A detection method, device, medium and electronic device for a substation monitoring system

Abstract

The present application discloses a detection method, device, medium, and electronic device for a substation monitoring system. It relates to the technical field of substations. The method includes: determining the monitored objects of the monitored monitoring system to be detected and the test data set corresponding to the monitored objects based on the detection requirements; controlling the monitored objects to perform test operations according to the test data set in response to the test operation control instruction of the user; obtaining the image data generated after the monitored objects execute the test operations collected by a preset image collector; and using a preset image recognition model to recognize the image data to obtain the detection result of the monitored monitoring system to be detected. The method of the present application can improve the detection efficiency and accuracy of the substation monitoring system.

Description

Technical Field

[0001] The present invention relates to the technical field of substations, and particularly relates to a method, device, medium and electronic device for detecting a substation monitoring system. Background Art

[0002] As one of the key links in the construction of the smart grid, a substation is the information perception source of power grid operation and the command execution terminal of power grid control, the core node of power flow and information flow, and the basic support for the safe and stable operation of the power grid. With the development of technology, the substation monitoring system plays an increasingly important role in improving the operation efficiency of substations, preventing accidents, and responding to faults in a timely manner. The basic functions of the substation monitoring system cover multiple aspects such as real-time monitoring and data acquisition, fault detection and early warning, remote control and automated operation, and data management and report generation, which are all key technical measures to ensure the efficient and stable operation of substations. Among them, real-time data can help managers understand the operating status of equipment, discover potential problems in a timely manner, and take corresponding measures; when the equipment shows abnormalities or faults, the system can issue an alarm in a timely manner to remind managers to handle it, thereby reducing the risk of equipment damage and power outages. Therefore, the accuracy of telemetry and telecommunication signals is the basis for the safe and stable operation of substations. The traditional automatic detection of substation monitoring systems uses the data collected by process layer equipment or the data forwarded by bay layer equipment for identification to achieve the automatic detection of substation monitoring systems. Although abnormalities can be detected, the detection results are not accurate enough. Summary of the Invention

[0003] In view of this, the present invention provides a method, device, medium and electronic device for detecting a substation monitoring system, mainly aiming to solve the problem that the detection results of the current automatic detection of substation monitoring systems are not accurate enough.

[0004] To solve the above problems, the present application provides a method for detecting a substation monitoring system, including:

[0005] Determining the monitored object of the monitoring system to be detected and the test data set corresponding to the monitored object based on the detection requirements;

[0006] Responding to the test operation control instruction of the user, controlling the monitored object to perform a test operation according to the test data set;

[0007] Obtaining the image data generated after the monitored object performs the test operation collected by a preset image collector;

[0008] Using a preset image recognition model to recognize the image data to obtain the detection result of the monitoring system to be detected.

[0009] Optionally, in response to the test operation control instruction of the user, controlling the monitored object to perform a test operation according to the test data set specifically includes:

[0010] Sending the telemetry test instruction in the control instruction to a preset tester to control the preset tester to perform a telemetry control operation on the monitored object according to the telemetry data in the test data set;

[0011] Sending the telecommunication test instruction in the control instruction to a preset emulator to control the preset emulator to perform a telecommunication control operation on the monitored object according to the telecommunication data in the test data set.

[0012] Optionally, before using the preset image recognition model to recognize the image data, the method further includes constructing the preset image recognition model;

[0013] The constructing of the preset image recognition model specifically includes:

[0014] Obtaining a plurality of historical primary wiring image data;

[0015] Performing preprocessing on each of the historical primary wiring image data to obtain an initial training data set, and the preprocessing process includes data cleaning, data normalization processing, and data augmentation processing;

[0016] Labeling the initial training data set to obtain a label data set;

[0017] Training an initial neural network recognition model based on the label data set as a training sample to generate the preset image recognition model.

[0018] Optionally, the training the initial neural network recognition model based on the label data set as a training sample to generate the preset image recognition model specifically includes:

[0019] Preprocessing each label data in the label data set by using the input layer of the initial neural network recognition model to obtain first image data corresponding to each label data;

[0020] Performing local feature extraction on each of the first image data by using the convolutional layer of the initial neural network recognition model to obtain first feature data corresponding to each of the first image data;

[0021] Performing downsampling processing on each of the feature data by using the pooling layer of the initial neural network recognition model to obtain second feature data corresponding to each of the first feature data;

[0022] Use the fully connected layer of the initial neural network recognition model to recognize each piece of the second feature data, obtaining an initial prediction data set;

[0023] Based on the initial prediction data set and the label data set, use a preset cross-entropy loss function to update the model parameters of the initial neural network recognition model, generating a current neural network recognition model;

[0024] Based on the label data set as training samples, iteratively train the current neural network recognition model in a loop until the loss value obtained by calculation using the preset cross-entropy loss function meets the preset conditions, and then determine the current neural network recognition model as the preset image recognition model.

[0025] Optionally, using the preset image recognition model to recognize the image data to obtain the detection result of the to-be-detected monitoring system specifically includes:

[0026] Preprocess the image data to obtain an image to be recognized;

[0027] Use the preset image recognition model to recognize the image to be recognized, obtaining a prediction data set corresponding to the monitored object in the image to be recognized;

[0028] Based on the test data set, detect the prediction data set to obtain the detection result of the to-be-detected monitoring system.

[0029] Optionally, using the preset image recognition model to recognize the image to be recognized, obtaining a prediction data set corresponding to the monitored object in the image to be recognized specifically includes:

[0030] Use the input layer of the preset image recognition model to preprocess the image to be recognized, obtaining second image data corresponding to the image to be recognized;

[0031] Use the convolutional layer of the preset image recognition model to extract local features from the second image data, obtaining first target feature data corresponding to the second image data;

[0032] Use the pooling layer of the preset image recognition model to perform downsampling on the first target feature data, obtaining second target feature data corresponding to the first target feature data;

[0033] Use the fully connected layer of the preset image recognition model to recognize the second target feature data, obtaining a prediction data set corresponding to the monitored object in the image to be recognized;

[0034] Among them, the prediction data set includes prediction device information, prediction category information, prediction telemetry data, and prediction telecontrol data.

[0035] Optionally, after using a preset image recognition model to recognize the image data and obtaining the detection result of the to-be-detected monitoring system, the method further includes:

[0036] Generating a test report for the to-be-detected monitoring system based on the detection result and a preset template.

[0037] To solve the above problems, the present application provides a substation monitoring system detection device, including:

[0038] A determination module, configured to determine a monitored object of the to-be-detected monitoring system and a test data set corresponding to the monitored object based on detection requirements;

[0039] An operation module, configured to control the monitored object to perform a test operation according to the test data set in response to a user's test operation control instruction;

[0040] An acquisition module, configured to acquire image data generated after the monitored object executes the test operation collected by a preset image collector;

[0041] An identification module, configured to use a preset image recognition model to recognize the image data and obtain the detection result of the to-be-detected monitoring system.

[0042] To solve the above problems, the present application provides a storage medium, characterized in that the storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned substation monitoring system detection method are implemented.

[0043] To solve the above problems, the present application provides an electronic device, characterized in that it includes at least a memory and a processor, the memory stores a computer program, and when the processor executes the computer program on the memory, the steps of the above-mentioned substation monitoring system detection method are implemented

[0044] The beneficial effects in the present application: The present application detects the to-be-detected monitoring system by collecting a primary wiring diagram as image data, and uses a preset image recognition model to recognize the image data, which can discover potential electrical connection errors or equipment defects, make corrections in a timely manner, avoid electrical accidents caused by wiring errors, and at the same time, the primary wiring diagram can display the connection status of the equipment in real time, helping the operation and maintenance personnel quickly locate the fault point, and improving the efficiency and accuracy of fault handling.

[0045] The above description is only an overview of the technical solution of the present invention. In order to understand the technical means of the present invention more clearly, it can be implemented according to the content of the specification. And in order to make the above and other objects, features and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention are specifically exemplified below. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0047] Figure 1 The flowchart of a method for detecting a substation monitoring system provided by an embodiment of the present application is shown;

[0048] Figure 2 The flowchart of a method for detecting a substation monitoring system provided by another embodiment of the present application is shown;

[0049] Figure 3 The schematic diagram of the principle for detecting a substation monitoring system to be detected according to an embodiment of the present application is shown;

[0050] Figure 4 The structural block diagram of a device for detecting a substation monitoring system provided by another embodiment of the present application is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] Reference is made herein to the various aspects and features of the present application with reference to the drawings.

[0052] It should be understood that various modifications can be made to the embodiments described herein. Therefore, the above description should not be construed as a limitation, but only as an example of the embodiments. Those skilled in the art will envision other modifications within the scope and spirit of the present application.

[0053] The drawings included in and forming a part of the specification illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, serve to explain the principles of the present application.

[0054] These and other features of the present application will become apparent from the following description of the preferred form of the embodiments given by way of non-limiting example with reference to the drawings.

[0055] It should also be understood that although the present application has been described with reference to some specific examples, those skilled in the art can surely implement many other equivalent forms of the present application.

[0056] The above and other aspects, features, and advantages of the present application will become more apparent in view of the following detailed description when taken in conjunction with the accompanying drawings.

[0057] Specific embodiments of the present application will be described hereinafter with reference to the accompanying drawings; however, it should be understood that the embodiments claimed are merely examples of the present application, which can be implemented in various ways. Well-known and / or repetitive functions and structures are not described in detail to avoid obscuring the present application with unnecessary or redundant details. Therefore, the specific structural and functional details claimed herein are not intended to be limiting, but are merely a basis and representative basis for the claims to teach those skilled in the art to use the present application in substantially any suitable detailed structure in a variety of ways.

[0058] This specification may use the phrases "in one embodiment", "in another embodiment", "in yet another embodiment", or "in other embodiments", each of which may refer to one or more of the same or different embodiments according to the present application.

[0059] An embodiment of the present application provides a method for detecting a substation monitoring system, as Figure 1 shown, including:

[0060] Step S101: Determine the monitored object of the monitoring system to be detected and the test data set corresponding to the monitored object based on the detection requirement;

[0061] In the specific implementation process of this step, the detection requirement may be the requirement to detect one or more monitored objects of the monitoring system to be detected; the monitored object may be each intelligent electronic device (IED) monitored by the monitoring system to be detected; the test data set may be obtained from the substation configuration description (SCD) file. The SCD file describes the instance configuration and communication parameters of all IEDs, the communication configuration between IEDs, and the primary system structure of the substation. The monitoring system to be detected realizes the unified access, unified storage, and unified management of substation information such as power grid and equipment operation information, status monitoring information, and metering information through system integration optimization and information sharing, and realizes functions such as substation operation monitoring, operation and control, comprehensive information analysis and intelligent alarm, operation management, and auxiliary applications, and provides unified substation operation and access services for master stations such as dispatching and production. Based on the user's detection requirement, determine the monitored object of the monitoring system to be detected; the monitored object is at least one device to be monitored. Query the substation configuration description file based on the monitored object to obtain the test data set corresponding to the monitored object.

[0062] Step S102: Determine the monitored object of the monitored monitoring system and the test data set corresponding to the monitored object based on the detection requirements;

[0063] In the specific implementation process of this step, in response to the test operation clicked by the user, a control instruction for the detection requirements is generated; the control instruction is a control instruction for controlling the monitored object to perform a test operation according to the test data set. Specifically, the control instruction includes a telemetry test instruction for performing a test operation on the monitored object and a telecommunication test instruction for performing a test operation on the monitored object.

[0064] Step S103: Obtain the image data generated after the monitored object executes the test operation collected by the preset image collector;

[0065] In the specific implementation process of this step, the substation monitoring system receives the operation data sent by the monitored object through the station control layer network; an image splitting joint is configured at the output end of the substation monitoring system; the image splitting joint copies the image signal sent by the substation monitoring system to obtain two identical first image signals; one of the first image signals is signal-converted to generate a first fully digital audio and video transmission interface signal, that is, an HDMI signal, and the HDMI signal is sent to a preset display for display; the other first image signal is signal-converted to generate a second fully digital audio and video transmission interface signal HDMI signal and then sent to a preset image collector; receive the image data generated after the monitored object executes the control instruction collected by the preset image collector, and the image data is a primary wiring diagram; the primary wiring diagram is a substation configuration description language that describes the primary system structure of the substation and related logical nodes, describes the instance configuration and communication parameters of all IEDs, and the communication configuration between IEDs; it lays a foundation for subsequent identification of the image data using a preset image recognition model.

[0066] Step S104: Use a preset image recognition model to recognize the image data to obtain the detection result of the monitored monitoring system.

[0067] In the specific implementation process of this step, the image data is preprocessed to obtain the image to be recognized; the preset image recognition model is used to recognize the image to be recognized, and a prediction data set corresponding to the monitored object in the image to be recognized is obtained; the prediction data set includes data such as predicted device information, predicted category information, predicted telemetry data, and predicted telecontrol data. The prediction data set is detected based on the test data set to obtain the detection result of the monitored system to be detected. Specifically, the detection result of the monitored system to be detected is obtained based on the predicted device information, predicted category information, predicted telemetry data, predicted telecontrol data, and the initial device information, initial category information, initial telemetry data, and initial telecontrol data corresponding to the monitored object in the pre-obtained test data set.

[0068] In this application, the one-line diagram is collected as image data to detect the monitored system to be detected, and the preset image recognition model is used to recognize the image data, so that potential electrical connection errors or device defects can be found and corrected in time to avoid electrical accidents caused by wiring errors. At the same time, the one-line diagram can display the connection status of the device in real time, helping the operation and maintenance personnel quickly locate the fault point and improving the efficiency and accuracy of fault handling.

[0069] Another embodiment of this application provides another method for detecting a substation monitoring system, as Figure 2 shown, including:

[0070] Step S201: Determine the monitored object of the monitored system to be detected and the test data set corresponding to the monitored object based on the detection requirements;

[0071] In the specific implementation process of this step, the detection requirement may be the requirement to detect one or more monitored objects of the monitored monitoring system; the monitored object may be each intelligent electronic device (IED) monitored by the monitored monitoring system; the test data set can be obtained from the Substation Configuration Description (SCD) file. The SCD file describes the instance configuration and communication parameters of all IEDs, the communication configuration between IEDs, and the primary system structure of the substation. The monitored monitoring system realizes the unified access, unified storage, and unified management of substation information such as power grid and equipment operation information, status monitoring information, and metering information through system integration optimization and information sharing, and realizes functions such as substation operation monitoring, operation and control, comprehensive information analysis, and intelligent alarm, operation management, and auxiliary applications, and provides unified substation operation and access services for master systems such as dispatching and production. Based on the user's detection requirement, determine the monitored object of the monitored monitoring system; the monitored object is at least one device to be monitored. Query the substation system configuration file based on the monitored object to obtain a test data set corresponding to the monitored object.

[0072] Step S202: In response to the user's test operation control instruction, control the monitored object to perform a test operation according to the test data set;

[0073] In the specific implementation process of this step, in response to the test operation clicked by the user, generate a control instruction for the detection requirement; the control instruction is a control instruction for controlling the monitored object to perform a test operation according to the test data set. Specifically, the control instruction includes a telemetry test instruction for performing a test operation on the monitored object and a teleindication test instruction for performing a test operation on the monitored object. Send the telemetry test instruction in the control instruction to a preset tester to control the preset tester to perform a telemetry control operation on the monitored object according to the telemetry data in the test data set; as Figure 3As shown in the figure, it is a schematic diagram of the principle for detecting the substation to-be-detected monitoring system of the present application; the substation monitoring system detection method is applied to an automatic test host, and the automatic test host sends the telemetry test instruction in the control instruction to a preset tester to control the preset tester to perform telemetry control on the monitored object according to the telemetry data in the test dataset. The tele-signal test instruction in the control instruction is sent to a preset emulator to control the preset emulator to perform tele-signal control operations on the monitored object according to the tele-signal data in the test dataset; the automatic test host sends the tele-signal test instruction in the control instruction to a preset emulator to control the preset tester to perform tele-signal control on the monitored object according to the tele-signal data in the test dataset.

[0074] Step S203: Construct a preset image recognition model;

[0075] In the specific implementation process of this step, a number of historical primary wiring image data are obtained; preprocessing is performed on each of the historical primary wiring image data to obtain an initial training dataset, and the preprocessing process includes data cleaning, data normalization processing, and data augmentation processing; the initial training dataset is labeled to obtain a label dataset; based on the label dataset as training samples, the initial neural network recognition model is trained to generate the preset image recognition model. Specifically, the input layer of the initial neural network recognition model is used to preprocess each label data in the label dataset to obtain first image data corresponding to each label data; the convolutional layer of the initial neural network recognition model is used to extract local features from each of the first image data to obtain first feature data corresponding to each of the first image data; the pooling layer of the initial neural network recognition model is used to perform downsampling processing on each of the feature data to obtain second feature data corresponding to each of the first feature data; the fully connected layer of the initial neural network recognition model is used to recognize each of the second feature data to obtain an initial prediction dataset; based on the initial prediction dataset and the label dataset, a preset cross-entropy loss function is used to update the model parameters of the initial neural network recognition model to generate a current neural network recognition model; based on the label dataset as training samples, the current neural network recognition model is cyclically and iteratively trained until the loss value calculated by using the preset cross-entropy loss function meets the preset conditions, and the current neural network recognition model is determined as the preset image recognition model.

[0076] Step S204: Preprocess the image data to obtain an image to be recognized;

[0077] In the specific implementation process of this step, data cleaning is performed on the image data to remove noise and adjust the size of the image, generating a first image to be recognized; data normalization processing is performed on the first image to be recognized to obtain a second image to be recognized; data augmentation processing is performed on the second image to be recognized to obtain the image to be recognized.

[0078] Step S205: Use the preset image recognition model to recognize the image to be recognized, obtaining a prediction data set corresponding to the monitored object in the image to be recognized;

[0079] In the specific implementation process of this step, preprocessing is performed on the image to be recognized using the input layer of the preset image recognition model to obtain second image data corresponding to the image to be recognized; local feature extraction is performed on the second image data using the convolutional layer of the preset image recognition model to obtain first target feature data corresponding to the second image data; downsampling processing is performed on the first target feature data using the pooling layer of the preset image recognition model to obtain second target feature data corresponding to the first target feature data; recognition is performed on the second target feature data using the fully connected layer of the preset image recognition model to obtain a prediction data set corresponding to the monitored object in the image to be recognized; wherein, the prediction data set includes predicted device information, predicted category information, predicted telemetry data, and predicted telecontrol data. The predicted device information includes information such as device name and device ID; the predicted category information is the device type, and the predicted category information is device type information such as switch and disconnecting switch; the predicted telemetry data includes information such as predicted voltage data and predicted current data; the predicted telecontrol data includes data information such as the graphic element state being open and closed; the prediction data set further includes predicted alarm character information, and the predicted alarm character information is information such as interruption.

[0080] Step S206: Detect the prediction data set based on the test data set to obtain the detection result of the monitored control system to be detected;

[0081] In the specific implementation process of this step, detection is performed based on the predicted device information, predicted category information, predicted telemetry data, predicted telecontrol data, and the initial device information, initial category information, initial telemetry data, and initial telecontrol data corresponding to the monitored object in the pre-acquired test dataset, to obtain the detection result of the monitored system to be detected. Specifically, the device information detection result is obtained by comparing the predicted device information with the initial device information corresponding to the monitored object; the device category detection result is obtained by comparing the predicted category information with the initial category information corresponding to the monitored object; the telemetry data detection result is obtained by comparing the predicted telemetry data with the initial telemetry data corresponding to the monitored object; the telecontrol data detection result is obtained by comparing the predicted telecontrol data with the initial telecontrol data corresponding to the monitored object; when any one of the device information detection result, device category detection result, telemetry data detection result, and telecontrol data detection result does not meet the preset conditions, an alarm is issued for the fault, and fault location is performed based on the detection result that does not meet the preset conditions, so as to identify potential electrical connection errors or device defects, and timely corrections are made to avoid electrical accidents caused by wiring errors. At the same time, the primary wiring diagram can display the connection status of the device in real time, helping the operation and maintenance personnel quickly locate the fault point, and improving the efficiency and accuracy of fault handling.

[0082] Step S207: Generate a test report for the monitored system to be detected based on the detection result and a preset template.

[0083] In the specific implementation process of this step, the device information detection result, device category detection result, telemetry data detection result, and telecontrol data detection result are used to construct a test report using a preset template, generating a test report for the monitored system that reflects the device information detection result, device category detection result, telemetry data detection result, and telecontrol data detection result, and prompting the fault information in the detection result.

[0084] This application detects the monitored system to be detected by collecting the primary wiring diagram as image data, and uses a preset image recognition model to recognize the image data, which can discover potential electrical connection errors or device defects, and timely corrections are made to avoid electrical accidents caused by wiring errors. At the same time, the primary wiring diagram can display the connection status of the device in real time, helping the operation and maintenance personnel quickly locate the fault point, and improving the efficiency and accuracy of fault handling.

[0085] Another embodiment of this application provides a detection device for a substation monitoring system, as Figure 4 shown, including:

[0086] Determination module 1, configured to determine the monitored object of the monitored monitoring system and the corresponding test data set for the monitored object based on the detection requirements;

[0087] Operation module 2, configured to control the monitored object to perform a test operation according to the test data set in response to a test operation control instruction of a user;

[0088] Acquisition module 3, configured to acquire image data generated after the monitored object performs the test operation collected by a preset image collector;

[0089] Recognition module 4, configured to recognize the image data by using a preset image recognition model to obtain the detection result of the monitored monitoring system.

[0090] In a specific implementation process, the operation module 2 is specifically configured to: send the telemetry test instruction in the control instruction to a preset tester to control the preset tester to perform a telemetry control operation on the monitored object according to the telemetry data in the test data set; send the telecontrol test instruction in the control instruction to a preset simulator to control the preset simulator to perform a telecontrol control operation on the monitored object according to the telecontrol data in the test data set.

[0091] In a specific implementation process, the substation monitoring system detection device further includes a preset image recognition model construction module, and the preset image recognition model is specifically configured to: acquire a plurality of historical primary wiring image data; perform preprocessing on each of the historical primary wiring image data to obtain an initial training data set, and the preprocessing process includes data cleaning, data normalization processing, and data augmentation processing; label the initial training data set to obtain a label data set; perform model training on an initial neural network recognition model based on the label data set as a training sample to generate the preset image recognition model.

[0092] In the specific implementation process, the preset image recognition model construction module is further configured to: preprocess each label data in the label data set by using the input layer of the initial neural network recognition model to obtain first image data corresponding to each label data; extract local features from each first image data by using the convolutional layer of the initial neural network recognition model to obtain first feature data corresponding to each first image data; perform downsampling processing on each feature data by using the pooling layer of the initial neural network recognition model to obtain second feature data corresponding to each first feature data; identify each second feature data by using the fully connected layer of the initial neural network recognition model to obtain an initial prediction data set; update the model parameters of the initial neural network recognition model by using a preset cross-entropy loss function based on the initial prediction data set and the label data set to generate a current neural network recognition model; based on the label data set as a training sample, cyclically and iteratively train the current neural network recognition model until the loss value obtained by using the preset cross-entropy loss function for calculation processing meets the preset condition, and determine the current neural network recognition model as the preset image recognition model.

[0093] In the specific implementation process, the recognition module 4 is specifically configured to: preprocess the image data to obtain an image to be recognized; recognize the image to be recognized by using the preset image recognition model to obtain a prediction data set corresponding to the monitored object in the image to be recognized; detect the prediction data set based on the test data set to obtain a detection result of the monitored system to be detected.

[0094] In the specific implementation process, the recognition module 4 is further configured to: preprocess the image to be recognized by using the input layer of the preset image recognition model to obtain second image data corresponding to the image to be recognized; extract local features from the second image data by using the convolutional layer of the preset image recognition model to obtain first target feature data corresponding to the second image data; perform downsampling processing on the first target feature data by using the pooling layer of the preset image recognition model to obtain second target feature data corresponding to the first target feature data; identify the second target feature data by using the fully connected layer of the preset image recognition model to obtain a prediction data set corresponding to the monitored object in the image to be recognized; wherein, the prediction data set includes predicted device information, predicted category information, predicted telemetry data, and predicted telecontrol data.

[0095] In the specific implementation process, the substation monitoring system detection device further includes a test report generation module, and the test report generation module is specifically configured to: generate a test report of the monitoring system based on the detection result and a preset template.

[0096] This application detects the to-be-detected monitoring system by collecting a primary wiring diagram as image data, and uses a preset image recognition model to recognize the image data, which can discover potential electrical connection errors or equipment defects, correct them in time, avoid electrical accidents caused by wiring errors. At the same time, the primary wiring diagram can display the connection status of the equipment in real time, helping the operation and maintenance personnel quickly locate the fault point and improve the efficiency and accuracy of fault handling.

[0097] Another embodiment of this application provides a storage medium, which stores a computer program. When the computer program is executed by a processor, the following method steps are implemented:

[0098] Step 1: Determine the monitored object of the to-be-detected monitoring system and the test data set corresponding to the monitored object based on the detection requirements;

[0099] Step 2: In response to the test operation control instruction of the user, control the monitored object to perform a test operation according to the test data set;

[0100] Step 3: Obtain the image data generated after the monitored object performs the test operation collected by a preset image collector;

[0101] Step 4: Use a preset image recognition model to recognize the image data to obtain the detection result of the to-be-detected monitoring system.

[0102] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0103] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example for illustration. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

[0104] For the specific implementation process of the above method steps, reference can be made to the embodiments of any of the above substation monitoring system detection methods, and this embodiment will not be repeated here.

[0105] This application detects the monitoring system to be detected by collecting the primary wiring diagram as image data, and uses a preset image recognition model to recognize the image data, which can discover potential electrical connection errors or equipment defects, and make corrections in a timely manner to avoid electrical accidents caused by wiring errors. At the same time, the primary wiring diagram can display the connection status of the equipment in real time, helping the operation and maintenance personnel quickly locate the fault point and improving the efficiency and accuracy of fault handling.

[0106] Another embodiment of the present application provides an electronic device, which may be a server. The electronic device includes a processor, a memory, a network interface, and a database connected via a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external client via a network connection. When the electronic device program is executed by the processor, it realizes the functions or steps on the server side of a substation monitoring system detection method.

[0107] In one embodiment, an electronic device is provided, which may be a client. The electronic device includes a processor, a memory, a network interface, a display screen, and an input device connected via a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external server via a network connection. When the electronic device program is executed by the processor, it realizes the functions or steps on the client side of a substation monitoring system detection method.

[0108] Another embodiment of the present application provides an electronic device, at least including a memory and a processor. A computer program is stored on the memory. When the processor executes the computer program on the memory, the following method steps are realized:

[0109] Step 1: Based on the detection requirements, determine the monitored object of the monitored system to be detected and the test data set corresponding to the monitored object;

[0110] Step 2: In response to the test operation control instruction of the user, control the monitored object to perform a test operation according to the test data set;

[0111] Step 3: Obtain the image data generated by the monitored object after performing the test operation collected by a preset image collector;

[0112] Step 4: Use a preset image recognition model to recognize the image data to obtain the detection result of the monitored system to be detected.

[0113] For the specific implementation process of the above method steps, reference can be made to the embodiments of any of the above substation monitoring system detection methods, and this embodiment will not be repeated here.

[0114] This application detects the to-be-detected monitoring system by collecting a primary wiring diagram as image data, and uses a preset image recognition model to recognize the image data, which can discover potential electrical connection errors or equipment defects, and make corrections in a timely manner to avoid electrical accidents caused by wiring errors. At the same time, the primary wiring diagram can display the connection status of the equipment in real time, helping the operation and maintenance personnel quickly locate the fault point, and improving the efficiency and accuracy of fault handling.

[0115] The above embodiments are only exemplary embodiments of this application and are not used to limit this application. The protection scope of this application is defined by the claims. Those skilled in the art can make various modifications or equivalent replacements to this application within the essence and protection scope of this application, and such modifications or equivalent replacements should also be regarded as falling within the protection scope of this application.

Claims

1. A detection method for a substation monitoring system, characterized in that Including: Determine the monitored object of the monitored monitoring system to be detected and the test data set corresponding to the monitored object based on the detection requirements; In response to the test operation control instruction of the user, control the monitored object to perform a test operation according to the test data set; Obtain the image data generated after the monitored object performs the test operation collected by the preset image collector; Use the preset image recognition model to recognize the image data to obtain the detection result of the monitored monitoring system to be detected; Before using the preset image recognition model to recognize the image data to obtain the detection result of the monitored monitoring system to be detected, the method further includes: constructing a preset image recognition model; The constructing of the preset image recognition model specifically includes: Use the input layer of the initial neural network recognition model to preprocess each label data in the label data set to obtain the first image data corresponding to each label data; Use the convolutional layer of the initial neural network recognition model to extract local features from each first image data to obtain the first feature data corresponding to each first image data; Use the pooling layer of the initial neural network recognition model to perform downsampling processing on each feature data to obtain the second feature data corresponding to each first feature data; Use the fully connected layer of the initial neural network recognition model to recognize each second feature data to obtain an initial prediction data set; Based on the initial prediction data set and the label data set, use the preset cross-entropy loss function to update the model parameters of the initial neural network recognition model to generate the current neural network recognition model; Based on the label data set as the training sample, iteratively train the current neural network recognition model in a loop until the loss value obtained by using the preset cross-entropy loss function for calculation processing meets the preset conditions, and determine the current neural network recognition model as the preset image recognition model; The using the preset image recognition model to recognize the image data to obtain the detection result of the monitored monitoring system to be detected specifically includes: Preprocess the image data to obtain the image to be recognized; Use the preset image recognition model to recognize the image to be recognized to obtain a prediction data set corresponding to the monitored object in the image to be recognized; Based on the test data set, detect the prediction data set to obtain the detection result of the monitored monitoring system to be detected; The using the preset image recognition model to recognize the image to be recognized to obtain a prediction data set corresponding to the monitored object in the image to be recognized specifically includes: Use the input layer of the preset image recognition model to preprocess the image to be recognized to obtain the second image data corresponding to the image to be recognized; Use the convolutional layer of the preset image recognition model to extract local features from the second image data to obtain the first target feature data corresponding to the second image data; Perform downsampling processing on the first target feature data using the pooling layer of the preset image recognition model to obtain second target feature data corresponding to the first target feature data; Perform recognition on the second target feature data using the fully connected layer of the preset image recognition model to obtain a prediction data set corresponding to the monitored object in the image to be recognized; Among them, the prediction data set includes predicted device information, predicted category information, predicted telemetry data, and predicted telecontrol signal data.

2. The method according to claim 1, wherein The step of controlling the monitored object to perform a test operation according to the test data set in response to the user's test operation control instruction specifically includes: Send the telemetry test instruction in the control instruction to a preset tester to control the preset tester to perform a telemetry control operation on the monitored object according to the telemetry data in the test data set; Send the telecontrol signal test instruction in the control instruction to a preset simulator to control the preset simulator to perform a telecontrol signal control operation on the monitored object according to the telecontrol signal data in the test data set.

3. The method according to claim 1, characterized in that Before using the preset image recognition model to recognize the image data, the method further includes constructing the preset image recognition model; The constructing of the preset image recognition model specifically includes: Obtain a number of historical primary wiring diagram image data; Perform preprocessing on each of the historical primary wiring diagram image data to obtain an initial training data set. The preprocessing process includes data cleaning, data normalization processing, and data augmentation processing; Annotate the initial training data set to obtain a labeled data set; Use the labeled data set as a training sample to train an initial neural network recognition model to generate the preset image recognition model.

4. The method according to claim 1, characterized in that, After using the preset image recognition model to recognize the image data and obtaining the detection result of the monitored system to be detected, the method further includes: Generate a test report for the monitored system to be detected based on the detection result and a preset template.

5. A detection device for a substation monitoring system, characterized in that, Including: A determination module, configured to determine the monitored object of the monitored system to be detected and the test data set corresponding to the monitored object based on the detection requirement; An operation module, configured to control the monitored object to perform a test operation according to the test data set in response to the user's test operation control instruction; An acquisition module, configured to acquire the image data generated after the monitored object executes the test operation collected by a preset image collector; A preset image recognition model construction module is used to preprocess each label data in the label dataset by using the input layer of the initial neural network recognition model to obtain first image data corresponding to each label data; extract local features from each first image data by using the convolutional layer of the initial neural network recognition model to obtain first feature data corresponding to each first image data; perform downsampling processing on each feature data by using the pooling layer of the initial neural network recognition model to obtain second feature data corresponding to each first feature data; identify each second feature data by using the fully connected layer of the initial neural network recognition model to obtain an initial prediction dataset; update the model parameters of the initial neural network recognition model based on the initial prediction dataset and the label dataset by using a preset cross-entropy loss function to generate a current neural network recognition model; based on the label dataset as a training sample, iteratively train the current neural network recognition model in a loop until the loss value obtained by using the preset cross-entropy loss function for calculation processing meets the preset condition, and then determine the current neural network recognition model as the preset image recognition model; A recognition module is used to recognize the image data by using the preset image recognition model to obtain the detection result of the to-be-detected monitoring system, specifically used to preprocess the image data to obtain an image to be recognized; recognize the image to be recognized by using the preset image recognition model to obtain a prediction dataset corresponding to the monitored object in the image to be recognized; Detect the prediction dataset based on the test dataset to obtain the detection result of the to-be-detected monitoring system; The step of recognizing the image to be recognized by using the preset image recognition model to obtain a prediction dataset corresponding to the monitored object in the image to be recognized specifically includes: preprocessing the image to be recognized by using the input layer of the preset image recognition model to obtain second image data corresponding to the image to be recognized; extracting local features from the second image data by using the convolutional layer of the preset image recognition model to obtain first target feature data corresponding to the second image data; performing downsampling processing on the first target feature data by using the pooling layer of the preset image recognition model to obtain second target feature data corresponding to the first target feature data; identifying the second target feature data by using the fully connected layer of the preset image recognition model to obtain a prediction dataset corresponding to the monitored object in the image to be recognized; wherein, the prediction dataset includes predicted device information, predicted category information, predicted telemetry data, and predicted telecontrol data.

6. A storage medium, characterized in that, The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the substation monitoring system detection method according to any one of claims 1-4 above are implemented.

7. An electronic device, characterized in that, At least including a memory and a processor, a computer program is stored on the memory, and when the processor executes the computer program on the memory, the steps of the substation monitoring system detection method described in any one of the above claims 1-4 are implemented.

Images