features according to domain knowledge and experience to generate a feature set;
703 Model construction and training;
constructing a convolutional neural network model for processing the equipment image data and identifying an abnormal region in the image;
Constructing a cyclic neural network or a long-term and short-term memory network model for processing time series data and monitoring the running state of equipment;
Classifying and predicting equipment faults based on the extracted features by using an ensemble learning algorithm; the integrated learning algorithm is a random forest or gradient lifting tree;
704 Dividing the processed data into a training set and a testing set;
training the constructed model by using a training set, and optimizing the performance of the model by adjusting the model parameters and the super parameters of the learning rate;
evaluating the model by using a cross verification technology, and selecting the optimal model parameter configuration to obtain a trained fault diagnosis and abnormality processing model;
705 Using the test set to evaluate the accuracy, recall rate and F1 score index of the system;
optimizing the model according to the evaluation result, including adjusting the model structure, increasing the feature dimension and optimizing the super-parameters;
False alarm and missing alarm in actual operation are used as feedback for continuously improving a model and a data acquisition strategy so as to update the model regularly and keep a good running state of the system;
When fault diagnosis and exception handling are required, the robot platform calls a trained fault diagnosis and exception handling model, transformer substation equipment data acquired in real time are accessed into the robot platform, the real-time data are subjected to feature extraction and engineering operation identical to those of the training stage, and the extracted features are input into the trained model for real-time fault analysis and prediction; and generating an equipment fault early warning signal according to the output result of the model and a preset threshold value, and timely notifying related personnel to process.
CN202410083037.9A 2024-01-19 2024-01-19 Intelligent autonomous patrol system and method for transformer substation based on patrol path Pending CN118137355A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410083037.9A CN118137355A (en) 2024-01-19 2024-01-19 Intelligent autonomous patrol system and method for transformer substation based on patrol path

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410083037.9A CN118137355A (en) 2024-01-19 2024-01-19 Intelligent autonomous patrol system and method for transformer substation based on patrol path

Publications (1)

Publication Number Publication Date
CN118137355A true CN118137355A (en) 2024-06-04

Family

ID=91235027

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410083037.9A Pending CN118137355A (en) 2024-01-19 2024-01-19 Intelligent autonomous patrol system and method for transformer substation based on patrol path

Country Status (1)

Country Link
CN (1) CN118137355A (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118381194A (en) * 2024-06-21 2024-07-23 苏电华瑞科技有限公司 A remote intelligent inspection system for substations
CN118504810A (en) * 2024-07-19 2024-08-16 福州能汇电力设计有限公司 A transmission line intelligent inspection and optimization system
CN118690980A (en) * 2024-08-28 2024-09-24 国网山东省电力公司微山县供电公司 A method and system for evaluating the operation status of a distribution station based on ensemble learning
CN118809610A (en) * 2024-08-16 2024-10-22 南京干垠科技有限公司 An intelligent robot control system for substation inspection
CN118859928A (en) * 2024-06-20 2024-10-29 宜兴市宜宏米业有限责任公司 A self-avoiding obstacle robot remote control system based on rice production
CN118914727A (en) * 2024-10-09 2024-11-08 南京江行联加智能科技有限公司 Transformer substation live detection robot data anomaly detection method
CN118962273A (en) * 2024-06-27 2024-11-15 国网江苏省电力有限公司淮安供电分公司 Electrical equipment leakage detection system of transformer substation
CN119543456A (en) * 2025-01-21 2025-02-28 杭州继高电力技术有限公司 Distribution network automatic intelligent detection system and method

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118859928A (en) * 2024-06-20 2024-10-29 宜兴市宜宏米业有限责任公司 A self-avoiding obstacle robot remote control system based on rice production
CN118381194A (en) * 2024-06-21 2024-07-23 苏电华瑞科技有限公司 A remote intelligent inspection system for substations
CN118962273A (en) * 2024-06-27 2024-11-15 国网江苏省电力有限公司淮安供电分公司 Electrical equipment leakage detection system of transformer substation
CN118504810A (en) * 2024-07-19 2024-08-16 福州能汇电力设计有限公司 A transmission line intelligent inspection and optimization system
CN118809610A (en) * 2024-08-16 2024-10-22 南京干垠科技有限公司 An intelligent robot control system for substation inspection
CN118809610B (en) * 2024-08-16 2025-01-24 南京干垠科技有限公司 An intelligent robot control system for substation inspection
CN118690980A (en) * 2024-08-28 2024-09-24 国网山东省电力公司微山县供电公司 A method and system for evaluating the operation status of a distribution station based on ensemble learning
CN118914727A (en) * 2024-10-09 2024-11-08 南京江行联加智能科技有限公司 Transformer substation live detection robot data anomaly detection method
CN119543456A (en) * 2025-01-21 2025-02-28 杭州继高电力技术有限公司 Distribution network automatic intelligent detection system and method

Similar Documents

Publication Publication Date Title
CN118137355A (en) Intelligent autonomous patrol system and method for transformer substation based on patrol path
CN117853078B (en) Unmanned aerial vehicle-based dynamic safety alarm system and method for construction site of building engineering
Kakolu et al. Autonomous Robotics in Field Operations: A Data-Driven Approach to Optimize Performance and Safety
CN108189043B (en) Inspection method and inspection robot system applied to high-speed rail machine room
CN112213979A (en) Intelligent robot inspection system and method for station
CN118096131B (en) Operation and maintenance inspection method based on electric power scene model
CN110908370A (en) Unmanned inspection task planning method and system for thermal power plant
AU2020102181A4 (en) An intelligent recognition system and method of tunnel structure health based on robot vision recognition
CN117806355A (en) Control method and system for electric power line inspection unmanned aerial vehicle
CN117277592B (en) Protection switching method for monitoring high-voltage circuit signals
CN112650272B (en) 5G-based UAV inspection information perception method and perception system in coal mines
CN118734231B (en) Intelligent power plant inspection system based on large model
CN118966809A (en) A safe and intelligent control system for power operation sites
CN116512273A (en) Intelligent motion control method and system for inspection robot
CN117572863A (en) Path optimization method and system for substation robot
CN117235443A (en) Electric power operation safety monitoring method and system based on edge AI
CN117975713A (en) Intelligent traffic guiding management system for industrial upstairs
CN118196993A (en) Deep learning-based personnel and smoke and fire recognition system and device for photovoltaic factory
CN119146978A (en) Intelligent inspection robot and monitoring system
CN118117487B (en) Multidimensional three-dimensional monitoring system for power transmission line unplanned operation
CN117589177B (en) Autonomous navigation method based on industrial large model
CN118034343A (en) Inspection method and system for remote unmanned machine room equipment
CN116961237A (en) Intelligent monitoring system for power distribution safety operation
CN214376017U (en) Power equipment fault inspection system
CN118918732B (en) Traffic running risk real-time identification method based on low-altitude unmanned aerial vehicle

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination