On-line monitoring system and on-line monitoring method for pressing plate of transformer substation

Abstract

The invention discloses an on-line monitoring system and an on-line monitoring method for a pressing plate of a transformer substation, and belongs to the technical field of pressing plate monitoring, and the system comprises a pressing plate state monitoring unit which is used for collecting the state information of the pressing plate in a screen; the pressing plate state collection unit is used for receiving in-screen pressing plate state information; the management machine is used for obtaining in-screen pressing plate displacement identification information; and the master station is used for generating alarm information. According to the invention, the technical problems of mistaken switching, missing switching, large workload of manual checking of the state of the pressing plate and poor accuracy in traditional transformer substation pressing plate management are solved, and the technical effects of monitoring the state of the pressing plate in real time through intelligent monitoring and automatic alarm, reducing human errors and ensuring safe operation of a power system are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of pressure plate monitoring, and in particular to an online monitoring system and an online monitoring method for pressure plates in a transformer substation. Background Art

[0002] With the continuous development of the operation mode of the power system and the gradual expansion of the scale of the power grid, substations, as key nodes of the power system, undertake the task of power transmission and distribution. The protective pressure plate of the substation plays a vital role in the operation of power equipment and can ensure the correct operation of the relay protection device. However, the traditional substation pressure plate operation mainly relies on manual operation, lacks effective monitoring and management means, and is prone to operational errors or omissions, thereby affecting the normal realization of the relay protection function, and may even cause serious consequences such as large-scale power outages in the power grid. In the traditional power system, the pressure plate's operation and withdrawal process is entirely performed by the operation and inspection personnel according to the work procedures, but due to differences in personnel responsibility and operation attentiveness, the pressure plate's operation and withdrawal status is often unable to be effectively monitored and verified. Errors in the pressure plate's operation and withdrawal (such as missed operation and wrong operation) not only increase the complexity of the power system's operation and maintenance, but also directly affect the stability and safety of the power grid. This manual operation method has great hidden dangers, and due to problems such as long manual inspection cycles and heavy workload, its accuracy and efficiency are often not guaranteed. More importantly, the existing system lacks real-time monitoring and anti-error technical means, and cannot detect and correct these problems in a timely manner. Summary of the invention

[0003] This application provides an online monitoring system and method for substation pressure plates, aiming to solve the technical problems of mis-throwing and missed throwing, as well as the large workload and poor accuracy of manual verification of pressure plate status in traditional substation pressure plate management, so as to achieve the technical effect of real-time monitoring of pressure plate status through intelligent monitoring and automatic alarm, reducing human errors and ensuring the safe operation of the power system.

[0004] In view of the above problems, the present application provides an online monitoring system and an online monitoring method for a transformer substation pressure plate.

[0005] The first aspect disclosed in the present application provides an online monitoring system for a pressure plate in a substation, the system comprising: a pressure plate status monitoring unit, for collecting status information of the pressure plate in the panel; a pressure plate status collection unit, for receiving the status information of the pressure plate in the panel from the pressure plate status monitoring unit; a management machine, for receiving corresponding information from the pressure plate status collection unit, and performing a status evaluation on the status information of the pressure plate in the panel to obtain position displacement identification information of the pressure plate in the panel; a main station, for receiving the position displacement identification information of the pressure plate in the panel from the management machine, performing an abnormality analysis on the position displacement identification information of the pressure plate in the panel based on a circuit operation path, obtaining an abnormally displaced pressure plate, and generating an alarm information according to the abnormally displaced pressure plate.

[0006] Another aspect disclosed in the present application provides an online monitoring method for substation pressure plates, the method comprising: collecting status information of the pressure plate within the panel; receiving the status information of the pressure plate within the panel; performing status evaluation on the status information of the pressure plate within the panel to obtain position displacement identification information of the pressure plate within the panel; receiving the position displacement identification information of the pressure plate within the panel, performing abnormality analysis on the position displacement identification information of the pressure plate within the panel based on a circuit operation path, obtaining an abnormally displaced pressure plate, and generating alarm information based on the abnormally displaced pressure plate.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The pressure plate status monitoring unit is used to collect the pressure plate status information in the screen; the pressure plate status collection unit receives the pressure plate status information in the screen from the pressure plate status monitoring unit; the management machine receives the corresponding information from the pressure plate status collection unit, and performs status evaluation on the pressure plate status information in the screen to obtain the displacement identification information of the pressure plate in the screen; the main station receives the pressure plate displacement identification information in the screen from the management machine, and based on the circuit operation path, performs abnormal analysis on the pressure plate displacement identification information in the screen to obtain the abnormal displacement pressure plate, and generates alarm information according to the abnormal displacement pressure plate. The technical problems of mis-throwing and missing throwing in the traditional substation pressure plate management, as well as the large workload and poor accuracy of manual verification of the pressure plate status are solved, and the technical effect of real-time monitoring of the pressure plate status, reducing human errors and ensuring the safe operation of the power system through intelligent monitoring and automatic alarm is achieved. The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A structural schematic diagram of a substation pressure plate online monitoring system is provided for an embodiment of the present application.

[0010] Figure 2 A flow chart of an online monitoring method for a transformer substation pressure plate is provided for an embodiment of the present application.

[0011] Explanation of the accompanying drawings: pressure plate status monitoring unit 1, pressure plate status collection unit 2, management machine 3, main station 4. DETAILED DESCRIPTION

[0012] The present application solves the technical problems of mis-throwing and missed-throwing, as well as the large workload and poor accuracy of manual verification of pressure plate status in traditional substation pressure plate management by providing an online monitoring system and online monitoring method for substation pressure plates, thereby achieving the technical effect of real-time monitoring of pressure plate status through intelligent monitoring and automatic alarm, reducing human errors, and ensuring the safe operation of the power system.

[0013] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0014] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides an online monitoring system for a pressure plate in a substation, the system comprising:

[0015] The pressure plate status monitoring unit is used to collect the pressure plate status information inside the screen.

[0016] Specifically, the pressure plate status monitoring unit is a key component for performing online monitoring of the pressure plate in the substation. It is responsible for collecting the status information of the pressure plate in each panel cabinet in the substation in real time. The unit detects the switch status of the pressure plate (such as "on" or "off") through the sensor connected to the pressure plate (such as a photoelectric sensor or a magnetic sensor), and transmits the collected status data to the pressure plate status collection unit through the data bus for further processing and analysis. The above method can realize the accurate monitoring of the status of the substation pressure plate, greatly improve the automation of the pressure plate operation, and reduce the risk of human operation errors.

[0017] Further, the pressure plate status monitoring unit is deployed in the pressure plate screen cabinet, any one of the pressure plate status monitoring units corresponds to a pressure plate in a row of screens, any one of the pressure plate status monitoring units includes a photoelectric sensor, and the photoelectric sensor corresponds to the pressure plate in the screen one by one. The step of collecting the pressure plate status information in the screen includes:

[0018] Communicate with the photoelectric sensor and receive the photoelectric sensing signal; perform binary evaluation on the state of the pressure plate inside the screen according to the photoelectric sensing signal to obtain the state information of the pressure plate inside the screen, wherein any state of the pressure plate inside the screen in the state information is an input state or an exit state.

[0019] In a preferred embodiment, the pressure plate state monitoring unit is installed in the pressure plate panel cabinet of the substation, each pressure plate state monitoring unit corresponds to a row of pressure plates in the panel cabinet, and each monitoring unit includes a photoelectric sensor, which corresponds to the pressure plate in the panel one by one, and is used to collect the status information of the pressure plate in the panel in real time. The working principle of the pressure plate state monitoring unit is to use photoelectric sensing technology, without direct contact with the pressure plate in the panel, to accurately sense the movement changes of the pressure plate in the panel, and monitor the separation and closing state of the pressure plate in the panel in real time. Specifically, when monitoring the pressure plate in the panel, the pressure plate state monitoring unit will first establish a wireless communication connection with the photoelectric sensor, and the photoelectric sensor transmits and receives photoelectric sensing signals, and transmits the received photoelectric sensing signals to the pressure plate state monitoring unit through the established wireless communication. The pressure plate state monitoring unit detects whether the pressure plate is in the engaged state (i.e., the pressure plate is closed) or the withdrawn state (i.e., the pressure plate is open) through these photoelectric sensing signals, that is, the received photoelectric sensing signals are input into a predetermined evaluation model for signal analysis, the state of each pressure plate in the panel is judged, and it is concluded whether the pressure plate in the panel is in the engaged state or the withdrawn state. This method does not require physical contact and uses photoelectric signals to monitor the status of the pressure plate, making the monitoring process safer and more efficient, reducing the error rate of manual operation, and being able to collect accurate pressure plate status data in the first time, providing a reliable basis for subsequent monitoring, analysis and alarming.

[0020] Furthermore, the step of performing binary evaluation on the state of the pressure plate in the screen according to the photoelectric sensing signal and obtaining the state information of the pressure plate in the screen includes:

[0021] Obtain a state binary evaluation model; input the photoelectric sensing signal into the first state binary evaluation base model of the state binary evaluation model to obtain a first state binary result; until the photoelectric sensing signal is input into the Nth state binary evaluation base model of the state binary evaluation model to obtain an Nth state binary result, wherein N is an odd number; perform a majority full connection on the first state binary result and the Nth state binary result to obtain the state information of the pressure plate inside the screen.

[0022] In a feasible implementation, the system terminal acquires and activates a pre-built state binary evaluation model, which determines the actual state of the pressure plate in the screen by performing a binary evaluation (i.e., input or exit) on the state of the pressure plate in the screen. The base model of the evaluation model is trained by recording photoelectric sensing signals and identifying the state of the pressure plate in the screen, thereby providing a basis for subsequent state evaluation. In actual operation, the system terminal inputs the photoelectric sensing signal into the state binary evaluation model, and the first state binary evaluation base model of the state binary evaluation model determines the state of the pressure plate according to the input photoelectric sensing signal and generates a first state binary result. At the same time, the photoelectric sensing signal will be gradually evaluated by the Nth state binary evaluation base model of the state binary evaluation model, where N is an odd number. Each state binary evaluation base model performs signal analysis and state evaluation at different depths to obtain the corresponding Nth state binary result. Through multiple evaluations, the model can more accurately judge the state of the pressure plate in the screen; finally, the first state binary result and the Nth state binary result are fully connected by the majority to obtain the final state information of the pressure plate in the screen. The role of the majority full connection is to combine multiple evaluation results and select the result with the highest frequency as the final judgment result to improve the accuracy of the evaluation.

[0023] Furthermore, the steps of constructing the first state binary evaluation base model include:

[0024] Collect photoelectric sensing signal recording data and in-screen pressure plate status identification information, wherein the in-screen pressure plate status identification information is 1 or 0, 1 represents that the in-screen pressure plate status is in the engaged state, and 0 represents the exited state; use the in-screen pressure plate status identification information as supervision and the photoelectric sensing signal recording data as input to train the first state binary evaluation base model.

[0025] In a feasible implementation, in order to perform accurate binary status evaluation, the system terminal collects photoelectric sensing signal recording data and screen pressure plate status identification information at historical time. The photoelectric sensing signal recording data is extracted from the monitoring log of the pressure plate status monitoring unit. These signals contain the behavior information of the screen pressure plate at different time points, for example, whether the screen pressure plate is in a closed state (input) or an open state (exit). The changes in these signal data reflect the real-time status of the screen pressure plate action. The screen pressure plate status identification information is generated by manual detection or standardized procedures. The pressure plate status of each collection point is represented by 1 for the input state and 0 for the exit state. This identification data is used as the supervision data of the photoelectric sensing signal and is the subsequent The basis for model training; then, the photoelectric sensing signal recording data is used as input data, and the status identification information of the pressure plate in the screen is used as supervision data, and the first state binary evaluation base model is constructed in combination with the machine learning model. Taking the multi-layer perceptron (MLP) in the neural network as an example, the system terminal uses MLP to construct a pressure plate state binary evaluation model, including input layer, hidden layer, output layer, etc., and then initializes the number of neurons in the input layer to be the same as the dimension of the photoelectric sensing signal feature, and the output layer is set to 1 neuron, which is used to predict the state of the pressure plate in the screen (in or out); then, by randomly initializing the weights, a network structure with one or more hidden layers is constructed, and then the photoelectric sensing signal recording data and the status identification information of the pressure plate in the screen are used as the supervision data. The training set divided by information is input into the binary evaluation model of the pressure plate state for forward propagation. The data enters from the input layer, passes through the calculation and activation function (such as ReLU) of each layer, reaches the output layer, and calculates the predicted probability of whether the pressure plate in the screen is in the engaged state or the exited state. The prediction result is mapped to between 0 and 1 through the Sigmoid activation function, which is used to represent the binary classification result of the pressure plate state; then, the binary cross entropy loss function is used to calculate the loss value between the prediction result and the pressure plate state mark in the screen. The loss function measures the accuracy of the model prediction. The smaller the loss value, the more accurate the model. The back propagation algorithm is then used to calculate the gradient of the loss to the weight of each layer layer by layer. Based on these gradients, the Adam optimization is used. The optimizer adjusts the weight of the model, and the optimization goal is to minimize the value of the loss function. This process is repeated for multiple epochs until the maximum number of iterations is reached or the change in the loss function meets the stopping condition. During the training process, the hyperparameters of the model (such as learning rate, number of hidden layer neurons, training batches, etc.) can be adjusted through cross-validation and other methods to improve the accuracy of the model. After the training is completed, the performance of the model is evaluated using the divided test set to test the accuracy of the model in predicting the state of the pressure plate (entry or exit). If the accuracy meets the expected requirements, the current first-state binary evaluation base model is output as the final evaluation model. If the accuracy does not meet the requirements, the hyperparameters are adjusted according to the evaluation results, and retraining and optimization are performed.For the N-th state binary evaluation base model, it is constructed through other machine learning models, such as support vector machine (SVM), random forest, and gradient boosting tree. Through the above process, the system terminal can use the photoelectric sensing signal data to train a reliable evaluation model, so as to automatically and accurately evaluate the state of the pressure plate in the screen. The training of the model depends on a large amount of labeled data, so that the system terminal can adaptively identify the state of the pressure plate in actual operation. ;

[0026] The pressure plate status collection unit is used to receive the pressure plate status information within the screen from the pressure plate status monitoring unit.

[0027] Specifically, the pressure plate status collection unit is an important component in the online monitoring of pressure plates in substations. It is responsible for centrally receiving the pressure plate status information collected by each pressure plate status monitoring unit. Each pressure plate status monitoring unit is responsible for monitoring the status of the pressure plate in the panel cabinet and sending the collected data to the pressure plate status collection unit. Specifically, after the pressure plate status collection unit receives data from multiple pressure plate status monitoring units, it will summarize and integrate these data, and centrally manage the pressure plate status information transmitted from different monitoring units through bus communication. The pressure plate status collection unit is not only a receiver of information, it is also responsible for certain data caching work to ensure the accurate transmission of information, and transmit the summarized data to the management machine through bus communication or wireless WLAN to facilitate subsequent status analysis, abnormality detection and alarm processing.

[0028] The management machine is used to receive corresponding information from the pressure plate status collection unit, and perform status evaluation on the pressure plate status information within the screen to obtain the displacement identification information of the pressure plate within the screen.

[0029] Specifically, the management machine is the core control unit in the online monitoring of the pressure plate of the substation. It is responsible for receiving all the pressure plate status information from the pressure plate status collection unit, and centrally processing and evaluating it. Specifically, the management machine receives the pressure plate status data monitored in each panel cabinet from the pressure plate status collection unit. These data include the input or exit status of each pressure plate in the panel. After receiving this information, the management machine will conduct a comprehensive evaluation of the pressure plate status in the panel, analyze the current status of the pressure plates in different panels, and compare it with the stored pressure plate status in the panel to determine whether the pressure plate in the panel has changed (such as the status of a certain pressure plate has changed abnormally). Through this process, the management machine can generate the pressure plate displacement identification information in the panel, that is, mark which pressure plates have changed their status and identify the specific location of their displacement. This function is crucial for monitoring the normal operation of the pressure plate, especially in unmanned substations. The automatic evaluation of the management machine can timely detect abnormalities in the pressure plate operation, provide accurate displacement identification information, and provide data support for subsequent abnormal analysis and alarms.

[0030] Furthermore, the management machine is used to receive corresponding information from the pressure plate state collection unit, and to perform state evaluation on the pressure plate state information within the panel to obtain the displacement identification information of the pressure plate within the panel, and the execution steps include:

[0031] Obtain stored in-screen pressure plate status information, wherein the stored in-screen pressure plate status information is pre-configured in-screen pressure plate status information loaded from the master station; extract different in-screen pressure plate sets from the in-screen pressure plate status information and the stored in-screen pressure plate status information; and mark the in-screen pressure plate displacement identification information for the in-screen pressure plate set.

[0032] In a preferred embodiment, when performing status evaluation, the system terminal will obtain the stored status information of the pressure plate in the screen. The stored status information of the pressure plate in the screen refers to the status data of the pressure plate that has been stored by the preset configuration or historical data before the monitoring system is run. Usually, these data come from the pre-configuration file loaded by the main station or the standard status information saved when the system is initialized. When the monitoring system is started, the main station will load and provide a copy of the standard status information of the pressure plate in the screen. This information contains the initial or expected status of all pressure plates (for example, the pressure plate should be in the input state or the exit state), which is usually stored in the database or configuration file of the main station. The stored status information usually exists in the form of a data table or status log, and the content includes the number of the pressure plate in the screen, the current status, the historical change record, etc. Once the system terminal obtains the status information of the current pressure plate in the screen, it will compare the status information of the pressure plate in the screen with the pre-stored stored status information of the pressure plate in the screen to find inconsistencies. That is to say, the system terminal needs to check the actual status of each pressure plate in the screen with the pre-configured standard status information. Whether the quasi-state is consistent, through this comparison, the difference between the two can be extracted, and these difference parts are the in-screen pressure plates whose states have changed (such as the state of a certain in-screen pressure plate has changed from being put into use to being withdrawn), and the system terminal adds these changed pressure plates to the in-screen pressure plate set; based on the extracted in-screen pressure plate set, the system terminal will generate corresponding in-screen pressure plate displacement identification information, which not only indicates which in-screen pressure plates have undergone state changes (such as from being put into use to being withdrawn), but also indicates the specific location (in-screen pressure plate number), type (mis-put, missed put, etc.) and time (timestamp) of the change. Once the displacement identification information is generated, the system terminal will transmit the in-screen pressure plate displacement identification information to the main station for analysis and alarm, to help operation and maintenance personnel quickly locate problems, and promptly repair or adjust the pressure plate status.

[0033] The main station is used to receive the displacement identification information of the pressure plate in the screen from the management machine, perform abnormal analysis on the displacement identification information of the pressure plate in the screen based on the circuit operation path, obtain the abnormal displacement pressure plate, and generate alarm information according to the abnormal displacement pressure plate.

[0034] Specifically, the master station is an important component in the online monitoring of the pressure plate in the substation. It is mainly responsible for receiving the displacement identification information of the pressure plate in the panel from the management machine, and further analyzing and processing the information. The master station first receives the displacement identification information of the pressure plate in the panel from the management machine. These identification information indicate that the status of some pressure plates is inconsistent with the preset standard and may have changed. At this time, the master station will conduct further analysis based on the circuit operation path of the substation. The circuit operation path reflects the connection and function relationship between each pressure plate in the panel and other components in the power system. The master station calibrates the status of the pressure plate in the panel by understanding the layout of the circuit and passes it on. By comparing the calibration results with the displacement identification information of the pressure plate in the screen, an abnormal displacement pressure plate is analyzed to determine and mark it; when the master station finds an abnormal displacement pressure plate, the system terminal will generate an alarm message according to the preset standards and rules. The alarm message will include the number of the abnormal pressure plate, the type of change (such as mis-throwing, missed throwing), and important information such as the possible risks to the safe operation of the power grid. The generated alarm information will be transmitted to the operation and maintenance personnel in a timely manner so that measures can be taken quickly to repair or adjust it. This helps to avoid power system failures caused by pressure plate operation errors and ensure the safe and stable operation of substations and power grids.

[0035] Further, the master station is used to receive the displacement identification information of the pressure plate in the screen from the management machine, and based on the circuit operation path, perform abnormal analysis on the displacement identification information of the pressure plate in the screen to obtain the abnormal displacement pressure plate, and the execution steps include:

[0036] Communicate with the circuit operation control end to collect the circuit operation path; calibrate the state of the pressure plate inside the screen according to the circuit operation path to obtain the calibration result of the state of the pressure plate inside the screen; add the pressure plate inside the screen whose state calibration result of the pressure plate inside the screen is inconsistent with the displacement identification information of the pressure plate inside the screen into the abnormal displacement pressure plate.

[0037] In a preferred embodiment, the circuit operation control terminal is a module responsible for managing and monitoring the operation status of the substation circuit. It provides information such as the connection relationship, status and operation path of each circuit in the power system. The master station establishes communication with the circuit operation control terminal, exchanges information with the control terminal through protocols (such as IEC 61850, MODBUS, etc.), and obtains the real-time operation path and topology of the circuit. The circuit operation path refers to the connection relationship between various devices in the power system (such as pressure plates, circuit breakers, relay protection devices, etc.), including the physical connection of the circuit, the position of the pressure plate, the status of the circuit breaker, and the direction of power flow. The collected circuit operation path will provide a basis for the subsequent pressure plate state calibration; then, the system terminal inputs the circuit operation path into the pre-built in-screen pressure plate state calibration model to perform in-screen pressure plate state calibration, verify whether the actual state of each in-screen pressure plate meets the circuit operation requirements, and generate the state calibration result of each in-screen pressure plate, which will be marked The state that the pressure plate inside the screen should be in under the current environment; once the state calibration result of the pressure plate inside the screen is obtained, it will be compared with the position displacement identification information of the pressure plate inside the screen. If the calibration result is inconsistent with the position displacement identification information, it means that the state of the pressure plate has been abnormally displaced. For example, according to the circuit operation path analysis, it is found that a certain pressure plate inside the screen should be in the engaged state, but the position displacement identification information obtained through the pressure plate monitoring shows that the pressure plate is in the exit state, which constitutes a state inconsistency; when the calibration result does not match the position displacement identification information, the system terminal will identify these inconsistent pressure plates as abnormally displaced pressure plates, and these abnormally displaced pressure plates will be recorded and identified for subsequent processing and alarm use.

[0038] Furthermore, the state of the pressure plate in the panel is calibrated according to the circuit operation path to obtain the calibration result of the state of the pressure plate in the panel, including:

[0039] A neural network topology simulation is performed based on the circuit topology diagram to obtain a neural network topology structure, wherein the neural network topology structure is the same as the circuit topology diagram, the input data is the circuit connectivity state, and the output data is the state information of each pressure plate node; the circuit operation path recording data is configured; positive sample identification is performed on the circuit operation path recording data to obtain the target state identification data of the pressure plate inside the screen; the neural network topology structure is trained with the target state identification data of the pressure plate inside the screen as supervision and the circuit operation path recording data as input to obtain a calibration model of the pressure plate inside the screen; the circuit operation path is input into the calibration model of the pressure plate inside the screen, and the calibration result of the pressure plate inside the screen is output.

[0040] In a feasible implementation, the circuit topology diagram extracted from the circuit operation control terminal describes the connection relationship of various devices (such as pressure plates, circuit breakers, relay protection devices, etc.) in the power system. Each node in the topology diagram represents a device or state, and the edge represents the electrical connection or current flow path between the devices. By converting this circuit topology diagram into a neural network topology structure, the goal is to match the connection relationship of the circuit with the structure of the neural network. In this process, each circuit node will correspond to a neuron in the neural network, and the connection path in the circuit will correspond to the connection weight between the neurons. The input data of this neural network topology structure is the circuit connectivity state (i.e., the obtained circuit operation path), and the output data is the state information of each pressure plate node (i.e., the target state identification of the pressure plate in the panel); then, the system terminal extracts the circuit operation paths under multiple historical times from the circuit operation control terminal communication to configure the circuit operation path record data. The operation paths of these circuits refer to the actual flow paths of the current in the power system. Each circuit operation path contains the state information of the connected pressure plates, circuit breakers and other devices, and then the circuit operation path record data is positively identified. The positive sample identification process is to calibrate the target state of each pressure plate in the panel by analyzing the circuit operation path record data in combination with the circuit operation requirements. That is, determine the state that each in-screen pressure plate should be in under a specific circuit operating state. For example, when current needs to flow through a certain line, some in-screen pressure plates should be in the engaged state, and when the current is cut off, the in-screen pressure plates should be in the exit state. Through this positive sample identification, the target state identification data of each in-screen pressure plate is obtained, that is, the ideal state of each in-screen pressure plate under specific circuit operating conditions; then, the in-screen pressure plate target state identification data is used as a supervision signal, and the circuit operation path record data is used as input data, which are input into the neural network topology structure for training, and the cross entropy loss function is used to measure the gap between the prediction result of the neural network and the actual target state. , and then use the back propagation algorithm and optimizer (such as Adam optimizer) to adjust the weight of the neural network, minimize the loss function, and thus optimize the performance of the neural network. Through training, the neural network can automatically learn the relationship between the circuit operation path and the pressure plate state, and can predict the correct state of each pressure plate in the screen according to the operation of the circuit; the trained neural network will be used as the pressure plate state calibration model in the screen to apply to the actual pressure plate state calibration task. The system terminal will input the current circuit operation path into the pressure plate state calibration model in the screen. The model will output the calibration state of each pressure plate in the screen according to the operation state of the circuit, forming the pressure plate state calibration result in the screen. This method effectively combines the topological structure of the power system with the learning ability of the neural network, and realizes automatic and accurate pressure plate state calibration in the screen.

[0041] In summary, the substation pressure plate online monitoring system provided by the embodiment of the present application has the following technical effects:

[0042] The pressure plate status monitoring unit is used to collect the pressure plate status information in the panel; the pressure plate status collection unit is used to receive the pressure plate status information in the panel from the pressure plate status monitoring unit; the management machine is used to receive the corresponding information from the pressure plate status collection unit, and perform status evaluation on the pressure plate status information in the panel to obtain the displacement identification information of the pressure plate in the panel; the main station is used to receive the pressure plate displacement identification information in the panel from the management machine, perform abnormal analysis on the pressure plate displacement identification information in the panel based on the circuit operation path, obtain the abnormal displacement pressure plate, and generate alarm information according to the abnormal displacement pressure plate. Through the above steps, the technical problems of mis-throwing and missing throwing in the traditional substation pressure plate management, as well as the large workload and poor accuracy of manual verification of the pressure plate status are solved, and the technical effect of real-time monitoring of the pressure plate status, reducing human errors and ensuring the safe operation of the power system through intelligent monitoring and automatic alarm is achieved.

[0043] Embodiment 2, based on the same inventive concept as the substation pressure plate online monitoring system in the above embodiment, Figure 2 As shown, the embodiment of the present application provides a method for online monitoring of a pressure plate in a substation, the method comprising:

[0044] Collect status information of the pressure plate inside the screen; receive the status information of the pressure plate inside the screen; perform status evaluation on the status information of the pressure plate inside the screen to obtain displacement identification information of the pressure plate inside the screen; receive the displacement identification information of the pressure plate inside the screen, perform abnormal analysis on the displacement identification information of the pressure plate inside the screen based on the circuit operation path, obtain the abnormal displacement pressure plate, and generate alarm information according to the abnormal displacement pressure plate.

[0045] Furthermore, the step of collecting the status information of the pressure plate in the screen includes:

[0046] Communicate with the photoelectric sensor and receive the photoelectric sensing signal; perform binary evaluation on the state of the pressure plate inside the screen according to the photoelectric sensing signal to obtain the state information of the pressure plate inside the screen, wherein any state of the pressure plate inside the screen in the state information is an input state or an exit state.

[0047] Furthermore, the step of performing binary evaluation on the state of the pressure plate in the screen according to the photoelectric sensing signal and obtaining the state information of the pressure plate in the screen includes:

[0048] Obtain a state binary evaluation model; input the photoelectric sensing signal into the first state binary evaluation base model of the state binary evaluation model to obtain a first state binary result; until the photoelectric sensing signal is input into the Nth state binary evaluation base model of the state binary evaluation model to obtain an Nth state binary result, wherein N is an odd number; perform a majority full connection on the first state binary result and the Nth state binary result to obtain the state information of the pressure plate inside the screen.

[0049] Furthermore, the steps of constructing the first state binary evaluation base model include:

[0050] Collect photoelectric sensing signal recording data and in-screen pressure plate status identification information, wherein the in-screen pressure plate status identification information is 1 or 0, 1 represents that the in-screen pressure plate status is in the engaged state, and 0 represents the exited state; use the in-screen pressure plate status identification information as supervision and the photoelectric sensing signal recording data as input to train the first state binary evaluation base model.

[0051] Furthermore, obtaining the displacement identification information of the pressure plate in the screen includes:

[0052] Obtain stored in-screen pressure plate status information, wherein the stored in-screen pressure plate status information is pre-configured in-screen pressure plate status information loaded from the master station; extract different in-screen pressure plate sets from the in-screen pressure plate status information and the stored in-screen pressure plate status information; and mark the in-screen pressure plate displacement identification information for the in-screen pressure plate set.

[0053] Furthermore, the abnormal displacement pressure plate is obtained, and the execution steps include:

[0054] Communicate with the circuit operation control end to collect the circuit operation path; calibrate the state of the pressure plate inside the screen according to the circuit operation path to obtain the calibration result of the state of the pressure plate inside the screen; add the pressure plate inside the screen whose state calibration result of the pressure plate inside the screen is inconsistent with the displacement identification information of the pressure plate inside the screen into the abnormal displacement pressure plate.

[0055] Furthermore, the state of the pressure plate in the panel is calibrated according to the circuit operation path to obtain the calibration result of the state of the pressure plate in the panel, including:

[0056] A neural network topology simulation is performed based on the circuit topology diagram to obtain a neural network topology structure, wherein the neural network topology structure is the same as the circuit topology diagram, the input data is the circuit connectivity state, and the output data is the state information of each pressure plate node; the circuit operation path recording data is configured; positive sample identification is performed on the circuit operation path recording data to obtain the target state identification data of the pressure plate inside the screen; the neural network topology structure is trained with the target state identification data of the pressure plate inside the screen as supervision and the circuit operation path recording data as input to obtain a calibration model of the pressure plate inside the screen; the circuit operation path is input into the calibration model of the pressure plate inside the screen, and the calibration result of the pressure plate inside the screen is output.

[0057] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0058] Furthermore, the first or second mentioned above may not only represent an order relationship, but may also represent a specific concept, and / or refer to the selection of multiple elements individually or in whole. Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application intends to include these modifications and variations.

Claims

1. Substation pressure plate online monitoring system, characterized by: include: The pressure plate status monitoring unit is used to collect the pressure plate status information in the screen; A pressure plate state collection unit, used for receiving the pressure plate state information in the panel from the pressure plate state monitoring unit; A management machine, used for receiving corresponding information from the pressure plate state collection unit, and performing state evaluation on the pressure plate state information within the panel to obtain displacement identification information of the pressure plate within the panel; The main station is used to receive the displacement identification information of the pressure plate in the screen from the management machine, perform abnormal analysis on the displacement identification information of the pressure plate in the screen based on the circuit operation path, obtain the abnormal displacement pressure plate, and generate alarm information according to the abnormal displacement pressure plate.

2. The substation pressure plate online monitoring system according to claim 1, characterized in that: The pressure plate status monitoring unit is deployed in the pressure plate screen cabinet, any one of the pressure plate status monitoring units corresponds to a pressure plate in a row of screens, any one of the pressure plate status monitoring units includes a photoelectric sensor, and the photoelectric sensor corresponds to the pressure plate in the screen one by one. The step of collecting the pressure plate status information in the screen includes: Communicate with the photoelectric sensor and receive a photoelectric sensing signal; The state of the inner-screen pressure plate is binary evaluated according to the photoelectric sensing signal to obtain the inner-screen pressure plate state information, wherein any one of the inner-screen pressure plate states in the inner-screen pressure plate state information is an engaged state or an exited state.

3. The substation pressure plate online monitoring system according to claim 2, characterized in that: The step of performing binary evaluation on the state of the inner-screen pressure plate according to the photoelectric sensing signal and obtaining the state information of the inner-screen pressure plate comprises: Obtain a state dichotomous assessment model; Inputting the photoelectric sensing signal into a first state binary evaluation base model of the state binary evaluation model to obtain a first state binary result; Until the photoelectric sensing signal is input into the Nth state binary evaluation base model of the state binary evaluation model to obtain the Nth state binary result, wherein N is an odd number; Perform majority full connection on the first state binary result and the Nth state binary result to obtain the in-screen pressure plate state information.

4. The substation pressure plate online monitoring system according to claim 3, characterized in that: The steps of constructing the first state binary evaluation base model include: Collecting photoelectric sensing signal recording data and screen pressure plate status identification information, wherein the screen pressure plate status identification information is 1 or 0, 1 indicates that the screen pressure plate status is in the engaged state, and 0 indicates that the screen pressure plate status is in the exit state; The first state binary evaluation base model is trained by taking the identification information of the pressure plate state in the screen as supervision and the photoelectric sensing signal recording data as input.

5. The substation pressure plate online monitoring system according to claim 1, characterized in that: The management machine is used to receive corresponding information from the pressure plate state collection unit, and to perform state evaluation on the pressure plate state information within the panel to obtain the displacement identification information of the pressure plate within the panel. The execution steps include: Obtaining stored in-screen pressure plate state information, wherein the stored in-screen pressure plate state information is pre-configured in-screen pressure plate state information loaded from the master station; Extracting different sets of in-screen pressure plates from the in-screen pressure plate state information and the stored in-screen pressure plate state information; The displacement identification information of the intra-panel pressure plate is identified for the intra-panel pressure plate set.

6. The substation pressure plate online monitoring system according to claim 1, characterized in that: The master station is used to receive the displacement identification information of the pressure plate in the panel from the management machine, and based on the circuit operation path, perform abnormal analysis on the displacement identification information of the pressure plate in the panel to obtain the abnormal displacement pressure plate. The execution steps include: Communicate with the circuit operation control terminal to collect the circuit operation path; Calibrate the state of the pressure plate in the screen according to the circuit operation path to obtain the calibration result of the state of the pressure plate in the screen; The intra-screen pressure plates whose status calibration results are inconsistent with the intra-screen pressure plate displacement identification information are added into the abnormal displacement pressure plates.

7. The substation pressure plate online monitoring system according to claim 6, characterized in that: The state of the pressure plate in the screen is calibrated according to the circuit operation path to obtain the calibration result of the state of the pressure plate in the screen, including: Performing neural network topology simulation based on the circuit topology diagram to obtain a neural network topology structure, wherein the neural network topology structure is the same as the circuit topology diagram, the input data is the circuit connectivity state, and the output data is the state information of each pressure plate node; Configure circuit operation path recording data; Performing positive sample identification on the circuit operation path record data to obtain target state identification data of the pressure plate in the panel; Using the target state identification data of the pressure plate in the panel as supervision and the circuit operation path record data as input, the neural network topology structure is trained to obtain a calibration model of the pressure plate state in the panel; The circuit operation path is input into the in-panel pressure plate state calibration model, and the in-panel pressure plate state calibration result is output.

8. A method for online monitoring of a pressure plate in a substation, characterized in that: The method is performed by the substation pressure plate online monitoring system according to any one of claims 1 to 7, comprising: Collect the status information of the pressure plate inside the screen; Receiving the status information of the pressure plate in the screen; Performing status evaluation on the status information of the inner-panel pressure plate to obtain displacement identification information of the inner-panel pressure plate; Receive the displacement identification information of the pressure plate in the screen, perform abnormal analysis on the displacement identification information of the pressure plate in the screen based on the circuit operation path, obtain the abnormal displacement pressure plate, and generate alarm information according to the abnormal displacement pressure plate.

Images