[go: up one dir, main page]

CN118643996B - Operation method of hydraulic engineering property operation management system combined with intelligent sensing equipment - Google Patents

Operation method of hydraulic engineering property operation management system combined with intelligent sensing equipment Download PDF

Info

Publication number
CN118643996B
CN118643996B CN202411125163.2A CN202411125163A CN118643996B CN 118643996 B CN118643996 B CN 118643996B CN 202411125163 A CN202411125163 A CN 202411125163A CN 118643996 B CN118643996 B CN 118643996B
Authority
CN
China
Prior art keywords
data
water quality
water conservancy
conservancy project
facilities
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.)
Active
Application number
CN202411125163.2A
Other languages
Chinese (zh)
Other versions
CN118643996A (en
Inventor
辛星
张民
胡斌
甘贵文
李祺祯
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.)
Jiangxi Shuitou Technology Co ltd
Original Assignee
Jiangxi Shuitou 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 Jiangxi Shuitou Technology Co ltd filed Critical Jiangxi Shuitou Technology Co ltd
Priority to CN202411125163.2A priority Critical patent/CN118643996B/en
Publication of CN118643996A publication Critical patent/CN118643996A/en
Application granted granted Critical
Publication of CN118643996B publication Critical patent/CN118643996B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/10—Pre-processing; Data cleansing
    • G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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 OR CALCULATING; 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
    • G06N3/0475—Generative networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06Q50/08—Construction
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A20/00—Water conservation; Efficient water supply; Efficient water use
    • Y02A20/152—Water filtration

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Mathematical Physics (AREA)
  • Biophysics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Business, Economics & Management (AREA)
  • Multimedia (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • Medical Informatics (AREA)
  • Primary Health Care (AREA)
  • Probability & Statistics with Applications (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Databases & Information Systems (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)

Abstract

本发明公开了一种结合智能感知设备的水利工程物业化运行管理系统的运行方法，包括S1、实时监测工程设施和设备的运行状态；S2、利用无线通信技术将监测数据传输到中央管理平台；S3、在中央管理平台对数据进行清洗、格式化和去噪处理；S4、将处理后的数据存储在大数据存储系统中，并进行深度分析；S5、通过故障预测、状态评估和生成维护建议提供实时监控报告；S6、自动触发报警机制并通知维护人员；S7、提供数据可视化功能，展示实时状态和历史数据；S8、集成工程巡查、设备巡查、打捞作业和水质检测功能，通过平台统一管理和协调。本发明不仅可以精确评估设施的健康状态，还能提前预测可能出现的故障，提供科学维护建议，确保设施长期稳定运行。

The present invention discloses an operation method of a water conservancy project property operation management system combined with intelligent sensing equipment, including S1, real-time monitoring of the operation status of engineering facilities and equipment; S2, using wireless communication technology to transmit monitoring data to a central management platform; S3, cleaning, formatting and denoising the data on the central management platform; S4, storing the processed data in a large data storage system and performing in-depth analysis; S5, providing real-time monitoring reports through fault prediction, status evaluation and generating maintenance suggestions; S6, automatically triggering an alarm mechanism and notifying maintenance personnel; S7, providing data visualization functions to display real-time status and historical data; S8, integrating engineering inspections, equipment inspections, salvage operations and water quality testing functions, and unified management and coordination through a platform. The present invention can not only accurately evaluate the health status of facilities, but also predict possible faults in advance, provide scientific maintenance suggestions, and ensure long-term stable operation of facilities.

Description

Operation method of hydraulic engineering property operation management system combined with intelligent sensing equipment
Technical Field
The invention relates to the technical field of hydraulic engineering, in particular to an operation method of a hydraulic engineering property operation management system combined with intelligent sensing equipment.
Background
Along with the development of social economy and the acceleration of urban progress, the hydraulic engineering has more and more important roles in flood control, drought resistance, irrigation, water supply, power generation and the like. However, the traditional hydraulic engineering management mode mainly depends on manual inspection and periodical maintenance, and has various problems and defects, so that the requirements of high-efficiency, safe and intelligent management of the modern hydraulic engineering are difficult to meet.
First, manual inspection in the traditional hydraulic engineering management mode has obvious limitations. The manual inspection period is longer, real-time monitoring cannot be achieved, problems cannot be found and processed in time, and the safety operation of hydraulic engineering facilities can be threatened. Meanwhile, the monitoring precision of manual inspection is low, and the manual inspection is limited by manpower and technical means, so that the running states of engineering facilities and equipment cannot be comprehensively and accurately acquired. For example, in the inspection of critical facilities such as dams and embankments, it is difficult to comprehensively and systematically evaluate the health conditions of the facilities by means of manual visual inspection and simple instrument detection.
Second, equipment inspection also faces many challenges. The running states of the water pump, the gate, the drainage system and other equipment are directly related to the normal running of the hydraulic engineering. Traditional equipment inspection mode mainly relies on manual detection and periodic maintenance, lacks real-time monitoring and fault prediction means, leads to equipment failure unable in time discovery and handling, influences hydraulic engineering's overall operation efficiency and security.
In addition, the water salvage operation is an important content in hydraulic engineering management, and the traditional mode mainly depends on manual and mechanical equipment. The manual salvage operation has low efficiency and high risk, is limited by environmental and climatic conditions, and is difficult to ensure the timeliness and effectiveness of the salvage operation. Especially under the condition of poor water quality and deeper water area, the traditional salvage operation mode is difficult to meet the actual requirements.
Finally, water quality detection is used as a key link in hydraulic engineering management, and the traditional mode mainly relies on manual sampling and laboratory detection. The method is long in time consumption and high in cost, and real-time monitoring and rapid assessment of water quality are difficult to realize, water quality change cannot be found and dealt with in time, and the water quality management effect of hydraulic engineering is affected.
In summary, the conventional hydraulic engineering management method has the problems of untimely monitoring, low monitoring precision, low management efficiency, untimely response and the like, and is difficult to meet the requirements of efficient, safe and intelligent management of the modern hydraulic engineering. Therefore, there is a need for a hydraulic engineering property operation management system combining intelligent sensing equipment and advanced information technology, so as to realize comprehensive, real-time and intelligent management of hydraulic engineering and improve management efficiency and safety.
Disclosure of Invention
The invention aims to provide an operation method of a hydraulic engineering property operation management system combined with intelligent sensing equipment, which not only can accurately evaluate the health state of facilities, but also can predict possible faults in advance, provide scientific maintenance suggestions and ensure long-term stable operation of the facilities.
According to the embodiment of the invention, the operation method of the hydraulic engineering property operation management system combined with the intelligent sensing equipment comprises the following steps:
s1, installing a plurality of intelligent sensing devices in hydraulic engineering facilities, wherein the intelligent sensing devices comprise vibration sensors, displacement sensors and water quality sensors and are used for monitoring the running states of the engineering facilities and the devices in real time and constructing a hydraulic engineering running data set;
s2, transmitting the hydraulic engineering operation data set to a central management platform in real time by utilizing a wireless communication technology;
S3, performing preliminary processing on the received hydraulic engineering operation data set in the central management platform, wherein the preliminary processing comprises data cleaning, data formatting and denoising;
S4, storing the processed hydraulic engineering operation data set in a big data storage system, and carrying out deep analysis and processing on the hydraulic engineering operation data set by utilizing a big data analysis technology and an artificial intelligence algorithm;
S5, performing fault prediction, state evaluation and maintenance suggestion generation on the analyzed data, and providing real-time monitoring reports and management suggestions;
s6, the system automatically triggers an alarm mechanism according to the monitoring data and the analysis result, informs relevant maintenance personnel, and generates an alarm and a maintenance record;
s7, providing a data visualization function on the management platform, and displaying the real-time state, the historical data and the analysis result of the hydraulic engineering for the manager to review and make a decision;
S8, integrating engineering inspection, equipment inspection, salvage operation and water quality detection function modules by the system, and managing and coordinating the modules through a platform;
S9, the engineering inspection module monitors the structural state and the running condition of facilities in real time through intelligent sensing equipment arranged on the dam, the embankment and the channel facilities;
s10, an equipment inspection module monitors operation parameters of equipment in real time through intelligent sensing equipment arranged on water pumps, gates and drainage system equipment, and evaluates equipment states;
s11, a salvage operation module utilizes an intelligent robot technology to be provided with a camera and a sensor, recognizes sundries in water through an image recognition and processing technology, and performs automatic salvage and cleaning;
and S12, the water quality detection module acquires water quality parameters in real time through a water quality sensor arranged in a designated water area, analyzes and evaluates the data and provides water quality report and early warning information.
Optionally, the step S1 specifically includes:
s11, installing a plurality of intelligent sensing devices in hydraulic engineering facilities, wherein the intelligent sensing devices comprise a vibration sensor, a displacement sensor and a water quality sensor;
s12, the vibration sensor is arranged on structural facilities such as a dam, a dyke and a channel and is used for monitoring vibration data of the structural facilities in real time to generate a vibration data set :
;
Wherein, Representing vibration data collected for the nth time;
S13, installing a displacement sensor on structural facilities such as a dam, a dyke and a channel, and the like, and monitoring displacement data of the structural facilities in real time to generate a displacement data set :
;
Wherein, Representing displacement data acquired for the nth time;
s14, installing a water quality sensor in a designated water area for monitoring water quality parameters in real time to generate a water quality data set :
;
Wherein, Representing the water quality data collected for the nth time;
s15, combining the vibration data set, the displacement data set and the water quality data set to construct a hydraulic engineering operation data set :
。
Optionally, the step S3 specifically includes:
S31, hydraulic engineering operation data set transmitted to central management platform Performing data cleaning to remove abnormal values and invalid data, and generating a hydraulic engineering operation data set after cleaning;
S32, cleaning the hydraulic engineering operation data setData formatting is carried out, data of different sensors are uniformly converted into a standard format, and a formatted hydraulic engineering operation data set is generated;
S33, formatting hydraulic engineering operation data setDenoising, namely removing noise and interference signals in the data to generate a denoising hydraulic engineering operation data set;
S34, combining the hydraulic engineering operation data sets after the cleaning, formatting and denoising treatment to construct a hydraulic engineering operation data set after the preliminary treatment。
Optionally, the step S4 specifically includes:
s41, a hydraulic engineering operation data set after preliminary treatment The method comprises the steps of storing in a big data storage system, wherein the big data storage system comprises a distributed file system and a distributed database;
;
Wherein, 、AndRespectively representing a vibration data set, a displacement data set and a water quality data set in the ith acquisition period, wherein N represents the total number of the acquisition periods;
S42, utilizing a self-adaptive multi-scale structural health monitoring algorithm to monitor and evaluate the structural health state of the hydraulic engineering facility in real time;
;
wherein H (t) represents a structural health state, Representing the weight of the sensor(s),Structural health data representing an ith sensor at time t, N representing the number of sensors;
s43, performing fault prediction on hydraulic engineering facilities by using a fault prediction algorithm based on a space-time diagram convolutional network;
;
Wherein, A failure prediction value representing time t +1,Representing the adjacency matrix of the kth figure,The picture convolution kernel representing the k-th layer,The input characteristic representing the time t is indicated,Representing the weight matrix of the k-th layer,Representing an activation function;
s44, monitoring and early warning the water quality by utilizing a water quality monitoring and pollution early warning algorithm based on a dynamic Bayesian network;
;
Wherein, Indicating the water quality state at time tIs used to determine the posterior probability of (1),The water quality state at time t-1 is indicated,Sensor data representing time t;
s45, optimizing resource scheduling of hydraulic engineering facilities by using a reinforcement learning-based facility optimizing scheduling algorithm;
;
Wherein, The optimal policy is represented by a set of criteria,Representing the discount factor(s),A reward representing time t; representing a policy;
s46, combining the results of big data analysis and artificial intelligence algorithm processing to construct a hydraulic engineering operation management decision support data set :
。
Wherein, The prediction data set generated based on the sequence prediction model is mainly used for predicting the future state of hydraulic engineering facilities;
the analysis result based on the Bayesian network model is mainly used for water quality monitoring and pollution early warning, and the probability relation among all factors is provided;
representing a decision dataset generated by fault prediction and state assessment for supporting maintenance and management decisions for hydraulic engineering;
Representing a result dataset based on spatial analysis, primarily for spatially correlated data analysis;
the data set based on simulation is mainly used for simulating the influence of different management strategies on hydraulic engineering facilities;
representing an analysis data set based on multi-mode fusion, and generating comprehensive decision support data by combining multiple data sources and models;
and the optimization strategy set generated based on the reinforcement learning algorithm is represented and used for dynamic scheduling and optimization management of facility resources.
Optionally, the step S5 specifically includes:
s51, performing fault prediction on the processed hydraulic engineering operation data set, and generating a fault prediction result set by using a fault prediction algorithm based on a multi-layer attention mechanism long-term and short-term memory network:
;
Wherein, A failure prediction value representing time t +1,、、The weight matrix is represented by a matrix of weights,、、The term of the bias is indicated,The hidden state is indicated and the hidden state is indicated,The input characteristics are represented as such,Representing an element-by-element multiplication,The state of the cell is indicated and,The global attention weight is represented as such,The local attention weight is indicated as such,Representing an attention matrix, and optimizing parameters by combining the data characteristics of hydraulic engineering;
s52, performing state evaluation on the analyzed data, and generating a state evaluation result set by using a state evaluation algorithm of a support vector machine based on the self-adaptive kernel function:
;
;
Wherein, The state evaluation result of the hydraulic engineering facility is represented,Representing the lagrangian multiplier and,Representing the class of the i-th sample,Representing an adaptive kernel function for computing an input x and a support vectorSimilarity between, b represents the bias term,The adaptive weights are represented by the weights,I is the number of support vectors, m is the number of kernel functions, and the number of the basic kernel functions included in the kernel function combination is represented;
S53, generating maintenance suggestions, and generating a maintenance suggestion set by using a maintenance suggestion generation algorithm based on the multi-mode fusion random forest :
;
Where k represents the number of modalities, referring to the number of different data sources or feature sets;
Represents maintenance advice, N represents the number of trees, Representing the prediction of the input x by the ith tree,The modal weight is represented as a function of the modal weight,Representing the prediction result of the kth modality;
s54, generating a real-time monitoring report by combining the fault prediction result, the state evaluation result and the maintenance suggestion Management advice:
;
;
Wherein, Representing a real-time monitoring report, and providing a comprehensive facility running state report by combining fault prediction and state evaluation results; representing management advice, providing optimized management decision support by weighted summing of maintenance advice, Is the result of the fault prediction.
Optionally, the step S8 specifically includes:
s81, integrating an engineering inspection module by the system, analyzing and identifying inspection images of engineering facilities by using intelligent sensing equipment, and generating an inspection report;
s82, a system integrated equipment inspection module monitors operation parameters of equipment in real time through the Internet of things technology and generates an equipment state report;
S83, a system integrated salvage operation module is used for identifying and cleaning sundries in the water area by utilizing an intelligent salvage robot, and a salvage operation report is generated;
s84, a system integrated water quality detection module detects and analyzes water quality parameters by using a chemical sensor and a data fusion technology to generate a water quality report;
S85, unified management and coordination are carried out on engineering inspection, equipment inspection, salvage operation and water quality detection functional modules through a management platform, and comprehensive management reports and coordination suggestions are generated.
The beneficial effects of the invention are as follows:
According to the invention, the vibration sensor, the displacement sensor and the water quality sensor are arranged in the hydraulic engineering facilities, so that the hydraulic engineering facilities and equipment are monitored in real time and data are acquired. The acquired data are transmitted to the central management platform in real time by utilizing a wireless communication technology, so that the timeliness of monitoring and the accuracy of the data are ensured. The collected data is analyzed and predicted in real time by the fault prediction algorithm based on the multi-layer attention mechanism long-term memory network, so that the accuracy and the advance of fault detection are improved, and the risk of sudden faults is obviously reduced.
The system carries out state evaluation on data by utilizing a support vector machine algorithm based on a self-adaptive kernel function, and comprehensively evaluates the running state of hydraulic engineering facilities and generates maintenance suggestions by combining a maintenance suggestion generation algorithm based on a multi-mode fusion random forest. By applying the intelligent algorithms, the system not only can accurately evaluate the health state of the facility, but also can predict possible faults in advance, provide scientific maintenance suggestions and ensure the long-term stable operation of the facility.
The invention integrates engineering inspection, equipment inspection, salvage operation and water quality detection function modules, manages and coordinates through a unified platform, and generates comprehensive management reports and coordination suggestions by utilizing big data analysis technology and artificial intelligent algorithm, thereby realizing efficient management and unified coordination of each function module. Through an image recognition algorithm based on a deep convolutional neural network and an intelligent salvage robot, the system can automatically recognize and process problems in hydraulic engineering, and management efficiency and safety are improved.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
fig. 1 is a flowchart of an operation method of a hydraulic engineering property operation management system combining intelligent sensing equipment.
Detailed Description
The invention will now be described in further detail with reference to the accompanying drawings. The drawings are simplified schematic representations which merely illustrate the basic structure of the invention and therefore show only the structures which are relevant to the invention.
Referring to fig. 1, an operation method of a hydraulic engineering property operation management system combined with an intelligent sensing device includes the following steps:
s1, installing a plurality of intelligent sensing devices in hydraulic engineering facilities, wherein the intelligent sensing devices comprise vibration sensors, displacement sensors and water quality sensors and are used for monitoring the running states of the engineering facilities and the devices in real time to construct a hydraulic engineering running data set;
s2, transmitting the hydraulic engineering operation data set to a central management platform in real time by utilizing a wireless communication technology;
S3, performing preliminary processing on the received hydraulic engineering operation data set in the central management platform, wherein the preliminary processing comprises data cleaning, data formatting and denoising;
S4, storing the processed hydraulic engineering operation data set in a big data storage system, and carrying out deep analysis and processing on the hydraulic engineering operation data set by utilizing a big data analysis technology and an artificial intelligence algorithm;
S5, performing fault prediction, state evaluation and maintenance suggestion generation on the analyzed data, and providing real-time monitoring reports and management suggestions;
s6, the system automatically triggers an alarm mechanism according to the monitoring data and the analysis result, informs relevant maintenance personnel, and generates an alarm and a maintenance record;
s7, providing a data visualization function on the management platform, and displaying the real-time state, the historical data and the analysis result of the hydraulic engineering for the manager to review and make a decision;
S8, integrating engineering inspection, equipment inspection, salvage operation and water quality detection function modules by the system, and managing and coordinating the modules through a platform;
S9, the engineering inspection module monitors the structural state and the running condition of facilities in real time through intelligent sensing equipment arranged on the dam, the embankment and the channel facilities;
s10, an equipment inspection module monitors operation parameters of equipment in real time through intelligent sensing equipment arranged on water pumps, gates and drainage system equipment, and evaluates equipment states;
s11, a salvage operation module utilizes an intelligent robot technology to be provided with a camera and a sensor, recognizes sundries in water through an image recognition and processing technology, and performs automatic salvage and cleaning;
and S12, the water quality detection module acquires water quality parameters in real time through a water quality sensor arranged in a designated water area, analyzes and evaluates the data and provides water quality report and early warning information.
In this embodiment, step S1 specifically includes:
S11, installing a plurality of intelligent sensing devices in hydraulic engineering facilities, wherein the intelligent sensing devices comprise a vibration sensor, a displacement sensor and a water quality sensor;
s12, the vibration sensor is arranged on structural facilities such as a dam, a dyke and a channel and is used for monitoring vibration data of the structural facilities in real time to generate a vibration data set :
;
Wherein, Representing vibration data collected for the nth time;
S13, installing a displacement sensor on structural facilities such as a dam, a dyke and a channel, and the like, and monitoring displacement data of the structural facilities in real time to generate a displacement data set :
;
Wherein, Representing displacement data acquired for the nth time;
s14, installing a water quality sensor in a designated water area for monitoring water quality parameters in real time to generate a water quality data set :
;
Wherein, Representing the water quality data collected for the nth time;
s15, combining the vibration data set, the displacement data set and the water quality data set to construct a hydraulic engineering operation data set :
。
In this embodiment, S3 specifically includes:
S31, hydraulic engineering operation data set transmitted to central management platform Performing data cleaning to remove abnormal values and invalid data, and generating a hydraulic engineering operation data set after cleaning;
S32, cleaning the hydraulic engineering operation data setData formatting is carried out, data of different sensors are uniformly converted into a standard format, and a formatted hydraulic engineering operation data set is generated;
S33, formatting hydraulic engineering operation data setDenoising, namely removing noise and interference signals in the data to generate a denoising hydraulic engineering operation data set;
S34, combining the hydraulic engineering operation data sets after the cleaning, formatting and denoising treatment to construct a hydraulic engineering operation data set after the preliminary treatment。
In this embodiment, S4 specifically includes:
s41, a hydraulic engineering operation data set after preliminary treatment The method comprises the steps of storing in a big data storage system, wherein the big data storage system comprises a distributed file system and a distributed database;
;
Wherein, 、AndRespectively representing a vibration data set, a displacement data set and a water quality data set in the ith acquisition period, wherein N represents the total number of the acquisition periods;
S42, utilizing a self-adaptive multi-scale structural health monitoring algorithm to monitor and evaluate the structural health state of the hydraulic engineering facility in real time;
;
wherein H (t) represents a structural health state, Representing the weight of the sensor(s),Structural health data representing an ith sensor at time t, N representing the number of sensors;
s43, performing fault prediction on hydraulic engineering facilities by using a fault prediction algorithm based on a space-time diagram convolutional network;
;
Wherein, A failure prediction value representing time t +1,Representing the adjacency matrix of the kth figure,The picture convolution kernel representing the k-th layer,The input characteristic representing the time t is indicated,Representing the weight matrix of the k-th layer,Representing an activation function;
s44, monitoring and early warning the water quality by utilizing a water quality monitoring and pollution early warning algorithm based on a dynamic Bayesian network;
;
Wherein, Indicating the water quality state at time tIs used to determine the posterior probability of (1),The water quality state at time t-1 is indicated,Sensor data representing time t;
s45, optimizing resource scheduling of hydraulic engineering facilities by using a reinforcement learning-based facility optimizing scheduling algorithm;
;
Wherein, The optimal policy is represented by a set of criteria,Representing the discount factor(s),A reward representing time t; representing a policy;
s46, combining the results of big data analysis and artificial intelligence algorithm processing to construct a hydraulic engineering operation management decision support data set :
。
Wherein, Representing a prediction dataset generated based on the sequence prediction model for predicting a future state of the hydraulic engineering facility;
the analysis result based on the Bayesian network model is shown and used for water quality monitoring and pollution early warning, and probability relations among all factors are provided;
representing a decision dataset generated by fault prediction and state assessment for supporting maintenance and management decisions for hydraulic engineering;
representing a result dataset based on the spatial analysis for spatially correlated data analysis;
the data set based on simulation is used for simulating the influence of different management strategies on hydraulic engineering facilities;
representing an analysis data set based on multi-mode fusion, and generating comprehensive decision support data by combining multiple data sources and models;
and the optimization strategy set generated based on the reinforcement learning algorithm is represented and used for dynamic scheduling and optimization management of facility resources.
In this embodiment, S5 specifically includes:
s51, performing fault prediction on the processed hydraulic engineering operation data set, and generating a fault prediction result set by using a fault prediction algorithm based on a multi-layer attention mechanism long-term and short-term memory network:
;
Wherein, A failure prediction value representing time t +1,、、The weight matrix is represented by a matrix of weights,、、The term of the bias is indicated,The hidden state is indicated and the hidden state is indicated,The input characteristics are represented as such,Representing an element-by-element multiplication,The state of the cell is indicated and,The global attention weight is represented as such,The local attention weight is indicated as such,Representing an attention matrix, and optimizing parameters by combining the data characteristics of hydraulic engineering;
s52, performing state evaluation on the analyzed data, and generating a state evaluation result set by using a state evaluation algorithm of a support vector machine based on the self-adaptive kernel function:
;
;
Wherein, The state evaluation result of the hydraulic engineering facility is represented,Representing the lagrangian multiplier and,Representing the class of the i-th sample,Representing an adaptive kernel function for computing an input x and a support vectorSimilarity between, b represents the bias term,The adaptive weights are represented by the weights,Representing the j-th basic kernel function, l being the number of support vectors, representing the number of support vectors for state evaluation, m being the number of kernel functions, representing the number of basic kernel functions contained in the kernel function combination;
s53, generating maintenance suggestions, and generating a maintenance suggestion set by using a maintenance suggestion generation algorithm based on a multi-mode fusion random forest:
;
Where k represents the number of modalities, referring to the number of different data sources or feature sets;
Represents maintenance advice, N represents the number of trees, Representing the prediction of the input x by the ith tree,The modal weight is represented as a function of the modal weight,Representing the prediction result of the kth modality;
s54, generating a real-time monitoring report by combining the fault prediction result, the state evaluation result and the maintenance suggestion Management advice:
;
;
Wherein, Representing a real-time monitoring report, and providing a comprehensive facility running state report by combining fault prediction and state evaluation results; representing management advice, providing optimized management decision support by weighted summing of maintenance advice, Is the result of the fault prediction.
In this embodiment, S8 specifically includes:
s81, integrating an engineering inspection module by the system, analyzing and identifying inspection images of engineering facilities by using intelligent sensing equipment, and generating an inspection report;
s82, a system integrated equipment inspection module monitors operation parameters of equipment in real time through the Internet of things technology and generates an equipment state report;
S83, a system integrated salvage operation module is used for identifying and cleaning sundries in the water area by utilizing an intelligent salvage robot, and a salvage operation report is generated;
s84, a system integrated water quality detection module detects and analyzes water quality parameters by using a chemical sensor and a data fusion technology to generate a water quality report;
S85, unified management and coordination are carried out on engineering inspection, equipment inspection, salvage operation and water quality detection functional modules through a management platform, and comprehensive management reports and coordination suggestions are generated.
Example 1
The embodiment takes a main flood prevention dam of a coastal city as a background, the dam is about 5 kilometers long and 30 meters high, and the dam is mainly used for preventing flood caused by sea tides and storm water. Because of its importance, the management and maintenance requirements of the dam are extremely high. However, the traditional management method mainly relies on manual inspection and periodic detection, and has the problems of untimely monitoring, low monitoring precision, low management efficiency and the like. To solve these problems, the present embodiment applies the hydraulic engineering property operation management system in combination with the intelligent perception device to daily management and maintenance of the dam.
In this embodiment, a variety of intelligent sensing devices including vibration sensors, displacement sensors, and water quality sensors are first installed at strategic locations on the dam. These sensors are used to monitor in real time the structural status of the dam, the equipment operation and the water quality changes. The concrete sensor arrangement is that vibration sensors are mainly arranged at the top and the bottom of the dam and used for monitoring the vibration condition of the dam, displacement sensors are arranged at the side wall and the bottom of the dam and used for monitoring the displacement and deformation condition of the dam, and water quality sensors are arranged in water bodies near the dam and used for monitoring water quality parameters such as pH value, dissolved oxygen, turbidity and the like.
Data collected by the sensors are transmitted to the central management platform in real time through a wireless communication technology. On the platform, the data is subjected to preliminary processing including data cleansing, data formatting and denoising, and then stored in a large data storage system. The system monitors and evaluates the structural health state of the dam in real time and predicts possible faults by utilizing a self-adaptive multi-scale structural health monitoring algorithm and a fault prediction algorithm based on a space-time diagram convolution network. And (3) carrying out real-time analysis and early warning on the water quality data based on a water quality monitoring and pollution early warning algorithm of a dynamic Bayesian network. In addition, the system also adopts a facility optimization scheduling algorithm based on reinforcement learning to optimize the resource scheduling and management strategy of the dam.
During a 6 month commissioning period, the system comprehensively monitors and manages the operation of the dam. The system continuously collects and analyzes data 24 hours a day, and generates real-time monitoring reports and management suggestions. In the engineering inspection aspect, the system utilizes an image recognition algorithm of a deep convolutional neural network to analyze and recognize inspection images of the dam, and timely discovers and processes a plurality of small cracks and displacement anomalies. In the equipment inspection aspect, the system monitors the operation parameters of the equipment in real time through the technology of the Internet of things, and discovers and prevents the faults of the water pump twice. In the aspect of salvaging operation, the intelligent salvaging robot cleans a large amount of floaters and sediments under the guidance of a system, and ensures the cleanliness and smoothness of the water area around the dam. In the aspect of water quality detection, the system utilizes a chemical sensor and a data fusion technology to detect and analyze water quality parameters in real time, finds and pre-warns about a water quality pollution event, and timely takes countermeasures. Specific data are shown in table 1 below:
table 1 comparison data of hydraulic engineering Property operation management System
As can be seen from the table 1, in the aspect of monitoring timeliness, the monitoring period of the traditional manual inspection is once per week, the monitoring timeliness is 7 days, and the system realizes 24-hour uninterrupted real-time monitoring, and the monitoring timeliness is 0 days. In the aspect of monitoring precision, the monitoring precision of the traditional manual inspection is about 90 percent, and is mainly limited by the precision and frequency of manual detection, and the system realizes 99 percent of monitoring precision through intelligent sensing equipment and advanced algorithm. In terms of fault prediction and prevention, the number of preventive maintenance times per year is 4 in the traditional method, and the system performs fault prediction through an intelligent algorithm, so that 8 equipment faults are successfully prevented during test operation. In the aspect of salvaging operation efficiency, the traditional manual salvaging work efficiency is about 100 kg of sundries per day, and the intelligent salvaging robot is about 200 kg of sundries per day, so that the work efficiency is doubled. In the aspect of water quality detection and early warning, the water quality detection frequency of the traditional method is once a month, the early warning timeliness is 30 days, and the system realizes real-time water quality detection and early warning, and the early warning timeliness is 0 day.
In conclusion, by applying the embodiment, monitoring timeliness, monitoring precision and management efficiency of the dam are remarkably improved, real-time fault prediction and water quality early warning are realized, and safe operation of the dam is effectively ensured. By comparing with the traditional method, the method has obvious advantages in all aspects, and the practicability and the novelty of the method are fully verified.
According to the invention, the vibration sensor, the displacement sensor and the water quality sensor are arranged in the hydraulic engineering facilities, so that the hydraulic engineering facilities and equipment are monitored in real time and data are acquired. The acquired data are transmitted to the central management platform in real time by utilizing a wireless communication technology, so that the timeliness of monitoring and the accuracy of the data are ensured. The collected data is analyzed and predicted in real time by the fault prediction algorithm based on the multi-layer attention mechanism long-term memory network, so that the accuracy and the advance of fault detection are improved, and the risk of sudden faults is obviously reduced.
The system carries out state evaluation on data by utilizing a support vector machine algorithm based on a self-adaptive kernel function, and comprehensively evaluates the running state of hydraulic engineering facilities and generates maintenance suggestions by combining a maintenance suggestion generation algorithm based on a multi-mode fusion random forest. By applying the intelligent algorithms, the system not only can accurately evaluate the health state of the facility, but also can predict possible faults in advance, provide scientific maintenance suggestions and ensure the long-term stable operation of the facility.
The invention integrates engineering inspection, equipment inspection, salvage operation and water quality detection function modules, manages and coordinates through a unified platform, and generates comprehensive management reports and coordination suggestions by utilizing big data analysis technology and artificial intelligent algorithm, thereby realizing efficient management and unified coordination of each function module. Through an image recognition algorithm based on a deep convolutional neural network and an intelligent salvage robot, the system can automatically recognize and process problems in hydraulic engineering, and management efficiency and safety are improved.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should make equivalent substitutions or modifications according to the technical scheme of the present invention and the inventive concept thereof, and should be covered by the scope of the present invention.

Claims (3)

1.一种结合智能感知设备的水利工程物业化运行管理系统，其特征在于，包括如下步骤：1. A water conservancy project property operation management system combined with intelligent sensing equipment, characterized in that it includes the following steps: S1、在水利工程设施中安装多个智能感知设备，所述智能感知设备包括振动传感器、位移传感器和水质传感器，用于实时监测工程设施和设备的运行状态，构建水利工程运行数据集；S1. Install multiple intelligent sensing devices in water conservancy project facilities, wherein the intelligent sensing devices include vibration sensors, displacement sensors and water quality sensors, which are used to monitor the operating status of engineering facilities and equipment in real time and construct a water conservancy project operation data set; S2、利用无线通信技术将水利工程运行数据集实时传输到中央管理平台；S2, using wireless communication technology to transmit water conservancy project operation data sets to the central management platform in real time; S3、在中央管理平台对接收到的水利工程运行数据集进行初步处理，包括数据清洗、数据格式化和去噪处理；S3. Perform preliminary processing on the received water conservancy project operation data set on the central management platform, including data cleaning, data formatting and denoising; S4、将处理后的水利工程运行数据集存储在大数据存储系统中，并利用大数据分析技术和人工智能算法对水利工程运行数据集进行深度分析和处理；S4. Store the processed water conservancy project operation data set in a big data storage system, and use big data analysis technology and artificial intelligence algorithms to perform in-depth analysis and processing on the water conservancy project operation data set; S5、对分析处理后的数据进行故障预测、状态评估和维护建议生成，提供实时的监控报告和管理建议；S5. Perform fault prediction, status assessment and maintenance suggestion generation on the analyzed and processed data, and provide real-time monitoring reports and management suggestions; S6、系统根据监测数据和分析结果，自动触发报警机制，通知相关维护人员，并生成报警和维护记录；S6. Based on the monitoring data and analysis results, the system automatically triggers the alarm mechanism, notifies the relevant maintenance personnel, and generates alarm and maintenance records; S7、在管理平台上提供数据可视化功能，展示水利工程的实时状态、历史数据和分析结果，供管理人员查阅和决策；S7. Provide data visualization function on the management platform to display the real-time status, historical data and analysis results of water conservancy projects for management personnel to review and make decisions; S8、系统集成工程巡查、设备巡查、打捞作业和水质检测功能模块，通过平台进行管理和协调；S8, system integration engineering inspection, equipment inspection, salvage operation and water quality testing functional modules are managed and coordinated through the platform; S9、工程巡查模块通过安装在大坝、堤防、渠道设施上的智能感知设备，实时监控设施的结构状态和运行情况；S9, engineering inspection module monitors the structural status and operation of facilities in real time through intelligent sensing devices installed on dams, levees and channel facilities; S10、设备巡查模块通过安装在水泵、闸门、排水系统设备上的智能感知设备，实时监控设备的运行参数，并评估设备状态；S10, the equipment inspection module monitors the operating parameters of the equipment in real time and evaluates the equipment status through the intelligent sensing devices installed on the water pumps, gates, and drainage system equipment; S11、打捞作业模块利用智能机器人技术，配备摄像头和传感器，通过图像识别和处理技术识别水域中的杂物，并进行自动打捞和清理；S11, the salvage operation module uses intelligent robot technology, equipped with cameras and sensors, to identify debris in the water through image recognition and processing technology, and automatically salvage and clean it up; S12、水质检测模块通过安装在指定水域的水质传感器，实时采集水质参数，并对数据进行分析和评估，提供水质报告和预警信息；S12, the water quality detection module collects water quality parameters in real time through water quality sensors installed in designated waters, analyzes and evaluates the data, and provides water quality reports and early warning information; 所述S1具体包括：The S1 specifically includes: S11、在水利工程设施中安装多个智能感知设备，所述智能感知设备包括振动传感器、位移传感器和水质传感器；S11. Install multiple intelligent sensing devices in water conservancy project facilities, wherein the intelligent sensing devices include vibration sensors, displacement sensors and water quality sensors; S12、振动传感器安装在大坝、堤防和渠道等结构设施上，用于实时监测结构设施的振动数据，生成振动数据集：S12. Vibration sensors are installed on structural facilities such as dams, levees and channels to monitor the vibration data of structural facilities in real time and generate vibration data sets. : ； ; 其中，表示第n次采集的振动数据；in, Indicates the vibration data collected for the nth time; S13、位移传感器安装在大坝、堤防和渠道等结构设施上，用于实时监测结构设施的位移数据，生成位移数据集：S13. Displacement sensors are installed on structural facilities such as dams, levees and channels to monitor the displacement data of structural facilities in real time and generate displacement data sets. : ； ; 其中，表示第n次采集的位移数据；in, Indicates the displacement data collected for the nth time; S14、水质传感器安装在指定水域，用于实时监测水质参数，生成水质数据集：S14. Water quality sensors are installed in designated waters to monitor water quality parameters in real time and generate water quality data sets : ； ; 其中，表示第n次采集的水质数据；in, Indicates the water quality data collected for the nth time; S15、将振动数据集、位移数据集和水质数据集组合，构建水利工程运行数据集：S15. Combine the vibration dataset, displacement dataset and water quality dataset to construct a water conservancy project operation dataset : ； ; 所述S3具体包括：The S3 specifically includes: S31、将传输到中央管理平台的水利工程运行数据集进行数据清洗，去除异常值和无效数据，生成清洗后水利工程运行数据集；S31. Water conservancy project operation data set to be transmitted to the central management platform Perform data cleaning, remove outliers and invalid data, and generate a cleaned water conservancy project operation data set ; S32、对清洗后水利工程运行数据集进行数据格式化处理，将不同传感器的数据统一转换为标准格式，生成格式化水利工程运行数据集；S32, water conservancy project operation data set after cleaning Perform data formatting, convert data from different sensors into a standard format, and generate a formatted water conservancy project operation data set ; S33、对格式化水利工程运行数据集进行去噪处理，去除数据中的噪声和干扰信号，生成去噪水利工程运行数据集；S33. Formatting water conservancy project operation data set Perform denoising to remove noise and interference signals in the data and generate a denoised water conservancy project operation data set ; S34、将清洗、格式化和去噪处理后的水利工程运行数据集组合，构建初步处理后的水利工程运行数据集；S34, combining the cleaned, formatted and denoised water conservancy project operation data sets to construct a preliminarily processed water conservancy project operation data set ; 所述S4具体包括：The S4 specifically includes: S41、将初步处理后的水利工程运行数据集存储在大数据存储系统中，所述大数据存储系统包括分布式文件系统和分布式数据库；S41. The water conservancy project operation data set after preliminary processing Storing in a big data storage system, the big data storage system includes a distributed file system and a distributed database; ； ; 其中，、和分别表示第i个采集周期内的振动数据集、位移数据集和水质数据集，N表示采集周期的总数；in, , and They represent the vibration data set, displacement data set and water quality data set in the i-th acquisition cycle respectively, and N represents the total number of acquisition cycles; S42、利用自适应多尺度结构健康监测算法，对水利工程设施的结构健康状态进行实时监测和评估；S42. Use adaptive multi-scale structural health monitoring algorithm to monitor and evaluate the structural health status of water conservancy project facilities in real time; ； ; 其中，H(t)表示结构健康状态，表示传感器权重，表示第i个传感器在时间t的结构健康数据，N表示传感器数量；Where H(t) represents the structural health status, represents the sensor weight, represents the structural health data of the i-th sensor at time t, and N represents the number of sensors; S43、利用基于时空图卷积网络的故障预测算法，对水利工程设施进行故障预测；S43. Use a fault prediction algorithm based on spatiotemporal graph convolutional networks to predict faults in water conservancy project facilities. ； ; 其中，表示时间t+1的故障预测值，表示第k个图的邻接矩阵，表示第k层的图卷积核，表示时间t的输入特征，表示第k层的权重矩阵，表示激活函数；in, represents the fault prediction value at time t+1, represents the adjacency matrix of the k-th graph, represents the graph convolution kernel of the kth layer, represents the input features at time t, represents the weight matrix of the kth layer, represents the activation function; S44、利用基于动态贝叶斯网络的水质监测和污染预警算法，对水质进行监测和预警；S44. Use the water quality monitoring and pollution early warning algorithm based on dynamic Bayesian network to monitor and warn water quality; ； ; 其中，表示在时间t水质状态的后验概率，表示时间t-1的水质状态，表示时间t的传感器数据；in, Indicates the water quality status at time t The posterior probability of represents the water quality status at time t-1, represents the sensor data at time t; S45、利用基于强化学习的设施优化调度算法，优化水利工程设施的资源调度；S45. Optimize the resource scheduling of water conservancy project facilities by using the facility optimization scheduling algorithm based on reinforcement learning; ； ; 其中，表示最优策略，表示折扣因子，表示时间t的奖励；表示策略；in, represents the optimal strategy, represents the discount factor, represents the reward at time t; Representation strategy; S46、将大数据分析和人工智能算法处理后的结果组合，构建水利工程运行管理决策支持数据集：S46. Combine the results of big data analysis and artificial intelligence algorithm processing to build a data set to support water conservancy project operation and management decision-making : ； ; 其中，表示基于序列预测模型生成的预测数据集，用于预测水利工程设施的未来状态；in, Represents a prediction data set generated based on a sequence prediction model, which is used to predict the future status of water conservancy project facilities; 表示基于贝叶斯网络模型的分析结果，用于水质监测和污染预警，提供各因素之间的概率关系； Represents the analysis results based on the Bayesian network model, which is used for water quality monitoring and pollution early warning, and provides the probabilistic relationship between various factors; 表示通过故障预测和状态评估生成的决策数据集，用于支持水利工程的维护和管理决策； It represents the decision dataset generated by fault prediction and status assessment, which is used to support maintenance and management decisions of water conservancy projects; 表示基于空间分析的结果数据集，用于空间相关的数据分析； Represents the result dataset based on spatial analysis, which is used for spatially related data analysis; 表示基于模拟仿真的数据集，用于模拟不同管理策略对水利工程设施的影响； Represents a simulation-based data set used to simulate the impact of different management strategies on water conservancy project facilities; 表示基于多模态融合的分析数据集，结合多种数据源和模型生成综合性决策支持数据； Represents an analytical data set based on multimodal fusion, combining multiple data sources and models to generate comprehensive decision support data; 表示基于强化学习算法生成的优化策略集，用于设施资源的动态调度和优化管理。 Represents the set of optimization strategies generated based on reinforcement learning algorithm, which is used for dynamic scheduling and optimization management of facility resources. 2.根据权利要求1所述的一种结合智能感知设备的水利工程物业化运行管理系统，其特征在于，所述S5具体包括：2. According to the water conservancy project property management system combined with intelligent sensing equipment according to claim 1, it is characterized in that the S5 specifically includes: S51、对处理后的水利工程运行数据集进行故障预测，利用基于多层注意力机制长短期记忆网络的故障预测算法，生成故障预测结果集：S51. Perform fault prediction on the processed water conservancy project operation data set, and use the fault prediction algorithm based on the multi-layer attention mechanism long short-term memory network to generate a fault prediction result set: ； ; 其中，表示时间t+1的故障预测值，、、表示权重矩阵，、、表示偏置项，表示隐藏状态，表示输入特征，表示逐元素乘法，表示单元状态，表示全局注意力权重，表示局部注意力权重，表示注意力矩阵；in, represents the fault prediction value at time t+1, , , represents the weight matrix, , , represents the bias term, Indicates the hidden state, represents the input features, represents element-wise multiplication, Indicates the unit status, represents the global attention weight, represents the local attention weight, represents the attention matrix; S52、对分析处理后的数据进行状态评估，利用基于自适应核函数的支持向量机的状态评估算法，生成状态评估结果集：S52, perform status assessment on the analyzed data, and generate a status assessment result set using a status assessment algorithm of a support vector machine based on an adaptive kernel function: ； ; ； ; 其中，表示水利工程设施的状态评估结果，表示拉格朗日乘数，表示第i个样本的类别，表示自适应核函数，用于计算输入x和支持向量 之间的相似性，b表示偏置项，表示自适应权重，表示第j个基础核函数，l是支持向量的数量，表示用于状态评估的支持向量个数，m是核函数的数量，表示在核函数组合中包含的基础核函数的数量；in, Indicates the status assessment results of water conservancy project facilities. represents the Lagrange multiplier, represents the category of the i-th sample, Represents the adaptive kernel function, which is used to calculate the input x and support vector The similarity between them, b represents the bias term, represents the adaptive weight, represents the jth basic kernel function, l is the number of support vectors, which indicates the number of support vectors used for state evaluation, and m is the number of kernel functions, which indicates the number of basic kernel functions included in the kernel function combination; S53、生成维护建议，利用基于多模态融合随机森林的维护建议生成算法，生成维护建议集：S53, Generate maintenance suggestions, use the maintenance suggestion generation algorithm based on multimodal fusion random forest to generate a maintenance suggestion set : ； ; 其中，k表示模态的数量，指的是不同的数据源或特征集的数量；Among them, k represents the number of modalities, which refers to the number of different data sources or feature sets; 表示维护建议，N表示树的数量，表示第i棵树对输入x的预测结果，表示模态权重，表示第k个模态的预测结果； represents maintenance suggestions, N represents the number of trees, represents the prediction result of the i-th tree for input x, represents the modal weight, represents the prediction result of the kth mode; S54、结合故障预测结果、状态评估结果和维护建议，生成实时的监控报告和管理建议：S54. Generate real-time monitoring reports by combining fault prediction results, status assessment results and maintenance recommendations and management recommendations : ； ; ； ; 其中，表示实时监控报告，结合故障预测和状态评估结果，提供全面的设施运行状态报告；表示管理建议，通过对维护建议进行加权求和，提供优化的管理决策支持，是故障预测结果。in, It represents real-time monitoring reports, which combine fault prediction and status assessment results to provide a comprehensive facility operation status report; Represents management suggestions, and provides optimized management decision support by weighted summation of maintenance suggestions. It is the fault prediction result. 3.根据权利要求1所述的一种结合智能感知设备的水利工程物业化运行管理系统，其特征在于，所述S8具体包括：3. According to the water conservancy project property management system combined with intelligent sensing equipment according to claim 1, it is characterized in that the S8 specifically includes: S81、系统集成工程巡查模块，利用智能感知设备对工程设施的巡查图像进行分析和识别，生成巡查报告；S81, system integrated engineering inspection module, uses intelligent sensing equipment to analyze and identify inspection images of engineering facilities and generate inspection reports; S82、系统集成设备巡查模块，通过物联网技术实时监控设备的运行参数，并生成设备状态报告；S82, system integrated equipment inspection module, real-time monitoring of equipment operating parameters through IoT technology, and generating equipment status reports; S83、系统集成打捞作业模块，利用智能打捞机器人对水域中的杂物进行识别和清理，生成打捞作业报告；S83, the system integrates the salvage operation module, uses the intelligent salvage robot to identify and clean up the debris in the water area, and generates a salvage operation report; S84、系统集成水质检测模块，利用化学传感器和数据融合技术对水质参数进行检测和分析，生成水质报告；S84, system integrated water quality detection module, using chemical sensors and data fusion technology to detect and analyze water quality parameters and generate water quality reports; S85、通过管理平台对工程巡查、设备巡查、打捞作业和水质检测功能模块进行统一管理和协调，生成综合管理报告和协调建议。S85. Through the management platform, unified management and coordination of engineering inspection, equipment inspection, salvage operation and water quality testing functional modules are carried out to generate comprehensive management reports and coordination suggestions.
CN202411125163.2A 2024-08-16 2024-08-16 Operation method of hydraulic engineering property operation management system combined with intelligent sensing equipment Active CN118643996B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411125163.2A CN118643996B (en) 2024-08-16 2024-08-16 Operation method of hydraulic engineering property operation management system combined with intelligent sensing equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411125163.2A CN118643996B (en) 2024-08-16 2024-08-16 Operation method of hydraulic engineering property operation management system combined with intelligent sensing equipment

Publications (2)

Publication Number Publication Date
CN118643996A CN118643996A (en) 2024-09-13
CN118643996B true CN118643996B (en) 2024-12-13

Family

ID=92661480

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411125163.2A Active CN118643996B (en) 2024-08-16 2024-08-16 Operation method of hydraulic engineering property operation management system combined with intelligent sensing equipment

Country Status (1)

Country Link
CN (1) CN118643996B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119273096B (en) * 2024-10-31 2025-07-25 江苏峻岭峰建设有限公司 Hydraulic engineering intelligent construction management method and system

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115865992A (en) * 2023-03-02 2023-03-28 中国建材检验认证集团湖南有限公司 Wisdom water conservancy on-line monitoring system

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104794578A (en) * 2015-04-23 2015-07-22 深圳市汇生通科技发展有限公司 Could computing based smart water affair management system
CN113903007A (en) * 2021-12-10 2022-01-07 宁波弘泰水利信息科技有限公司 Intelligent scene analysis system for water conservancy industry
CN116050674B (en) * 2023-03-31 2023-06-23 长江空间信息技术工程有限公司(武汉) Hydraulic engineering operation trend prediction method and device
CN118154119A (en) * 2024-03-08 2024-06-07 广东粤海珠三角供水有限公司 Hydraulic engineering full life cycle intelligent management system based on digital twin
CN118152993B (en) * 2024-03-26 2024-10-22 河南省水利第一工程局集团有限公司 Intelligent water conservancy resource sensing system based on Internet of things
CN118333423B (en) * 2024-04-19 2025-02-25 龙口市水利建筑安装工程有限公司 Water Conservancy Project Management Intelligent System

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115865992A (en) * 2023-03-02 2023-03-28 中国建材检验认证集团湖南有限公司 Wisdom water conservancy on-line monitoring system

Also Published As

Publication number Publication date
CN118643996A (en) 2024-09-13

Similar Documents

Publication Publication Date Title
Thai-Nghe et al. Deep learning approach for forecasting water quality in IoT systems
CN112785458A (en) Intelligent management and maintenance system for bridge health big data
CN107944590A (en) A kind of method and apparatus of fishing condition analysis and forecasting
CN118656584A (en) An intelligent environmental monitoring system for water quality sampling
CN118707061A (en) A water quality analysis system in water conservancy projects
Tipon Tanchangya et al. A review of deep learning applications for sustainable water resource management
CN119599642B (en) A safety early warning method and system for electric manhole
CN118643996B (en) Operation method of hydraulic engineering property operation management system combined with intelligent sensing equipment
CN119474177B (en) Big data basic business management system for canal dredging construction
CN117875860A (en) A smart supervision platform for river basin water environment management
CN118094488A (en) Method and system for predicting the amount of floating objects on the reservoir surface of water-retaining structures in water conservancy and hydropower projects
CN110765633A (en) An intelligent management method and device for a power plant
Zhou et al. Review of the development of hydrological data quality control in Typhoon Committee Members
CN119809142B (en) Intelligent water conservancy construction management platform
CN120235461B (en) Coal gangue storage yard environment risk real-time monitoring method and system based on edge calculation
CN119580100B (en) A method and system for rapid breach situation awareness based on multi-source data
CN119484528B (en) A water environment management system based on cloud computing
CN118627930B (en) Underground pipe gallery structure health monitoring early warning system and monitoring device
CN120317680A (en) An intelligent safety risk management system based on digital twins and AI
CN118780627A (en) A dynamic monitoring platform for construction risks of rainwater and sewage diversion pipelines
CN119687876B (en) RTU intelligent data analysis method, remote terminal equipment, medium and product
CN120744675B (en) Watershed water environment monitoring and emergency pollution quick tracing method and system based on water quality pollution detection
Wu et al. Smart water grid technology based on deep learning: a review
CN120579108B (en) A diagnostic system for urban underground drainage pipe network problems based on big data analysis
CN120338555B (en) A damage assessment method for nearshore waters

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
GR01 Patent grant
GR01 Patent grant