CN119089351A - A data processing method and system based on industrial Internet - Google Patents
A data processing method and system based on industrial Internet Download PDFInfo
- Publication number
- CN119089351A CN119089351A CN202411139067.3A CN202411139067A CN119089351A CN 119089351 A CN119089351 A CN 119089351A CN 202411139067 A CN202411139067 A CN 202411139067A CN 119089351 A CN119089351 A CN 119089351A
- Authority
- CN
- China
- Prior art keywords
- data
- equipment
- maintenance
- acquiring
- positioning
- 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
Links
- 238000003672 processing method Methods 0.000 title abstract description 11
- 238000004519 manufacturing process Methods 0.000 claims abstract description 81
- 239000000463 material Substances 0.000 claims abstract description 79
- 238000012544 monitoring process Methods 0.000 claims abstract description 70
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 26
- 238000004140 cleaning Methods 0.000 claims abstract description 19
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 230000004927 fusion Effects 0.000 claims abstract description 12
- 238000012423 maintenance Methods 0.000 claims description 122
- 230000002159 abnormal effect Effects 0.000 claims description 74
- 238000000034 method Methods 0.000 claims description 53
- 230000007613 environmental effect Effects 0.000 claims description 36
- 238000012545 processing Methods 0.000 claims description 28
- 230000005856 abnormality Effects 0.000 claims description 24
- 238000001514 detection method Methods 0.000 claims description 19
- 238000004458 analytical method Methods 0.000 claims description 16
- 230000033001 locomotion Effects 0.000 claims description 15
- 238000007726 management method Methods 0.000 claims description 14
- 239000013598 vector Substances 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 8
- 238000003062 neural network model Methods 0.000 claims description 7
- 230000003287 optical effect Effects 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 6
- 230000035939 shock Effects 0.000 claims description 6
- 238000009434 installation Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000003909 pattern recognition Methods 0.000 claims description 3
- 238000011958 production data acquisition Methods 0.000 claims description 3
- 239000007921 spray Substances 0.000 claims description 3
- 230000006870 function Effects 0.000 description 18
- 238000011176 pooling Methods 0.000 description 17
- 238000003860 storage Methods 0.000 description 13
- 238000004590 computer program Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 230000004913 activation Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 230000004044 response Effects 0.000 description 6
- 230000001960 triggered effect Effects 0.000 description 6
- 230000007246 mechanism Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000012795 verification Methods 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000010485 coping Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013077 scoring method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- 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
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
-
- 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
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
-
- 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
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Signal Processing (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Emergency Management (AREA)
- Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
本发明公开了一种基于工业互联网的数据处理方法及系统，该方法采集生产线各个环节的人员、设备和物料的定位数据、设备的运行状态数据和/或电参数、生产场所的温度、湿度和/或气体浓度参数以及生产场所的监控视频数据；将采集的数据通过工业互联网设备传输至大数据中心服务器，并进行清洗和预处理；识别风险和异常；通过预先训练的卷积神经网络对多源化数据进行分析，进行综合风险识别，输出识别结果，执行融合智能决策。本发明提供的基于工业互联网的数据处理方法及系统不仅提升了工业互联网系统的智能化水平，而且增强了生产线在复杂环境下的安全性和稳定性。
The present invention discloses a data processing method and system based on the industrial Internet, which collects the location data of personnel, equipment and materials in each link of the production line, the operating status data and/or electrical parameters of the equipment, the temperature, humidity and/or gas concentration parameters of the production site, and the monitoring video data of the production site; transmits the collected data to the big data center server through the industrial Internet equipment, and performs cleaning and preprocessing; identifies risks and anomalies; analyzes multi-source data through a pre-trained convolutional neural network, performs comprehensive risk identification, outputs identification results, and executes fusion intelligent decision-making. The data processing method and system based on the industrial Internet provided by the present invention not only improve the intelligence level of the industrial Internet system, but also enhances the safety and stability of the production line in a complex environment.
Description
[ Field of technology ]
The invention relates to the technical field of industrial Internet, in particular to a data processing method and system based on the industrial Internet.
[ Background Art ]
With the development of the industrial internet, the intelligent and automatic degree of the production line is continuously improved, and how to effectively manage and monitor the states of all links in the production process becomes a great challenge for the modern manufacturing industry. Industrial production lines typically include a variety of complex equipment, personnel flow, and material management, and the real-time collection, analysis, and processing of various types of data is of great importance to ensure successful and safe production.
However, existing production monitoring systems often face several major problems of diversity and complexity of data acquisition and processing, deficiencies in real-time risk identification and response, limitations in intelligent decision making capability, and difficulties in fusion and analysis of multiple input data when processing these multiple source data.
Therefore, how to design an intelligent data processing method based on the industrial Internet, so that the intelligent data processing method can effectively collect, process and analyze multi-source data, and realize comprehensive risk identification and intelligent decision through advanced algorithms, becomes an important research direction in the current technical field.
[ Invention ]
In view of the above, the embodiment of the invention provides a data processing method and system based on industrial Internet.
In a first aspect, an embodiment of the present invention provides a data processing method based on industrial internet, where the method includes:
S1, acquiring positioning data of personnel, equipment and materials in each link of a production line through a Bluetooth AOA positioning system, acquiring running state data and/or electrical parameters of the equipment through an equipment state sensor, acquiring temperature, humidity and/or gas concentration parameters of a production place through an environment sensor, and acquiring monitoring video data of the production place through a camera;
s2, transmitting the acquired data to a large data center server through industrial Internet equipment, and cleaning and preprocessing the data;
s3, identifying the fault risk of the equipment according to the positioning data, the running state data and the electrical parameters of the equipment, identifying the abnormal condition of the material according to the positioning data of the material, identifying the abnormal condition of the environment according to the environmental parameters provided by the environment sensor, identifying an abnormal event according to the monitoring video data, and sending a first-level early warning notice to maintenance personnel or carrying out a first-level alarm through alarm equipment;
S4, analyzing the multi-source data through a pre-trained convolutional neural network, performing comprehensive risk identification, and outputting an identification result;
s5, converting the identification result into a vector form, and executing a fusion intelligent decision, wherein the intelligent decision comprises the steps of sending a primary early warning notice to maintenance personnel or carrying out primary warning through warning equipment, executing secondary warning, stopping and/or reporting to a management end of a manager.
In the aspect and any possible implementation manner as described above, there is further provided an implementation manner, where the S1 specifically includes:
a Bluetooth AOA positioning base station is arranged in a production place in advance and is used for collecting positioning signals sent by Bluetooth labels on personnel, equipment and materials in each link of a production line;
Pre-installing device status sensors on the device, the device status sensors including shock sensors, pressure sensors, current sensors, and/or voltage sensors to monitor shock, internal pressure, current, and/or voltage data of the device;
Arranging environmental sensors in the production place in advance, wherein the environmental sensors comprise a temperature sensor, a humidity sensor and/or a gas sensor and are used for collecting temperature, humidity and/or target gas concentration parameters of the production place;
arranging a camera in a production place in advance, and acquiring monitoring video data of the production place through the camera;
A mobile terminal is configured for maintenance personnel in advance;
the industrial internet equipment is used for receiving data transmitted by the Bluetooth AOA positioning base station, the equipment state sensor, the environment sensor, the camera and the mobile terminal.
In the aspect and any possible implementation manner described above, there is further provided an implementation manner, where in S3, the identifying the fault risk of the device according to the positioning data, the operation state data and the electrical parameter of the device specifically includes:
cleaning and normalizing the acquired data, removing noise and abnormal values, and fusing the cleaned data to form a comprehensive operation data set of the equipment;
extracting features from a comprehensive operation data set of the equipment, and extracting key feature values including key features of moving frequency, vibration amplitude, pressure change, current fluctuation and voltage fluctuation;
Calculating the fault risk of the equipment according to a fault risk scoring formula, wherein the scoring formula of the fault risk is as follows:
R＝W1·Fm+W2·Fs+W3·P+W4·C+W5·V+W6·He-λT,
W1+W2+W3+W4+W5+W6=1,
Wherein R is a fault risk score of equipment, F m is a moving frequency of the equipment, F s is a vibration characteristic value of the equipment, P is a pressure characteristic value, C is a current characteristic value, V is a voltage characteristic value, H is a maintenance history score of the equipment, e is a natural constant, lambda is a time attenuation coefficient, T is a time from last maintenance, W 1、W2、W3、W4、W5 and W 6 are weight coefficients of the characteristic values respectively, M i is a number of days of operation of the equipment after the ith maintenance, Q i is a quality score representing the ith maintenance, and n is a total maintenance number;
Comparing the acquired fault risk with a preset risk threshold, generating fault early warning information when the fault risk score exceeds the risk threshold, and sending a device primary early warning notice to a maintenance end of maintenance personnel, wherein the device primary early warning notice comprises a device position, an ID and a fault type;
acquiring positioning data of maintenance personnel and fault risk equipment, and performing primary alarm through alarm equipment when the maintenance personnel and the fault risk equipment do not complete positioning contact within preset time;
And acquiring maintenance records and quality scores sent by a maintenance end of maintenance personnel, and updating the equipment maintenance history database.
In the foregoing aspect and any possible implementation manner, there is further provided an implementation manner, where in S3, identifying, according to positioning data of the material, an abnormal condition of the material specifically includes:
Cleaning and normalizing the collected material positioning data to remove noise and abnormal values;
track analysis is carried out on the positioning data of the materials, and the moving path and the stay point of the materials are extracted;
Setting a normal moving mode of the material according to the historical positioning data of the material, wherein the normal moving mode comprises a normal moving path, residence time and moving frequency;
Comparing the moving path and the stay point of the current material with the set normal moving mode, and identifying the abnormal condition of the material;
generating path abnormality early warning information if the path abnormality is identified, generating stay time abnormality early warning information if the stay time abnormality is identified, and generating movement frequency abnormality early warning information if the movement frequency abnormality is identified;
Sending a first-level material early warning notice to a maintenance end of a maintenance person, wherein the first-level material early warning notice comprises a material position, an ID and an abnormal type;
Acquiring positioning data of related personnel and abnormal materials, monitoring the position relationship between the related personnel and the abnormal materials, and carrying out primary alarm through alarm equipment when the related personnel do not complete positioning contact within preset time;
and acquiring a maintenance record sent by a maintenance end of a maintenance person, and updating a material exception handling database.
In the aspect and any possible implementation manner as described above, there is further provided an implementation manner, where in S3, the identifying an environmental abnormal condition according to an environmental parameter provided by an environmental sensor specifically includes:
Acquiring temperature, humidity and/or target gas concentration parameters of a production place through an environment sensor, cleaning and normalizing the acquired environment parameter data, and removing noise and abnormal values;
Setting the normal range of each environmental parameter according to the historical environmental data and the standard operation rules;
Monitoring environmental parameters in real time, comparing the real-time environmental parameters with a set normal range, and identifying whether an environmental abnormal condition exists or not;
When the environment abnormal condition is identified, generating abnormal early warning information, and sending an environment primary early warning notice to a maintenance end of a maintainer, wherein the environment primary early warning notice comprises abnormal environment parameters, positions and abnormal types;
acquiring the maintenance end of maintenance personnel and positioning data of abnormal environmental parameters;
Monitoring the position relation between related personnel and an abnormal environment sensor, and carrying out primary alarm through alarm equipment when maintenance personnel do not complete positioning contact within a preset range within preset time;
and acquiring a maintenance record sent by a maintenance end of a maintenance person, and updating an environment parameter exception handling database.
In the foregoing aspect and any possible implementation manner, there is further provided an implementation manner, where in S3, the identifying an abnormal event according to the surveillance video data specifically includes:
Acquiring installation parameters of a camera, selecting a plurality of fixed reference points in the view angle range of the camera, acquiring reference point coordinates through Bluetooth tags, establishing a two-dimensional monitoring coordinate system in a video image based on physical space coordinates of the reference points, mapping the physical space coordinates of the reference points into the video image to form the monitoring coordinate system, and finishing coordinate mapping and positioning of video and physical space;
acquiring real-time monitoring video data from cameras of a production place, and preprocessing the acquired monitoring video data, wherein the preprocessing comprises video denoising and image enhancement;
analyzing the video data and detecting whether suspected flames exist or not;
After confirming that suspected flames exist, sending a fire early-warning first-level notification to a mobile terminal of maintainers, wherein the fire early-warning first-level notification comprises suspected flame monitoring images, occurrence time and positioning;
acquiring maintenance end of maintenance personnel and positioning data of suspected flames;
Monitoring the position relation between related personnel and suspected flames, and when maintenance personnel do not complete positioning contact within a preset range within preset time, performing primary alarm through alarm equipment, and opening a fire control spray header within the preset range according to positioning data of the suspected flames;
and acquiring a maintenance record sent by a maintenance end of a maintenance person, and updating a monitoring video exception handling database.
Aspects and any possible implementation manner as described above, further provide an implementation manner, where the detecting whether a suspected flame exists specifically includes:
The method comprises the steps of extracting color information of each pixel in a video image, converting an RGB color space into an HSV color space, defining a color range of flame, setting an H channel to be 0% -50%, setting an S channel to be 50% -100% and setting a V channel to be 50% -100%, carrying out color detection on each frame of image, identifying the pixels conforming to the color characteristics of the flame, and generating a binarized flame candidate region image;
analyzing the difference between video frames, analyzing the pixel motion in a flame candidate area by an optical flow method, detecting random flicker and edge jump of flame, identifying the dynamic change of the flame by using a background subtraction algorithm, reducing the flame candidate area of the flame candidate area image, and eliminating the color matching objects of non-flame;
comparing the currently detected flame candidate region with a historical flame image library by using a SIFT similarity matching algorithm, and judging whether the currently detected flame candidate region is matched with the previous flame event features;
Different weights are distributed to color detection, dynamic pattern recognition and historical data checking results, flame suspected values are calculated based on the weights, the obtained flame suspected values are compared with a preset credibility threshold, and when the flame suspected values exceed the credibility threshold, suspected flames are judged to exist.
Aspects and any one of the possible implementations as set forth above, further provide an implementation, when confirming that there is a suspected flame, further including:
after confirming that the suspected flame exists, acquiring the positioning of the suspected flame, and generating a range area covering a preset radius as a dangerous area;
determining a personnel list positioned in the current dangerous area based on the Bluetooth AOA positioning system, screening personnel passing through the current dangerous area according to historical movement data of the personnel, updating the personnel list and generating a dangerous personnel list;
And sending a dangerous person list and an evacuation notification to the mobile terminal of the maintainer, and broadcasting fire alarm information of the name of the dangerous person list through alarm equipment.
In the foregoing aspect and any possible implementation manner, there is further provided an implementation manner, where the S4 specifically includes:
Acquiring collected positioning data, running state data and/or electrical parameters, temperature, humidity and/or gas concentration parameters and monitoring video data, synchronizing time stamps of different data sources, and performing preliminary processing on different types of data through a feature extraction tool to form a multi-source data set suitable for a convolutional neural network model input format based on a multi-input structure;
loading a pre-trained convolutional neural network model based on a multi-input structure;
the processed multi-source data set is used as input data and is input into a convolutional neural network model based on a multi-input structure;
Extracting characteristics of input data through multi-layer convolution operation in a convolution neural network model based on a multi-input structure, and integrating and classifying the extracted characteristics through a full connection layer of the convolution neural network model based on the multi-input structure;
And generating a risk identification result according to the output of the convolutional neural network model based on the multi-input structure.
In a second aspect, an embodiment of the present invention provides an industrial internet-based data processing system using the above method, including:
The production data acquisition module is used for acquiring positioning data of personnel, equipment and materials in each link of a production line through the Bluetooth AOA positioning system, acquiring running state data and/or electric parameters of the equipment through the equipment state sensor, acquiring temperature, humidity and/or gas concentration parameters of a production place through the environment sensor and acquiring monitoring video data of the production place through the camera;
the data processing module is used for transmitting the acquired data to the large data center server through industrial Internet equipment and cleaning and preprocessing the data;
the risk emergency identification module is used for identifying the fault risk of the equipment according to the positioning data, the running state data and the electrical parameters of the equipment, identifying the abnormal condition of the material according to the positioning data of the material, identifying the abnormal condition of the environment according to the environment parameters provided by the environment sensor, identifying the abnormal event according to the monitoring video data, and sending a first-level early warning notice to maintenance personnel or carrying out first-level warning through the warning equipment;
The risk comprehensive identification module is used for analyzing the multi-source data through a pre-trained convolutional neural network, carrying out comprehensive risk identification and outputting an identification result;
The intelligent decision module is used for converting the identification result into a vector form and executing fusion intelligent decision, and the intelligent decision comprises the steps of sending a primary early warning notice to maintenance personnel or carrying out primary alarm through alarm equipment, executing secondary alarm, stopping and/or reporting to a management end of a manager.
One of the above technical solutions has the following beneficial effects:
According to the method, the Bluetooth AOA positioning system, the equipment state sensor, the environment sensor and the monitoring video acquisition system are introduced, comprehensive monitoring of personnel, equipment and materials in each link of a production line is achieved, the multi-source data are transmitted to a big data center in real time through an industrial Internet platform for cleaning and preprocessing, the multi-source data are subjected to deep analysis and feature extraction through an algorithm and a model, potential risks such as equipment faults, material anomalies, environment anomalies and fires can be effectively identified, the identification results are comprehensively analyzed through an intelligent decision module, corresponding alarm and emergency treatment measures are generated, the intelligent level of the industrial Internet system is improved, the safety and stability of the production line in a complex environment are enhanced, and the method has wide application prospects and practical values.
[ Description of the drawings ]
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a data processing method based on industrial Internet according to an embodiment of the invention;
FIG. 2 is a functional block diagram of a system according to an embodiment of the present invention.
[ Detailed description ] of the invention
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to specific embodiments and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flow chart of a data processing method based on industrial internet according to an embodiment of the invention is shown in fig. 1, and the method includes the following steps:
S1, acquiring positioning data of personnel, equipment and materials in each link of a production line through a Bluetooth AOA positioning system, acquiring running state data and/or electrical parameters of the equipment through an equipment state sensor, acquiring temperature, humidity and/or gas concentration parameters of a production place through an environment sensor, and acquiring monitoring video data of the production place through a camera;
s2, transmitting the acquired data to a large data center server through industrial Internet equipment, and cleaning and preprocessing the data;
s3, identifying the fault risk of the equipment according to the positioning data, the running state data and the electrical parameters of the equipment, identifying the abnormal condition of the material according to the positioning data of the material, identifying the abnormal condition of the environment according to the environmental parameters provided by the environment sensor, identifying an abnormal event according to the monitoring video data, and sending a first-level early warning notice to maintenance personnel or carrying out a first-level alarm through alarm equipment;
S4, analyzing the multi-source data through a pre-trained convolutional neural network, performing comprehensive risk identification, and outputting an identification result;
s5, converting the identification result into a vector form, and executing a fusion intelligent decision, wherein the intelligent decision comprises the steps of sending a primary early warning notice to maintenance personnel or carrying out primary warning through warning equipment, executing secondary warning, stopping and/or reporting to a management end of a manager.
According to the embodiment of the invention, through a Bluetooth AOA positioning system, a device state sensor, an environment sensor, a camera and other various sensing devices, personnel, devices, materials and environment information of each link of a production line can be efficiently acquired, acquired data are transmitted to a big data center through industrial Internet equipment, noise and abnormal values in the data are eliminated through cleaning and preprocessing, and the accuracy and reliability of subsequent data analysis are ensured; the equipment fault risk can be identified in real time by comprehensively analyzing the positioning data, the running state data and the electrical parameters of the equipment, meanwhile, the material abnormality and the environment abnormality condition can be rapidly identified by analyzing the track of the material positioning data and monitoring the environment parameters, in addition, the fire safety hidden danger of the production site can be effectively detected by combining the analysis of the monitoring video data, and early warning notification or triggering alarm equipment can be timely sent to maintainers, so that the safety of the production line is improved; the invention can accurately judge potential multiple risks in a production line and output identification results through intelligent analysis of the model by adopting a pre-trained convolutional neural network model, can provide reliable basis for subsequent decisions, has self-adaptive learning capability, can continuously optimize and adjust a risk identification model according to the change and historical data of an actual production environment, converts the identification results into quantized risk vectors, executes corresponding emergency response measures including secondary alarm, shutdown processing, reporting to a management end and the like through an intelligent decision-making module according to the risk assessment results, in addition, the invention has good expansibility, can easily integrate other types of sensing equipment or analysis tools, and is suitable for the application scenes of production lines with different scales and complexity.
In a preferred embodiment, the S1 specifically includes:
a Bluetooth AOA positioning base station is arranged in a production place in advance and is used for collecting positioning signals sent by Bluetooth labels on personnel, equipment and materials in each link of a production line;
Pre-installing device status sensors on the device, the device status sensors including shock sensors, pressure sensors, current sensors, and/or voltage sensors to monitor shock, internal pressure, current, and/or voltage data of the device;
Arranging environmental sensors in the production place in advance, wherein the environmental sensors comprise a temperature sensor, a humidity sensor and/or a gas sensor and are used for collecting temperature, humidity and/or target gas concentration parameters of the production place;
arranging a camera in a production place in advance, and acquiring monitoring video data of the production place through the camera;
A mobile terminal is configured for maintenance personnel in advance;
the industrial internet equipment is used for receiving data transmitted by the Bluetooth AOA positioning base station, the equipment state sensor, the environment sensor, the camera and the mobile terminal.
According to the preferred embodiment of the invention, various sensing devices and positioning base stations are arranged in advance in the production place, so that the comprehensive monitoring and data acquisition of each link of the production line are realized, the intelligent monitoring capability of the production line is greatly improved, the accurate positioning, comprehensive state monitoring and efficient data management are realized, and the safety and the operation efficiency of the production line are ensured.
In a preferred embodiment, the identifying the fault risk of the device in S3 according to the positioning data, the operation state data and the electrical parameters of the device specifically includes:
cleaning and normalizing the acquired data, removing noise and abnormal values, and fusing the cleaned data to form a comprehensive operation data set of the equipment;
extracting features from a comprehensive operation data set of the equipment, and extracting key feature values including key features of moving frequency, vibration amplitude, pressure change, current fluctuation and voltage fluctuation;
Calculating the fault risk of the equipment according to a fault risk scoring formula, wherein the scoring formula of the fault risk is as follows:
R＝W1·Fm+W2·Fs+W3·P+W4·C+W5·V+W6·He-λT,
W1+W2+W3+W4+W5+W6=1,
Wherein R is a fault risk score of equipment, F m is a moving frequency of the equipment, F s is a vibration characteristic value of the equipment, P is a pressure characteristic value, C is a current characteristic value, V is a voltage characteristic value, H is a maintenance history score of the equipment, e is a natural constant, lambda is a time attenuation coefficient, T is a time from last maintenance, W 1、W2、W3、W4、W5 and W 6 are weight coefficients of the characteristic values respectively, M i is a number of days of operation of the equipment after the ith maintenance, Q i is a quality score representing the ith maintenance, and n is a total maintenance number;
Comparing the acquired fault risk with a preset risk threshold, generating fault early warning information when the fault risk score exceeds the risk threshold, and sending a device primary early warning notice to a maintenance end of maintenance personnel, wherein the device primary early warning notice comprises a device position, an ID and a fault type;
acquiring positioning data of maintenance personnel and fault risk equipment, and performing primary alarm through alarm equipment when the maintenance personnel and the fault risk equipment do not complete positioning contact within preset time;
And acquiring maintenance records and quality scores sent by a maintenance end of maintenance personnel, and updating the equipment maintenance history database.
The method comprises the steps of carrying out cleaning and normalization processing on collected data, effectively removing noise and abnormal values, ensuring accuracy and consistency of the data, carrying out quantification and comprehensive analysis on a plurality of key features through a fault risk scoring formula, fully considering changes of moving frequency, vibration features, pressure, current and voltage of equipment and equipment maintenance history scoring and time attenuation effects through the scoring formula, calculating comprehensive fault risk scoring of the equipment, carrying out accurate assessment on fault risk level of the equipment based on scientific weighted analysis, comparing the fault risk scoring with a preset risk threshold, generating fault early warning information in time and sending the fault early warning information to maintenance personnel when the fault risk scoring exceeds the threshold, carrying out real-time tracking on positioning data of the maintenance personnel and the fault equipment through the fact that the first-stage early warning notification comprises specific positions, IDs and fault types of the equipment, automatically triggering a first-stage warning mechanism if the positioning contact is not completed within the preset time, ensuring that the equipment fault is responded and processed, continuously updating a maintenance history database of the equipment, and carrying out dynamic assessment on the fault state of the equipment by acquiring the maintenance history database of the maintenance personnel, and carrying out operation quality and maintenance history data of the equipment after the maintenance is recorded and the maintenance quality is carried out, and the future performance of the equipment can be reflected by referring to the important maintenance history database. According to the invention, multidimensional state monitoring, accurate risk assessment, timely early warning and effective alarm mechanism are realized in the aspect of equipment fault risk identification, the intelligent level of equipment management is greatly improved through a scientific feature extraction and risk scoring method, the operation risk caused by equipment faults can be obviously reduced, and the overall operation efficiency and safety of a production line are improved.
In a preferred embodiment, in the step S3, identifying the abnormal condition of the material according to the positioning data of the material specifically includes:
Cleaning and normalizing the collected material positioning data to remove noise and abnormal values;
track analysis is carried out on the positioning data of the materials, and the moving path and the stay point of the materials are extracted;
Setting a normal moving mode of the material according to the historical positioning data of the material, wherein the normal moving mode comprises a normal moving path, residence time and moving frequency;
Comparing the moving path and the stay point of the current material with the set normal moving mode, and identifying the abnormal condition of the material;
generating path abnormality early warning information if the path abnormality is identified, generating stay time abnormality early warning information if the stay time abnormality is identified, and generating movement frequency abnormality early warning information if the movement frequency abnormality is identified;
Sending a first-level material early warning notice to a maintenance end of a maintenance person, wherein the first-level material early warning notice comprises a material position, an ID and an abnormal type;
Acquiring positioning data of related personnel and abnormal materials, monitoring the position relationship between the related personnel and the abnormal materials, and carrying out primary alarm through alarm equipment when the related personnel do not complete positioning contact within preset time;
and acquiring a maintenance record sent by a maintenance end of a maintenance person, and updating a material exception handling database.
According to the invention, efficient data processing, accurate track analysis and abnormality recognition based on a historical mode are realized in the aspect of material abnormal condition recognition, the track analysis can track the real-time position of a material, the motion state and behavior characteristics of the material in a production line can be reflected, and the abnormality recognition method based on the historical data can be better adapted to the normal behavior mode of the material, so that the possibility of false alarm is reduced, the intelligent and automatic level of material management is obviously improved, the production risk caused by material abnormality is effectively reduced through a timely early warning and alarm mechanism, the stable operation of the production line is ensured, and the method has a wide industrial application value.
In a preferred embodiment, the identifying an environmental abnormal condition in S3 according to the environmental parameter provided by the environmental sensor specifically includes:
Acquiring temperature, humidity and/or target gas concentration parameters of a production place through an environment sensor, cleaning and normalizing the acquired environment parameter data, and removing noise and abnormal values;
Setting the normal range of each environmental parameter according to the historical environmental data and the standard operation rules;
Monitoring environmental parameters in real time, comparing the real-time environmental parameters with a set normal range, and identifying whether an environmental abnormal condition exists or not;
When the environment abnormal condition is identified, generating abnormal early warning information, and sending an environment primary early warning notice to a maintenance end of a maintainer, wherein the environment primary early warning notice comprises abnormal environment parameters, positions and abnormal types;
acquiring the maintenance end of maintenance personnel and positioning data of abnormal environmental parameters;
Monitoring the position relation between related personnel and an abnormal environment sensor, and carrying out primary alarm through alarm equipment when maintenance personnel do not complete positioning contact within a preset range within preset time;
and acquiring a maintenance record sent by a maintenance end of a maintenance person, and updating an environment parameter exception handling database.
According to the invention, efficient data processing, accurate real-time monitoring and timely abnormal response are realized in the aspect of environment abnormal condition identification, the environment safety management capability of a production place is remarkably improved, the influence of environment abnormality on the production process is effectively reduced through a real-time early warning and intelligent alarm mechanism, and the production continuity and safety are ensured.
In a preferred embodiment, the identifying an abnormal event in S3 according to the surveillance video data specifically includes:
Acquiring installation parameters of a camera, selecting a plurality of fixed reference points in the view angle range of the camera, acquiring reference point coordinates through Bluetooth tags, establishing a two-dimensional monitoring coordinate system in a video image based on physical space coordinates of the reference points, mapping the physical space coordinates of the reference points into the video image to form the monitoring coordinate system, and finishing coordinate mapping and positioning of video and physical space;
acquiring real-time monitoring video data from cameras of a production place, and preprocessing the acquired monitoring video data, wherein the preprocessing comprises video denoising and image enhancement;
analyzing the video data and detecting whether suspected flames exist or not;
After confirming that suspected flames exist, sending a fire early-warning first-level notification to a mobile terminal of maintainers, wherein the fire early-warning first-level notification comprises suspected flame monitoring images, occurrence time and positioning;
acquiring maintenance end of maintenance personnel and positioning data of suspected flames;
Monitoring the position relation between related personnel and suspected flames, and when maintenance personnel do not complete positioning contact within a preset range within preset time, performing primary alarm through alarm equipment, and opening a fire control spray header within the preset range according to positioning data of the suspected flames;
and acquiring a maintenance record sent by a maintenance end of a maintenance person, and updating a monitoring video exception handling database.
The invention establishes a two-dimensional monitoring coordinate system in a video image by acquiring installation parameters of a camera and selecting a plurality of fixed reference points in the view angle range of the camera and utilizing a Bluetooth tag to acquire physical space coordinates of the reference points, the process maps the accurate coordinates of the physical space into the video image, thereby realizing seamless combination of the video and the physical space, ensuring the accuracy and the real-time performance of subsequent video data analysis, preprocessing the monitoring video data acquired in real time, including video denoising and image enhancement operation, remarkably improving the quality of the video data by removing noise in the video and enhancing the definition of the image, ensuring the video monitoring effect in the complex production environment, providing a basis for accurately detecting abnormal events, utilizing an advanced image analysis technology to deeply analyze the preprocessed video data, detecting whether suspected flames exist in the video, immediately sending a first-level notification of fire disaster to a moving end of a maintainer after the system confirms the existence of the suspected flames, informing the suspected flames, including monitoring images, time and accurate positioning, helping the maintainer to rapidly and coping with the fire risks, acquiring the moving end of the maintainer, triggering the corresponding fire disaster early warning function according to the acquired by removing the noise in the video and the image enhancement, triggering the corresponding fire early warning function, and triggering the automatic positioning system to the fire alarm position of the fire alarm can be triggered in the corresponding fire alarm and the fire alarm position can be triggered in the range when the corresponding fire alarm is triggered and the corresponding to the fire alarm is triggered automatically, thereby the fire alarm is triggered and the fire alarm is triggered in the real time has been lowered, the monitoring video exception handling database is continuously updated, the processing process and the result of all video exception events are recorded in the monitoring video exception handling database, important reference data can be provided for future exception detection and processing, and the monitoring video exception handling database helps to optimize the coping strategy of the system and improve the overall response efficiency.
In a preferred embodiment, the detecting whether a suspected flame exists specifically includes:
The method comprises the steps of extracting color information of each pixel in a video image, converting an RGB color space into an HSV color space, defining a color range of flame, setting an H channel to be 0% -50%, setting an S channel to be 50% -100% and setting a V channel to be 50% -100%, carrying out color detection on each frame of image, identifying the pixels conforming to the color characteristics of the flame, and generating a binarized flame candidate region image;
analyzing the difference between video frames, analyzing the pixel motion in a flame candidate area by an optical flow method, detecting random flicker and edge jump of flame, identifying the dynamic change of the flame by using a background subtraction algorithm, reducing the flame candidate area of the flame candidate area image, and eliminating the color matching objects of non-flame;
comparing the currently detected flame candidate region with a historical flame image library by using a SIFT similarity matching algorithm, and judging whether the currently detected flame candidate region is matched with the previous flame event features;
Different weights are distributed to color detection, dynamic pattern recognition and historical data checking results, flame suspected values are calculated based on the weights, the obtained flame suspected values are compared with a preset credibility threshold, and when the flame suspected values exceed the credibility threshold, suspected flames are judged to exist.
The invention can rapidly identify the pixels conforming to the flame color characteristics and generate a binarized flame candidate area image by converting each pixel in the video image from RGB color space to HSV color space and screening H, S, V channels according to the set flame color range, the color detection method not only improves the efficiency of flame detection, but also effectively reduces false alarm caused by illumination change and ensures the accuracy of the flame candidate area, the optical flow method analyzes the pixel movement in the flame candidate area, detects random flicker and edge jump of the flame, further reduces the flame candidate area, combines a background subtraction algorithm to identify the dynamic change of the flame, can effectively exclude the color matching objects of non-flame, such as reflection, facula and the like, improves the accuracy of flame detection by adopting a SIFT similarity matching algorithm, compares the currently detected flame candidate area with a historical image library, judges the similarity of the characteristics of the current flame and the historical flame by extracting key characteristic points in the image, further confirms the accuracy, and the method is improved by utilizing the reliability of the detection method, and the false flame detection method is based on the fact that the false flame detection value is more than the false flame, and the false flame detection value is calculated by the false flame detection value, and the false flame detection value is calculated and the false flame has the false flame detection value is calculated when the false flame detection value is more than the false flame value has the false flame detection value has the false flame value, the system can immediately trigger fire early warning notification and respond through a related mechanism, and can send fire early warning information to maintenance personnel through a mobile terminal, wherein the fire early warning information comprises monitoring images, occurrence time and specific positions of flames, so that the timeliness and accuracy of fire emergency treatment are effectively improved, and the potential harm of fire to a production environment is reduced to the greatest extent.
In a preferred embodiment, the method further comprises, after confirming the existence of the suspected flame:
after confirming that the suspected flame exists, acquiring the positioning of the suspected flame, and generating a range area covering a preset radius as a dangerous area;
determining a personnel list positioned in the current dangerous area based on the Bluetooth AOA positioning system, screening personnel passing through the current dangerous area according to historical movement data of the personnel, updating the personnel list and generating a dangerous personnel list;
And sending a dangerous person list and an evacuation notification to the mobile terminal of the maintainer, and broadcasting fire alarm information of the name of the dangerous person list through alarm equipment.
After the existence of suspected flames is confirmed, the method can quickly acquire the accurate positioning of the flames, generate a dangerous area covering the periphery of the flames based on the preset radius, and timely define the range of the dangerous area by accurately positioning the flame occurrence position, so that the relevant area can be effectively monitored and managed before the fire risk is spread, and the safety of a production place is protected to the greatest extent; the Bluetooth AOA positioning system can accurately determine all people currently located in a dangerous area, screen out people passing through the dangerous area according to historical movement data of the people, generate a dangerous person list through updating the person list, enable the system to grasp the situation of the dangerous area and the possible dangerous person in real time, provide guarantee for fire hazard prevention, immediately send evacuation notification to a mobile terminal of maintenance personnel after the dangerous person list is generated, report name fire alarm information in the dangerous person list through alarm equipment, enable related people to quickly receive alarm information and evacuate the dangerous area in time when a possible fire happens, greatly improve the efficiency of fire emergency response, effectively reduce risks of casualties and property loss, avoid confusion and influence on production due to false alarm, enable the personnel list to be dynamically updated through real-time positioning and historical data analysis of the people in the dangerous area, enable any person entering or passing through the dangerous area to be recognized and notified in time, enable the system to transmit the alarm information to the related people in the shortest time through the real-time function of the alarm equipment, further enhance the fire emergency response speed and the broadcasting effect.
In a preferred embodiment, the step S4 specifically includes:
Acquiring collected positioning data, running state data and/or electrical parameters, temperature, humidity and/or gas concentration parameters and monitoring video data, synchronizing time stamps of different data sources, and performing preliminary processing on different types of data through a feature extraction tool to form a multi-source data set suitable for a convolutional neural network model input format based on a multi-input structure;
loading a pre-trained convolutional neural network model based on a multi-input structure;
the processed multi-source data set is used as input data and is input into a convolutional neural network model based on a multi-input structure;
Extracting characteristics of input data through multi-layer convolution operation in a convolution neural network model based on a multi-input structure, and integrating and classifying the extracted characteristics through a full connection layer of the convolution neural network model based on the multi-input structure;
And generating a risk identification result according to the output of the convolutional neural network model based on the multi-input structure.
The embodiment of the invention carries out preliminary processing on different types of data through a characteristic extraction tool to form a multi-source data set suitable for analysis of a convolutional neural network model, ensures the accuracy and consistency of the data, adopts the convolutional neural network model based on a multi-input structure, can process a plurality of data inputs simultaneously, carries out deep characteristic extraction on the input data through multi-layer convolutional operation, can extract key characteristics from time sequence data, image data and environment data, realizes multi-dimensional understanding of a complex production environment, improves the accuracy and depth of risk identification, can accurately judge the running state of the production line, generates a corresponding risk identification result, greatly improves the safety and operation efficiency of the production line through the intelligent analysis process, provides a decision basis for timely and accurate risk early warning and countermeasure for a manager, has good feasibility and self-adaptability, can continuously optimize the analysis model according to the change of the actual production environment, and is suitable for different types of data input.
The convolutional neural network model based on the multi-input structure is designed as follows:
1. The data input type comprises positioning data, equipment state data, environment parameter data, image data and monitoring video frame data, wherein the positioning data comprise parameters such as equipment vibration, internal pressure, current and voltage collected by a vibration sensor, a pressure sensor, a current sensor and a voltage sensor, the environment parameter data comprise parameters such as temperature, humidity and gas concentration, the environment sensor is arranged at a production place, and the monitoring video frame data comprise image data from a camera at the production place.
2. Data synchronization and preliminary processing:
The method comprises the steps of synchronizing time stamps of different data sources, ensuring that all data are analyzed on the same time axis, performing preliminary processing on the data by using a feature extraction tool, wherein the preliminary processing comprises normalization, noise reduction and outlier removal operations, and forming a multi-source data set suitable for being input into a CNN model, wherein the multi-source data set comprises standard input formats required for converting time series data and image data into CNN.
3. Model structure:
The input layer is provided with 1 (positioning data) which is the positioning data collected by a Bluetooth AOA positioning base station, wherein the shape is (T, F1), T is the time step number, F1 is the positioning characteristic dimension, 2 (equipment state data) which is the data from vibration, pressure, current and voltage sensors, and is (T, F2), 3 (environment parameter data) which is the temperature, humidity and gas concentration data, and is (T, F3), 4 (image data) which is the monitoring video frame from a camera, is (H, W, C), H is the image height, W is the image width, and C is the channel number;
convolution layer and pooling layer:
Positioning a data channel, namely performing 1:1D convolution on a convolution layer, wherein the convolution kernel size is 3, the number is 64, the step length is 1, the filling mode is the same (same), the activation function is ReLU, the pooling layer is 1:1D max pooling, the pooling window size is 2, the step length is 2, and the output shape is (T/2,64) after pooling;
The device state data channel comprises a convolution layer 2:1D convolution, a pooling layer 2:1D maximum pooling, a pooling window size 2, a step length 2, an output shape, a pooled output shape (T/2,64), wherein the convolution kernel size is 3, the number is 64, the step length is 1, the filling modes are the same, the activation function is ReLU;
The environment parameter data channel comprises a convolution layer 3:1D convolution, a pooling layer 3:1D maximum pooling, a pooling window size 2, a step length 2, an output shape, a pooled output shape (T/2, 32), wherein the convolution kernel size is 3, the number is 32, the step length is 1, the filling modes are the same, the activation function is ReLU;
The image data channel comprises a convolution layer 4:2D convolution, a pooling layer 4:2D maximum pooling, a pooling window size 2x2, a step length 2x2, an output shape, wherein the convolution kernel size is 3x3, the number is 32, the step length is 1x1, the filling modes are the same, the activation function is ReLU, the pooling window size is 2x2, the step length is 2x2, and the output shape after pooling is (H/2, W/2, 32);
feature fusion and full connection layer:
the pooling output of each channel is flattened into a one-dimensional vector, wherein the positioning data channel has flattened dimension of (T/2) x 64, the equipment state data channel has flattened dimension of (T/2) x 64, the environment parameter data channel has flattened dimension of (T/2) x 32, and the image data channel has flattened dimension of (H/2) x 32;
The feature fusion layer is used for connecting all flattened vectors into a large vector, wherein the dimension after fusion is (T/2) (64+64+32) + (H/2) (W/2) 32;
full connection layer 1, full connection layer, 256 output dimension, and ReLU activation function;
full connection layer 2, full connection layer, output dimension 128, activation function ReLU;
And the final output layer, wherein the output dimension is 4, and the activation function is Sigmoid and is used for two classification tasks.
4. Model training and optimizing:
A loss function, namely using cross entropy loss and an optimizer, namely using an Adam optimizer, and setting the initial learning rate to be 0.001;
training and verification, namely dividing a data set into a training set and a verification set, conventionally dividing the data set into 80% training data and 20% verification data, preventing overfitting by using an early-stop system, and optimizing model parameters through cross verification.
It should be noted that, the convolutional neural network model based on the multi-input structure of the present invention is not limited to the above design, and other existing neural network models can be adopted as required.
The comprehensive risk feature vector is subjected to nonlinear conversion by using a Sigmoid activation function, the output recognition result is a risk probability vector, each value corresponds to the recognition result of one risk category, different weights are given to each risk category according to the probability value of each risk category, the sum value is calculated, the sum value is compared with different level thresholds, and a fusion intelligent decision is executed according to the comparison result, wherein the intelligent decision comprises the steps of sending a first-level early warning notice to maintenance personnel or carrying out first-level warning through warning equipment, executing second-level warning, stopping and/or reporting to a management end of a manager;
The method comprises the steps of judging whether a comprehensive risk score exceeds a low risk threshold, sending a first-level early warning notice to maintenance personnel or carrying out first-level warning through warning equipment when the comprehensive risk score does not exceed the low risk threshold, triggering a second-level warning and reporting to a management end of a manager when the comprehensive risk score exceeds the medium risk threshold but does not exceed a highest risk threshold, and executing emergency shutdown and automatically reporting to the management end of the manager when the risk score exceeds the highest risk threshold.
The embodiment of the invention further provides an embodiment of a device for realizing the steps and the method in the embodiment of the method.
The embodiment of the invention provides a data processing system based on industrial Internet by utilizing the method. As shown in fig. 2, a functional block diagram of a system according to an embodiment of the present invention is provided, where the system includes:
The production data acquisition module is used for acquiring positioning data of personnel, equipment and materials in each link of a production line through the Bluetooth AOA positioning system, acquiring running state data and/or electric parameters of the equipment through the equipment state sensor, acquiring temperature, humidity and/or gas concentration parameters of a production place through the environment sensor and acquiring monitoring video data of the production place through the camera;
the data processing module is used for transmitting the acquired data to the large data center server through industrial Internet equipment and cleaning and preprocessing the data;
the risk emergency identification module is used for identifying the fault risk of the equipment according to the positioning data, the running state data and the electrical parameters of the equipment, identifying the abnormal condition of the material according to the positioning data of the material, identifying the abnormal condition of the environment according to the environment parameters provided by the environment sensor, identifying the abnormal event according to the monitoring video data, and sending a first-level early warning notice to maintenance personnel or carrying out first-level warning through the warning equipment;
The risk comprehensive identification module is used for analyzing the multi-source data through a pre-trained convolutional neural network, carrying out comprehensive risk identification and outputting an identification result;
The intelligent decision module is used for converting the identification result into a vector form and executing fusion intelligent decision, and the intelligent decision comprises the steps of sending a primary early warning notice to maintenance personnel or carrying out primary alarm through alarm equipment, executing secondary alarm, stopping and/or reporting to a management end of a manager.
The embodiments of the present invention also provide a computer-readable storage medium storing one or more programs, the one or more programs including instructions, which when executed by a server comprising a plurality of application programs, enable the server to perform the node operation method provided in any of the embodiments of the present invention.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above apparatus is described as being functionally divided into various units or modules, respectively. Of course, the functions of each unit or module may be implemented in one or more pieces of software and/or hardware when implementing the invention.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments of the present invention are described in a progressive manner, and the same and similar parts of the embodiments are all referred to each other, and each embodiment is mainly described in the differences from the other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The foregoing is merely exemplary of the present invention and is not intended to limit the present invention. Various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the invention are to be included in the scope of the claims of the present invention.
Claims (10)
1. A method for processing data based on the industrial internet, the method comprising:
S1, acquiring positioning data of personnel, equipment and materials in each link of a production line through a Bluetooth AOA positioning system, acquiring running state data and/or electrical parameters of the equipment through an equipment state sensor, acquiring temperature, humidity and/or gas concentration parameters of a production place through an environment sensor, and acquiring monitoring video data of the production place through a camera;
s2, transmitting the acquired data to a large data center server through industrial Internet equipment, and cleaning and preprocessing the data;
s3, identifying the fault risk of the equipment according to the positioning data, the running state data and the electrical parameters of the equipment, identifying the abnormal condition of the material according to the positioning data of the material, identifying the abnormal condition of the environment according to the environmental parameters provided by the environment sensor, identifying an abnormal event according to the monitoring video data, and sending a first-level early warning notice to maintenance personnel or carrying out a first-level alarm through alarm equipment;
S4, analyzing the multi-source data through a pre-trained convolutional neural network, performing comprehensive risk identification, and outputting an identification result;
s5, converting the identification result into a vector form, and executing a fusion intelligent decision, wherein the intelligent decision comprises the steps of sending a primary early warning notice to maintenance personnel or carrying out primary warning through warning equipment, executing secondary warning, stopping and/or reporting to a management end of a manager.
2. The method according to claim 1, wherein S1 specifically comprises:
a Bluetooth AOA positioning base station is arranged in a production place in advance and is used for collecting positioning signals sent by Bluetooth labels on personnel, equipment and materials in each link of a production line;
Pre-installing device status sensors on the device, the device status sensors including shock sensors, pressure sensors, current sensors, and/or voltage sensors to monitor shock, internal pressure, current, and/or voltage data of the device;
Arranging environmental sensors in the production place in advance, wherein the environmental sensors comprise a temperature sensor, a humidity sensor and/or a gas sensor and are used for collecting temperature, humidity and/or target gas concentration parameters of the production place;
arranging a camera in a production place in advance, and acquiring monitoring video data of the production place through the camera;
A mobile terminal is configured for maintenance personnel in advance;
the industrial internet equipment is used for receiving data transmitted by the Bluetooth AOA positioning base station, the equipment state sensor, the environment sensor, the camera and the mobile terminal.
3. The method according to claim 2, wherein the identifying the risk of the failure of the device in S3 based on the positioning data, the operation status data and the electrical parameters of the device, specifically comprises:
cleaning and normalizing the acquired data, removing noise and abnormal values, and fusing the cleaned data to form a comprehensive operation data set of the equipment;
extracting features from a comprehensive operation data set of the equipment, and extracting key feature values including key features of moving frequency, vibration amplitude, pressure change, current fluctuation and voltage fluctuation;
Calculating the fault risk of the equipment according to a fault risk scoring formula, wherein the scoring formula of the fault risk is as follows:
R＝W1·Fm+W2·Fs+W3·P+W4·C+W5·V+W6·He-λT,
W1+W2+W3+W4+W5+W6=1,
Wherein R is a fault risk score of equipment, F m is a moving frequency of the equipment, F s is a vibration characteristic value of the equipment, P is a pressure characteristic value, C is a current characteristic value, V is a voltage characteristic value, H is a maintenance history score of the equipment, e is a natural constant, lambda is a time attenuation coefficient, T is a time from last maintenance, W 1、W2、W3、W4、W5 and W 6 are weight coefficients of the characteristic values respectively, M i is a number of days of operation of the equipment after the ith maintenance, Q i is a quality score representing the ith maintenance, and n is a total maintenance number;
Comparing the acquired fault risk with a preset risk threshold, generating fault early warning information when the fault risk score exceeds the risk threshold, and sending a device primary early warning notice to a maintenance end of maintenance personnel, wherein the device primary early warning notice comprises a device position, an ID and a fault type;
acquiring positioning data of maintenance personnel and fault risk equipment, and performing primary alarm through alarm equipment when the maintenance personnel and the fault risk equipment do not complete positioning contact within preset time;
And acquiring maintenance records and quality scores sent by a maintenance end of maintenance personnel, and updating the equipment maintenance history database.
4. The method according to claim 3, wherein the identifying the abnormal condition of the material in S3 according to the positioning data of the material specifically includes:
Cleaning and normalizing the collected material positioning data to remove noise and abnormal values;
track analysis is carried out on the positioning data of the materials, and the moving path and the stay point of the materials are extracted;
Setting a normal moving mode of the material according to the historical positioning data of the material, wherein the normal moving mode comprises a normal moving path, residence time and moving frequency;
Comparing the moving path and the stay point of the current material with the set normal moving mode, and identifying the abnormal condition of the material;
generating path abnormality early warning information if the path abnormality is identified, generating stay time abnormality early warning information if the stay time abnormality is identified, and generating movement frequency abnormality early warning information if the movement frequency abnormality is identified;
Sending a first-level material early warning notice to a maintenance end of a maintenance person, wherein the first-level material early warning notice comprises a material position, an ID and an abnormal type;
Acquiring positioning data of related personnel and abnormal materials, monitoring the position relationship between the related personnel and the abnormal materials, and carrying out primary alarm through alarm equipment when the related personnel do not complete positioning contact within preset time;
and acquiring a maintenance record sent by a maintenance end of a maintenance person, and updating a material exception handling database.
5. The method according to claim 4, wherein the identifying the environmental anomaly in S3 based on the environmental parameter provided by the environmental sensor specifically comprises:
Acquiring temperature, humidity and/or target gas concentration parameters of a production place through an environment sensor, cleaning and normalizing the acquired environment parameter data, and removing noise and abnormal values;
Setting the normal range of each environmental parameter according to the historical environmental data and the standard operation rules;
Monitoring environmental parameters in real time, comparing the real-time environmental parameters with a set normal range, and identifying whether an environmental abnormal condition exists or not;
When the environment abnormal condition is identified, generating abnormal early warning information, and sending an environment primary early warning notice to a maintenance end of a maintainer, wherein the environment primary early warning notice comprises abnormal environment parameters, positions and abnormal types;
acquiring the maintenance end of maintenance personnel and positioning data of abnormal environmental parameters;
Monitoring the position relation between related personnel and an abnormal environment sensor, and carrying out primary alarm through alarm equipment when maintenance personnel do not complete positioning contact within a preset range within preset time;
and acquiring a maintenance record sent by a maintenance end of a maintenance person, and updating an environment parameter exception handling database.
6. The method according to claim 5, wherein the identifying an abnormal event according to the surveillance video data in S3 specifically includes:
Acquiring installation parameters of a camera, selecting a plurality of fixed reference points in the view angle range of the camera, acquiring reference point coordinates through Bluetooth tags, establishing a two-dimensional monitoring coordinate system in a video image based on physical space coordinates of the reference points, mapping the physical space coordinates of the reference points into the video image to form the monitoring coordinate system, and finishing coordinate mapping and positioning of video and physical space;
acquiring real-time monitoring video data from cameras of a production place, and preprocessing the acquired monitoring video data, wherein the preprocessing comprises video denoising and image enhancement;
analyzing the video data and detecting whether suspected flames exist or not;
After confirming that suspected flames exist, sending a fire early-warning first-level notification to a mobile terminal of maintainers, wherein the fire early-warning first-level notification comprises suspected flame monitoring images, occurrence time and positioning;
acquiring maintenance end of maintenance personnel and positioning data of suspected flames;
Monitoring the position relation between related personnel and suspected flames, and when maintenance personnel do not complete positioning contact within a preset range within preset time, performing primary alarm through alarm equipment, and opening a fire control spray header within the preset range according to positioning data of the suspected flames;
and acquiring a maintenance record sent by a maintenance end of a maintenance person, and updating a monitoring video exception handling database.
7. The method of claim 6, wherein the detecting whether a suspected flame is present comprises:
The method comprises the steps of extracting color information of each pixel in a video image, converting an RGB color space into an HSV color space, defining a color range of flame, setting an H channel to be 0% -50%, setting an S channel to be 50% -100% and setting a V channel to be 50% -100%, carrying out color detection on each frame of image, identifying the pixels conforming to the color characteristics of the flame, and generating a binarized flame candidate region image;
analyzing the difference between video frames, analyzing the pixel motion in a flame candidate area by an optical flow method, detecting random flicker and edge jump of flame, identifying the dynamic change of the flame by using a background subtraction algorithm, reducing the flame candidate area of the flame candidate area image, and eliminating the color matching objects of non-flame;
comparing the currently detected flame candidate region with a historical flame image library by using a SIFT similarity matching algorithm, and judging whether the currently detected flame candidate region is matched with the previous flame event features;
Different weights are distributed to color detection, dynamic pattern recognition and historical data checking results, flame suspected values are calculated based on the weights, the obtained flame suspected values are compared with a preset credibility threshold, and when the flame suspected values exceed the credibility threshold, suspected flames are judged to exist.
8. The method of claim 6, wherein upon confirming the existence of a suspected flame further comprises:
after confirming that the suspected flame exists, acquiring the positioning of the suspected flame, and generating a range area covering a preset radius as a dangerous area;
determining a personnel list positioned in the current dangerous area based on the Bluetooth AOA positioning system, screening personnel passing through the current dangerous area according to historical movement data of the personnel, updating the personnel list and generating a dangerous personnel list;
And sending a dangerous person list and an evacuation notification to the mobile terminal of the maintainer, and broadcasting fire alarm information of the name of the dangerous person list through alarm equipment.
9. The method according to claim 1, wherein S4 specifically comprises:
Acquiring collected positioning data, running state data and/or electrical parameters, temperature, humidity and/or gas concentration parameters and monitoring video data, synchronizing time stamps of different data sources, and performing preliminary processing on different types of data through a feature extraction tool to form a multi-source data set suitable for a convolutional neural network model input format based on a multi-input structure;
loading a pre-trained convolutional neural network model based on a multi-input structure;
the processed multi-source data set is used as input data and is input into a convolutional neural network model based on a multi-input structure;
Extracting characteristics of input data through multi-layer convolution operation in a convolution neural network model based on a multi-input structure, and integrating and classifying the extracted characteristics through a full connection layer of the convolution neural network model based on the multi-input structure;
And generating a risk identification result according to the output of the convolutional neural network model based on the multi-input structure.
10. An industrial internet-based data processing system utilizing the method of any of claims 1-9, comprising:
the production data acquisition module is used for acquiring positioning data of personnel, equipment and materials in each link of a production line through the Bluetooth AOA positioning system, acquiring running state data and/or electric parameters of the equipment through the equipment state sensor, acquiring temperature, humidity and/or gas concentration parameters of a production place through the environment sensor, and acquiring monitoring video data of the production place through the camera;
the data processing module is used for transmitting the acquired data to the large data center server through industrial Internet equipment and cleaning and preprocessing the data;
the risk emergency identification module is used for identifying the fault risk of the equipment according to the positioning data, the running state data and the electrical parameters of the equipment, identifying the abnormal condition of the material according to the positioning data of the material, identifying the abnormal condition of the environment according to the environment parameters provided by the environment sensor, identifying the abnormal event according to the monitoring video data, and sending a first-level early warning notice to maintenance personnel or carrying out first-level warning through the warning equipment;
The risk comprehensive identification module is used for analyzing the multi-source data through a pre-trained convolutional neural network, carrying out comprehensive risk identification and outputting an identification result;
The intelligent decision module is used for converting the identification result into a vector form and executing fusion intelligent decision, and the intelligent decision comprises the steps of sending a primary early warning notice to maintenance personnel or carrying out primary alarm through alarm equipment, executing secondary alarm, stopping and/or reporting to a management end of a manager.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411139067.3A CN119089351A (en) | 2024-08-20 | 2024-08-20 | A data processing method and system based on industrial Internet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411139067.3A CN119089351A (en) | 2024-08-20 | 2024-08-20 | A data processing method and system based on industrial Internet |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119089351A true CN119089351A (en) | 2024-12-06 |
Family
ID=93693792
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411139067.3A Pending CN119089351A (en) | 2024-08-20 | 2024-08-20 | A data processing method and system based on industrial Internet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119089351A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119296014A (en) * | 2024-12-13 | 2025-01-10 | 上海民原科技有限公司 | An intelligent judicial security control system |
| CN119383245A (en) * | 2024-11-04 | 2025-01-28 | 北京天地和兴科技有限公司 | Message sending and receiving method, system and medium based on industrial Internet |
| CN119644969A (en) * | 2025-02-17 | 2025-03-18 | 可之(宁波)人工智能科技有限公司 | Industrial production monitoring method, system, terminal and storage medium based on large model |
| CN120067737A (en) * | 2025-04-28 | 2025-05-30 | 江西五十铃汽车有限公司 | Environmental control method, system, readable storage medium and electronic device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103795984A (en) * | 2014-02-07 | 2014-05-14 | 彭世藩 | Self-learning omnibearing mobile monitoring system |
| CN107146168A (en) * | 2017-07-11 | 2017-09-08 | 大连锐勃电子科技有限公司 | Smart construction site management system based on global frequency conversion positioning and self-identification technology |
| CN117351643A (en) * | 2023-09-26 | 2024-01-05 | 山信软件股份有限公司 | Safety production early warning prevention and control method |
| CN117788223A (en) * | 2024-01-22 | 2024-03-29 | 浙江建设职业技术学院 | Building construction management method based on multi-data fusion |
-
2024
- 2024-08-20 CN CN202411139067.3A patent/CN119089351A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103795984A (en) * | 2014-02-07 | 2014-05-14 | 彭世藩 | Self-learning omnibearing mobile monitoring system |
| CN107146168A (en) * | 2017-07-11 | 2017-09-08 | 大连锐勃电子科技有限公司 | Smart construction site management system based on global frequency conversion positioning and self-identification technology |
| CN117351643A (en) * | 2023-09-26 | 2024-01-05 | 山信软件股份有限公司 | Safety production early warning prevention and control method |
| CN117788223A (en) * | 2024-01-22 | 2024-03-29 | 浙江建设职业技术学院 | Building construction management method based on multi-data fusion |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119383245A (en) * | 2024-11-04 | 2025-01-28 | 北京天地和兴科技有限公司 | Message sending and receiving method, system and medium based on industrial Internet |
| CN119296014A (en) * | 2024-12-13 | 2025-01-10 | 上海民原科技有限公司 | An intelligent judicial security control system |
| CN119644969A (en) * | 2025-02-17 | 2025-03-18 | 可之(宁波)人工智能科技有限公司 | Industrial production monitoring method, system, terminal and storage medium based on large model |
| CN120067737A (en) * | 2025-04-28 | 2025-05-30 | 江西五十铃汽车有限公司 | Environmental control method, system, readable storage medium and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118072255B (en) | Intelligent park multisource data dynamic monitoring and real-time analysis system and method | |
| CN119089351A (en) | A data processing method and system based on industrial Internet | |
| Lestari et al. | Fire hotspots detection system on CCTV videos using you only look once (YOLO) method and tiny YOLO model for high buildings evacuation | |
| KR102149832B1 (en) | Automated Violence Detecting System based on Deep Learning | |
| CN114926781B (en) | Multi-person time-space domain abnormal behavior positioning method and system supporting real-time monitoring scene | |
| US20240233385A1 (en) | Multi modal video captioning based image security system and method | |
| CN118486152B (en) | Security alarm information data interaction system and method | |
| KR102263512B1 (en) | IoT integrated intelligent video analysis platform system capable of smart object recognition | |
| CN118470890A (en) | Fire safety monitoring method and system based on Internet of things | |
| CN116862244B (en) | Industrial field vision AI analysis and safety pre-warning system and method | |
| CN114218992A (en) | Abnormal object detection method and related device | |
| CN119600503A (en) | Public safety situation prediction method and system based on multi-mode data fusion | |
| CN119229355A (en) | A terminal device collaborative video monitoring method and system | |
| CN118506446A (en) | Distribution network engineering worker illegal behavior identification method, system and medium | |
| KR101581162B1 (en) | Automatic detection method, apparatus and system of flame, smoke and object movement based on real time images | |
| CN119672613A (en) | A surveillance video information intelligent processing system based on cloud computing | |
| CN119671283A (en) | A behavior analysis and safety risk prevention and control system for electrical workers | |
| CN119672904A (en) | A method for discovering and warning potential safety hazards in confined space operations | |
| CN119625632A (en) | A 5G message video monitoring method and system based on artificial intelligence | |
| CN119228133A (en) | Method for determining the operation safety risk of operators and safety risk linkage system | |
| CN119205839A (en) | Monitoring image processing system and method based on big data | |
| CN116597501A (en) | Video analysis algorithm and edge device | |
| Singh et al. | Exploring anomaly detection techniques for crime detection | |
| CN118365475B (en) | Intelligent monitoring method and device for photovoltaic power plant | |
| CN117354495B (en) | Video monitoring quality diagnosis method and system based on deep learning |
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 |