Explosion-proof power distribution cabinet control method and system based on situation awareness

Abstract

The invention provides an explosion-proof power distribution cabinet control method and system based on situation awareness, and relates to the technical field of power distribution cabinets, and the method comprises the steps: obtaining the associated power equipment information of a target power distribution cabinet; analyzing the connection relation of the same-level equipment to generate an equipment network topology structure; acquiring use scene information, and generating an operation configuration parameter set; acquiring an operation condition data set; judging whether a running configuration parameter set is met or not; if yes, performing real-time state monitoring to obtain state monitoring information of the target power distribution cabinet; inputting a situation awareness prediction model to carry out abnormal state prediction to obtain an abnormal state prediction coefficient; and judging whether an abnormal state prediction coefficient threshold value is met or not, and if yes, generating a first emergency processing instruction to perform emergency processing. According to the method, the problems of low data acquisition and processing efficiency and poor timeliness and safety of power distribution cabinet control due to lack of accurate prediction of abnormal states in a traditional method are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution cabinets, and in particular to a situation awareness-based explosion-proof power distribution cabinet control method and system. Background Art

[0002] The power system is one of the important infrastructures of modern society. As an important part of the power system, the distribution cabinet is responsible for the distribution and control of electric energy. Its safe and stable operation is crucial to the normal and safe operation of the power grid. In the traditional distribution cabinet monitoring system, there are still some technical problems. On the one hand, the traditional monitoring system usually uses discrete data acquisition equipment, which leads to low efficiency of data acquisition and processing, and cannot monitor the operating status of power equipment in a timely and accurate manner; on the other hand, the traditional distribution cabinet monitoring system usually relies on rules or simple statistical methods to predict abnormal conditions. This method often cannot accurately predict complex abnormal conditions, resulting in untimely processing or misjudgment. Summary of the invention

[0003] This application provides an explosion-proof distribution cabinet control method based on situational awareness, aiming to solve the problem of low data collection and processing efficiency in traditional methods, which leads to the inability to detect abnormal situations in a timely and accurate manner, and the lack of accurate prediction of abnormal conditions, and the inability to take timely countermeasures, resulting in technical problems such as poor timeliness and safety of distribution cabinet control.

[0004] In view of the above problems, the present application provides an explosion-proof distribution cabinet control method and system based on situation awareness.

[0005] The first aspect disclosed in the present application provides an explosion-proof distribution cabinet control method based on situational awareness, the method is applied to an explosion-proof distribution cabinet control system, the system is communicatively connected with an electric power equipment management system and a data monitoring system, the method comprises: obtaining associated electric power equipment information of a target distribution cabinet through the electric power equipment management system, wherein the target distribution cabinet is connected with a plurality of associated electric power equipment; classifying the plurality of associated electric power equipment based on the associated electric power equipment information, analyzing the connection relationship of the same-level equipment according to the class classification result, and generating a device network topology structure; obtaining usage scenario information of the plurality of associated electric power equipment, and configuring the operation parameters of the device network topology structure based on the usage scenario information , generate an operation configuration parameter set; through the data monitoring system, collect the operation condition data of the multiple related power equipment to obtain the operation condition data set; determine whether the operation condition data set satisfies the operation configuration parameter set; when satisfied, perform real-time status monitoring of the target distribution cabinet to obtain the target distribution cabinet status monitoring information; input the target distribution cabinet status monitoring information and the operation condition data set into the situation awareness prediction model to predict the abnormal state and obtain the abnormal state prediction coefficient; determine whether the abnormal state prediction coefficient satisfies the abnormal state prediction coefficient threshold, and when satisfied, generate a first emergency processing instruction, and perform emergency processing of the target distribution cabinet based on the first emergency processing instruction.

[0006] The second aspect disclosed in the present application provides an explosion-proof distribution cabinet control system based on situational awareness, the system is used for the above-mentioned explosion-proof distribution cabinet control method based on situational awareness, the system is communicatively connected with the power equipment management system and the data monitoring system, and the system includes: an associated power equipment information acquisition module, the associated power equipment information acquisition module is used to obtain the associated power equipment information of the target distribution cabinet through the power equipment management system, wherein the target distribution cabinet is connected to a plurality of associated power equipment; a network topology structure generation module, the network topology structure generation module is used to classify the plurality of associated power equipment based on the associated power equipment information, analyze the connection relationship of the same-level equipment according to the classification result, and generate a device network topology structure; an operation configuration parameter acquisition module, the operation configuration parameter acquisition module is used to obtain the usage scenario information of the plurality of associated power equipment, configure the operation parameters of the device network topology structure based on the usage scenario information, and generate an operation A configuration parameter set; an operating condition data acquisition module, the operating condition data acquisition module is used to collect the operating condition data of the multiple related power equipment through the data monitoring system, and obtain an operating condition data set; a judgment module, the judgment module is used to judge whether the operating condition data set satisfies the operating configuration parameter set; a real-time status monitoring module, the real-time status monitoring module is used to perform real-time status monitoring of the target distribution cabinet when the status is satisfied, and obtain the status monitoring information of the target distribution cabinet; an abnormal state prediction module, the abnormal state prediction module is used to input the status monitoring information of the target distribution cabinet and the operating condition data set into the situation awareness prediction model to predict the abnormal state, and obtain the abnormal state prediction coefficient; an emergency processing module, the emergency processing module is used to judge whether the abnormal state prediction coefficient satisfies the abnormal state prediction coefficient threshold, and when it is satisfied, generate a first emergency processing instruction, and perform emergency processing of the target distribution cabinet based on the first emergency processing instruction.

[0007] According to a third aspect disclosed in the present application, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, any step of the first aspect disclosed in the present application is implemented.

[0008] The fourth aspect disclosed in the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any step of the first aspect disclosed in the present application.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] By communicating with the power equipment management system and the data monitoring system, the timely collection and interaction of related power equipment information, operating condition data and status monitoring information are realized, and the efficiency of data collection and processing is improved; the situation awareness prediction model is used to analyze the status monitoring information and operating condition data of the target distribution cabinet, and the accurate prediction of abnormal state is realized, and the corresponding emergency processing instructions are generated, which improves the system's ability to respond to abnormal situations; according to whether the abnormal state prediction coefficient meets the threshold, the first emergency processing instruction is automatically generated, thereby realizing timely emergency processing of the target distribution cabinet and improving the efficiency and accuracy of emergency processing. In summary, the situation awareness-based explosion-proof distribution cabinet control method can monitor and manage more effectively, improve the safety, stability and reliability of the system, and ensure the normal operation of the power system and the safety of equipment.

[0011] 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

[0012] Figure 1 A flow chart of a method for controlling an explosion-proof power distribution cabinet based on situation awareness provided in an embodiment of the present application;

[0013] Figure 2 A schematic diagram of the structure of an explosion-proof power distribution cabinet control system based on situational awareness provided in an embodiment of the present application;

[0014] Figure 3 This is a diagram of the internal structure of a computer device provided in an embodiment of the present application.

[0015] Explanation of the reference numerals: associated power equipment information acquisition module 10, network topology structure generation module 20, operation configuration parameter acquisition module 30, operation condition data acquisition module 40, judgment module 50, real-time status monitoring module 60, abnormal status prediction module 70, emergency processing module 80. DETAILED DESCRIPTION

[0016] The embodiment of the present application solves the problem of low data collection and processing efficiency in traditional methods by providing an explosion-proof distribution cabinet control method based on situation awareness, which results in the inability to detect abnormal situations in a timely and accurate manner, and the lack of accurate prediction of abnormal conditions, and the inability to take timely countermeasures, resulting in technical problems such as poor timeliness and safety of distribution cabinet control.

[0017] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically introduced below in conjunction with the accompanying drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0018] like Figure 1 As shown, an embodiment of the present application provides an explosion-proof distribution cabinet control method based on situational awareness, the method is applied to an explosion-proof distribution cabinet control system, the system is communicatively connected with an electric power equipment management system and a data monitoring system, and the method includes:

[0019] Acquiring associated power equipment information of a target power distribution cabinet through the power equipment management system, wherein the target power distribution cabinet is connected to a plurality of associated power equipment;

[0020] The situational awareness-based explosion-proof distribution cabinet control method provided in the embodiment of the present application is applied to an explosion-proof distribution cabinet control system, and the system is communicatively connected with an electric power equipment management system and a data monitoring system, wherein the electric power equipment management system is a system for monitoring, managing and optimizing various electric power equipment in an electric power system, and is responsible for obtaining the associated electric power equipment information of a target distribution cabinet, and communicating with other systems to realize intelligent control of the overall distribution system; the data monitoring system is a system for collecting and monitoring the operating condition data of various equipment in an electric power system, and can obtain information such as the operating status, parameters and working conditions of electric power equipment in real time through sensors and other equipment.

[0021] First, the power equipment management system establishes a communication connection with the target distribution cabinet, and then sends a query instruction to the target distribution cabinet to obtain the power equipment information of its associated power equipment, which includes the name, model, location, rated parameters, etc. of the equipment, so as to realize the effective management and monitoring of the equipment information in the power system.

[0022] Classify the plurality of associated power devices based on the associated power device information, analyze the connection relationship of devices of the same level according to the classification result, and generate a device network topology structure;

[0023] According to the information of related power equipment, multiple related power equipment are classified into grades. The grade classification can be carried out according to factors such as the importance, function, and load carrying capacity of the equipment. For example, high-voltage switchgear and transformers can be classified as high-level equipment, while general distribution cabinets or distribution equipment can be classified as low-level equipment. After the equipment grade classification is completed, the connection relationship of the same-level equipment is analyzed according to the grade classification results, including the physical connection, electrical connection, and functional association between the equipment. For example, a high-level switchgear is directly connected to a high-level transformer, while a low-level distribution cabinet is connected to multiple low-level terminal devices.

[0024] Based on the results of the connection relationship analysis, the topology of the device network is generated. The topology describes the connection mode and relationship between devices, usually in the form of a graph. The topology can be a tree structure, a mesh structure, etc. The specific form depends on the actual device connection situation. In this way, the connection relationship between related power devices can be established and represented as a clear device network topology, which provides a basis for subsequent operation parameter configuration and status monitoring.

[0025] Acquire usage scenario information of the plurality of associated power devices, configure operation parameters of the device network topology structure based on the usage scenario information, and generate an operation configuration parameter set;

[0026] Obtain usage scenario information of multiple related power equipment, including equipment working characteristics, workload, operation mode, powered equipment, etc. This information can be obtained through on-site surveys, equipment manuals, historical data analysis, etc. Configure the operating parameters based on the acquired usage scenario information, including the equipment's operation mode, connection status, parameter settings, etc. For example, according to the workload and operation mode, the load distribution and operation status of the equipment can be adjusted; according to the situation of the powered equipment, the connection method and parameter settings of the equipment can be adjusted.

[0027] In the process of configuring parameters, the device network topology is adjusted and configured according to the usage scenario information, and a set of operation configuration parameter sets is generated. These parameter sets include configuration information on the operation mode, connection status, parameter settings, etc. of each power device. In this way, the operation parameters of the device network topology can be configured according to the actual usage scenario information, thereby realizing intelligent management of power equipment, thereby improving the operation efficiency and safety of the system and meeting the power needs in different scenarios.

[0028] Through the data monitoring system, the operating condition data of the plurality of related power devices are collected to obtain an operating condition data set;

[0029] Establish a communication connection between the data monitoring system and multiple related power equipment. The data monitoring system collects operating condition data from multiple related power equipment regularly or in real time through various sensors. These data include various parameters such as current, voltage, temperature, humidity, power factor, etc. The collected data are transmitted to the data monitoring system through the communication channel, providing basic data support for the intelligent monitoring and control of the system.

[0030] Determining whether the operating condition data set satisfies the operating configuration parameter set;

[0031] When the conditions are met, real-time status monitoring is performed on the target power distribution cabinet to obtain status monitoring information of the target power distribution cabinet;

[0032] The collected operating condition data set is compared with the previously configured operating parameter set, including comparing the actual operating status, parameter values, etc. of each associated power equipment with the preset operating configuration parameters.

[0033] According to the comparison results, conditional judgment is performed to determine whether the preset operation configuration parameter set is met. If the actual operation status and parameter values ​​of all devices are within the preset range and meet the preset conditions, it is judged to be satisfied. When satisfied, the target distribution cabinet is monitored in real time through the established monitoring channel, and the status information of the target distribution cabinet is collected in real time, including current, voltage, temperature, humidity, switch status and other parameters. The collected distribution cabinet status information is integrated to generate the target distribution cabinet status monitoring information, which includes the real-time operation status of the distribution cabinet, the working conditions of each component, etc.

[0034] Inputting the target distribution cabinet state monitoring information and the operating condition data set into a situation awareness prediction model to perform abnormal state prediction and obtain an abnormal state prediction coefficient;

[0035] The acquired target distribution cabinet status monitoring information and operating condition data are combined as input and passed to the situation awareness prediction model. The situation awareness prediction model is a trained machine learning model that can analyze the current status of the distribution cabinet based on the input data and predict whether there is a possibility of abnormal status. The model can be built based on deep learning and other methods. After model analysis, the abnormal status prediction coefficient is obtained. This coefficient reflects the possibility of abnormal status in the current distribution cabinet. A higher coefficient indicates a greater possibility of abnormality, while a lower coefficient indicates a smaller possibility of abnormality.

[0036] Determine whether the abnormal state prediction coefficient meets the abnormal state prediction coefficient threshold, and if so, generate a first emergency processing instruction, and perform emergency processing on the target distribution cabinet based on the first emergency processing instruction.

[0037] According to the actual situation and needs, set the abnormal state prediction coefficient threshold. This threshold can be set according to historical data, system performance requirements, safety standards and other factors. A higher threshold means that the system judges the abnormality more strictly, while a lower threshold may lead to more frequent false alarms. The predicted abnormal state prediction coefficient is judged. If the abnormal state prediction coefficient exceeds the threshold, it is judged that there is a serious abnormality. In this case, the first emergency processing instruction is generated. This instruction includes emergency processing measures such as shutting down the distribution cabinet, switching to backup equipment, and notifying maintenance personnel. These measures are aimed at responding to potential abnormalities as soon as possible to ensure the safe and stable operation of the power system.

[0038] Furthermore, it also includes:

[0039] When the operating condition data set does not satisfy the operating configuration parameter set, generating a second emergency processing instruction;

[0040] The abnormal state emergency plan of the target power distribution cabinet is read, and based on the abnormal state emergency plan and the second emergency processing instruction, emergency processing of the target power distribution cabinet is performed.

[0041] When it is detected that the operating condition data set does not meet the preset operating configuration parameter set, that is, it is found that the actual operating status of the equipment does not match the expected configuration, a second emergency processing instruction is generated. The second emergency processing instruction is a specific response measure for specific abnormal situations, such as equipment shutdown, switching to backup equipment, adjusting operating parameters, etc. These measures are aimed at restoring the normal operating status of the equipment as soon as possible to prevent possible faults from expanding.

[0042] According to the second emergency processing instruction, the abnormal state emergency plan of the target distribution cabinet is read. The abnormal state emergency plan is a detailed processing plan for various abnormal situations formulated in advance. Based on the abnormal state emergency plan and combined with the second emergency processing instruction, emergency processing of the target distribution cabinet is carried out, including notifying relevant personnel, taking emergency measures, dispatching maintenance personnel and other operations, so as to restore the normal operating state of the power system as soon as possible and ensure the safe and reliable operation of the power system.

[0043] Furthermore, obtaining usage scenario information of the plurality of associated power devices, configuring the operation parameters of the device network topology structure based on the usage scenario information, and generating an operation configuration parameter set include:

[0044] According to the usage scenario information, obtain working characteristics, workload, operation mode, and powered equipment;

[0045] generating a first configuration constraint according to the working characteristic, the workload, the operating mode, and the powered device;

[0046] generating a second configuration constraint according to a connection relationship between devices of the same level in the device network topology structure;

[0047] generating a third configuration constraint based on the rated parameters of the plurality of associated electrical devices;

[0048] The operation configuration parameter set is generated based on the first configuration constraint, the second configuration constraint, and the third configuration constraint, wherein the operation configuration parameter set includes power equipment operation mode configuration, equipment connection status configuration, and power equipment parameter configuration.

[0049] The following information is obtained from the usage scenarios, including working characteristics, which refer to the environmental characteristics and power load types of the distribution cabinet; workload, which refers to the size and changes of the power load borne by the distribution cabinet; operation mode, which refers to the operation mode of the distribution cabinet, such as normal operation, standby operation, maintenance status, etc.; powered equipment, which refers to the electrical equipment connected to the distribution cabinet, including load equipment, power equipment, etc.

[0050] Based on the acquired working characteristics, workload, operation mode and powered equipment information, the first configuration constraint is generated. The first configuration constraint includes the following: restrictions on equipment operating characteristics, that is, according to the working characteristics and operation mode, the working characteristics of each device in the distribution cabinet are determined, such as rated current, rated voltage, temperature range, etc.; load distribution and balance requirements, that is, according to the workload information, the load distribution ratio between each powered equipment is determined to ensure the load balance of the power system; operating mode switching conditions, that is, according to the operating mode information, the conditions and restrictions for switching the operating mode of the distribution cabinet are determined, such as under what circumstances to switch to the standby mode; connection requirements for powered equipment, that is, according to the powered equipment information, the connection relationship and parameter configuration requirements between the distribution cabinet and each powered equipment are determined to ensure normal power supply and safe operation. By generating the first configuration constraint, it can be ensured that the configuration of the distribution cabinet meets the actual usage scenario requirements to ensure the normal operation and safety of the power system.

[0051] The second configuration constraint is determined based on the connection relationship between devices of the same level in the device network topology. Specifically, the connection relationship between devices of the same level describes the connection mode and topology between each power device in the distribution cabinet. Based on these connection relationships, the mutual influence and constraint conditions between devices can be determined. The generated second configuration constraint includes the order and mode of device connection, that is, determining the connection mode between each power device, including series connection, parallel connection, star connection, etc.; data exchange and communication requirements between devices, that is, determining the data exchange and communication mode between each device based on the connection relationship to ensure the reliability and efficiency of information transmission.

[0052] A third configuration constraint is generated based on the rated parameters of multiple associated power devices. Specifically, the rated parameters of the associated power devices describe the rated power, voltage, current, frequency and other parameters of each power device. Based on these parameters, the configuration restrictions and operating conditions of the distribution cabinet are determined. The generated third configuration constraint includes: the rated power and capacity of the power equipment, that is, the power capacity limit of the equipment is determined based on the rated parameters of the equipment to ensure that the equipment is not overloaded under normal operation; the rated voltage and current of the power equipment, that is, the operating voltage and current range of the equipment is determined based on the rated parameters of the equipment to ensure that the equipment operates within a safe voltage and current range.

[0053] By generating the second and third configuration constraints, the connection relationship and parameter restrictions between devices can be better displayed, so that the distribution cabinet can be configured more accurately and the stability and safety of the power system can be improved.

[0054] The operating mode of the power equipment is configured according to the working characteristics, workload and operating mode determined by the first configuration constraint, and the equipment connection relationship determined by the second configuration constraint. The operating mode configuration includes switching the distribution cabinet to normal operating mode, standby operating mode, maintenance mode, etc. Determine the operating mode that best suits the current situation based on actual conditions and needs.

[0055] According to the device connection relationship determined by the second configuration constraint, the connection status of the power equipment is configured. The device connection status configuration includes determining the connection mode, connection sequence and connection parameters between each power equipment. These configurations ensure normal communication and data exchange between the power equipment.

[0056] According to the rated parameters of the power equipment determined by the third configuration constraint, the specific parameters of the power equipment are configured. The power equipment parameter configuration includes setting the rated power, rated voltage, rated current, frequency and other parameters of the power equipment. These parameter settings are based on the technical specifications and performance requirements of the equipment to ensure that the equipment operates within a safe and stable working range.

[0057] By generating a set of operating configuration parameters, the operating mode of the distribution cabinet, equipment connection status and power equipment parameters can be reasonably configured according to the actual situation and equipment requirements to ensure the normal operation and safety of the power system.

[0058] Furthermore, the target distribution cabinet state monitoring information and the operating condition data set are input into the situation awareness prediction model to perform abnormal state prediction to obtain an abnormal state prediction coefficient, including:

[0059] Inputting the target distribution cabinet state monitoring information into the distribution cabinet explosion-proof performance evaluation channel of the situation awareness prediction model to obtain the distribution cabinet explosion-proof grade;

[0060] The explosion-proof grade of the power distribution cabinet and the operating condition data set are input into the abnormal state prediction channel of the situation awareness prediction model to obtain the abnormal state prediction coefficient.

[0061] The situational awareness prediction model includes a distribution cabinet explosion-proof performance evaluation channel and an abnormal state prediction channel. The target distribution cabinet state monitoring information is input into the distribution cabinet explosion-proof performance evaluation channel of the situational awareness prediction model. In this channel, the model evaluates the explosion-proof performance of the distribution cabinet, including analyzing the structure, material, sealing and other factors of the distribution cabinet, and obtains the explosion-proof grade of the distribution cabinet according to the evaluation results. The grade reflects the ability of the distribution cabinet to resist explosion; the explosion-proof grade and operating condition data set of the distribution cabinet are input into the abnormal state prediction channel of the situational awareness prediction model. In this channel, the explosion-proof grade and operating condition data of the distribution cabinet are used to predict possible abnormal states, and an abnormal state prediction coefficient is generated to reflect the possibility of abnormality in the distribution cabinet.

[0062] Furthermore, the explosion-proof grade of the power distribution cabinet and the operating condition data set are input into the abnormal state prediction channel of the situation awareness prediction model to obtain the abnormal state prediction coefficient, including:

[0063] The abnormal state prediction channel includes an initial digital twin model of the distribution cabinet, and the explosion-proof grade of the distribution cabinet is rendered to the initial digital twin model of the distribution cabinet to obtain the digital twin model of the distribution cabinet;

[0064] Based on the digital twin model of the power distribution cabinet, simulate the operation of the operating condition data set to obtain a number of simulated operation abnormality data of a number of abnormality-related power equipment that have abnormalities within a preset time zone, wherein the simulated operation abnormality data includes the time node and degree of abnormality when the abnormality occurs;

[0065] Anomaly assessment is performed based on the plurality of simulated operation abnormal data to obtain a plurality of abnormality assessment coefficients, and a maximum value among the plurality of abnormality assessment coefficients is extracted as the abnormal state prediction coefficient.

[0066] Establish an initial digital twin model of the distribution cabinet. The digital twin model is a virtual digital simulation model corresponding to the actual distribution cabinet. This model uses information such as the structure, components, and working principles of the distribution cabinet, and is calibrated with actual operating data to reflect the operating characteristics of the distribution cabinet as realistically as possible. The initial digital twin model can simulate the operating status of the distribution cabinet under different working conditions, including normal operation, load fluctuations, abnormal conditions, etc.

[0067] The explosion-proof grade information of the distribution cabinet is rendered into the initial digital twin model of the distribution cabinet. This rendering process is to associate the explosion-proof grade information of the distribution cabinet with the digital twin model, so that the digital twin model can consider the explosion-proof performance of the distribution cabinet. By integrating the explosion-proof grade information into the digital twin model, the safety of the distribution cabinet can be more accurately evaluated and this factor can be taken into account when predicting abnormal conditions. Combined with the rendering of the explosion-proof grade information, a complete digital twin model of the distribution cabinet is obtained, which can more accurately simulate the operation of the distribution cabinet.

[0068] The established digital twin model of the power distribution cabinet is used to simulate the operation of the power distribution cabinet in the preset time zone. During the simulation operation, load changes, environmental conditions, equipment status, etc. are simulated to simulate the actual operation of the power distribution cabinet as realistically as possible. During the simulation operation, the operating status of each power device associated with the power distribution cabinet is monitored. When abnormalities are detected in some power devices, the relevant information of these abnormalities is recorded. Specifically, for each abnormal associated power device, the time node of the abnormality is recorded, that is, the specific time when the abnormality occurs; the degree of the abnormality is also recorded to describe the severity or impact of the abnormality.

[0069] Evaluate several abnormal data recorded during the simulation process. The evaluation includes analyzing the time when the abnormality occurs, the duration of the abnormality, the degree of the abnormality, and other factors. Generate an abnormality evaluation coefficient based on the analysis results. This coefficient is used to indicate the severity of the abnormality. By evaluating several abnormal data, several corresponding abnormality evaluation coefficients are obtained. After obtaining several abnormality evaluation coefficients, extract the maximum value from them as the abnormal state prediction coefficient.

[0070] Furthermore, the data monitoring system further includes a mobile image acquisition device, and the method includes:

[0071] By using the mobile image acquisition device, the gas transportation pipeline within the preset range of the target power distribution cabinet is inspected to obtain an inspection pipeline image set;

[0072] Based on the inspection pipeline image set, identify gas leakage hazards and obtain multiple hazard points, wherein the multiple hazard points correspond to multiple hazard coefficients;

[0073] Acquire multiple distance information between the multiple potential danger points and the target power distribution cabinet;

[0074] Comprehensively calculating the multiple hidden danger coefficients based on the multiple distance information to obtain a comprehensive hidden danger coefficient;

[0075] The abnormal state prediction coefficient threshold is corrected based on the comprehensive hidden danger coefficient.

[0076] First, determine the preset range of the target distribution cabinet, that is, the area that needs to be inspected, including the gas transportation pipeline within a certain range around the distribution cabinet. Prepare a mobile image acquisition device, which is a mobile device equipped with a camera, such as a drone or inspection robot.

[0077] Deploy the mobile image acquisition device within the preset range and start inspecting the gas transportation pipeline. The device can move along the pipeline path to capture images around the pipeline, or use an aircraft to take aerial photos of the pipeline in the air. The mobile image acquisition device captures pipeline images and saves them as image collections, which include pipeline images at different angles and positions, covering the entire pipeline area within the preset range.

[0078] The inspection pipeline image set is analyzed to identify the potential gas leakage risk points in the image, which can be cracks, leakage, damage, etc. on the pipeline surface. For each identified risk point, a risk coefficient is assigned to it according to its location, size, shape, possible danger level, etc. The risk coefficient is used to indicate the severity of the risk and can reflect the potential threat level of the risk to safety.

[0079] The distance information between each potential hazard point and the target distribution cabinet is obtained. This distance information indicates the distance between each potential hazard point and the distribution cabinet, which can affect the potential impact of the potential hazard on the safety of the distribution cabinet.

[0080] Using the acquired distance information, the hidden danger coefficient of each hidden danger point is comprehensively calculated. For example, the hidden dangers that are closer may pose a greater potential threat to the distribution cabinet, so their hidden danger coefficients need to be weighted accordingly. The result of the comprehensive calculation is the comprehensive hidden danger coefficient of each hidden danger point. This coefficient combines the distance factor and the original hidden danger coefficient, and more accurately reflects the comprehensive impact of each hidden danger point on the safety of the distribution cabinet.

[0081] According to the comprehensive hidden danger coefficient, the previously set abnormal state prediction coefficient threshold is revised. That is, if the comprehensive hidden danger coefficient indicates that the hidden danger situation is more serious, the threshold of the abnormal state prediction coefficient will be lowered, so that the system can detect potential abnormal conditions more sensitively; on the contrary, if the comprehensive hidden danger coefficient indicates that the hidden danger situation is relatively minor, the threshold of the abnormal state prediction coefficient can be increased to reduce false alarms or excessive alarms. By revising the threshold of the abnormal state prediction coefficient, the sensitivity and accuracy of the abnormal state prediction can be adjusted according to the actual situation and urgency of the hidden danger situation, so as to better ensure the safe operation of the distribution cabinet.

[0082] Furthermore, based on the inspection pipeline image set, gas leakage hidden dangers are identified to obtain multiple hidden danger points, including:

[0083] Acquire a set of standard pipeline images, and establish a first twin recognition pair of a first inspection pipeline image in the inspection pipeline image set and a first standard pipeline image in the standard pipeline image set;

[0084] Based on the similarity twin network, perform similarity recognition on the first twin recognition pair to obtain the first image similarity;

[0085] Wherein, the similarity twin network includes a first feature extraction channel and a second feature extraction channel, and the first feature extraction channel and the second feature extraction channel have the same structure and shared parameters;

[0086] Determining whether the first inspection pipeline image has a potential hazard point based on the first image similarity;

[0087] When the similarity of the first image is less than a preset similarity threshold, a synchronous search is performed in the first twin recognition pair based on a preset anchor frame pair to obtain an area whose search similarity is less than the preset similarity threshold as a first hidden danger point;

[0088] A first search similarity of the first hidden danger point is obtained, and a first hidden danger coefficient is obtained based on the first search similarity, wherein the first search similarity is inversely proportional to the first hidden danger coefficient.

[0089] A set of standard pipeline image collections is established. These images are photos of the pipeline taken under normal conditions. The standard images represent the normal state of the pipeline and can be used as a reference to identify abnormal conditions in inspection images.

[0090] Any image is selected from the inspection pipeline image set as the first inspection pipeline image. For the first inspection pipeline image, a first standard pipeline image at a corresponding position is searched in the standard pipeline image to establish a first twin recognition pair.

[0091] The similarity twin network consists of two feature extraction channels, namely the first feature extraction channel and the second feature extraction channel. The two feature extraction channels have the same structure and share the same parameters, which means that they have the same network structure and weight parameters, but are applied to different input images. Among them, the first feature extraction channel receives the first inspection pipeline image as input and extracts the feature representation of the image; the second feature extraction channel receives the standard pipeline image as input and extracts the feature representation of the image.

[0092] The extracted feature representation is sent to the similarity calculation module to calculate the similarity between the first image and the standard image in its twin recognition pair. The similarity can be calculated using various methods, such as cosine similarity, Euclidean distance, etc., and the similarity value between the first image and the standard image is output. This value reflects the degree of similarity between them. This similarity value will be used as a basis for judging whether the first image is similar to the standard image, and then used for anomaly detection and pipeline status evaluation.

[0093] By comparing the similarity of the first image with a preset similarity threshold, it is determined whether the first image is similar to the standard image. If the similarity of the first image is lower than the preset similarity threshold, it is considered that there is a difference in the first image and there are potential danger points.

[0094] When the similarity of the first image is lower than the preset similarity threshold, a synchronous search based on a preset anchor frame is started. The preset anchor frame is a pair of frames of fixed size and shape, which are used to locate potential target areas in the image. A synchronous search is performed in the first twin recognition pair, that is, a pair of anchor frames are used to slide in the first inspection pipeline image and the first standard pipeline image respectively, and the regional similarity of the areas divided by the anchor frames on both sides is calculated. When the regional similarity is lower than the preset similarity threshold, it is identified as the first hidden danger point, that is, the area with hidden dangers. This process helps to quickly and accurately identify pipeline areas that may have problems, providing an information basis for subsequent detection.

[0095] The first search similarity of the first hidden danger point is obtained. The first search similarity indicates the similarity between the first inspection pipeline image and the first standard pipeline image in the first hidden danger point area. The lower the first search similarity, the higher the possibility of hidden danger. Therefore, the hidden danger coefficient of the first hidden danger point can be calculated based on the first search similarity. The hidden danger coefficient is inversely proportional to the first search similarity. The higher the hidden danger coefficient, the greater the possibility of the hidden danger point and the higher the possibility of the problem.

[0096] In summary, the explosion-proof power distribution cabinet control method based on situation awareness provided in the embodiment of the present application has the following technical effects:

[0097] 1. Through communication and connection with the power equipment management system and data monitoring system, timely collection and interaction of related power equipment information, operating condition data and status monitoring information are realized, improving the efficiency of data collection and processing;

[0098] 2. The situation awareness prediction model is used to analyze the status monitoring information and operating condition data of the target distribution cabinet, which enables accurate prediction of abnormal status and generates corresponding emergency processing instructions, thus improving the system's ability to respond to abnormal situations;

[0099] 3. According to whether the abnormal state prediction coefficient meets the threshold, the first emergency processing instruction is automatically generated, thereby realizing timely emergency processing of the target distribution cabinet and improving the efficiency and accuracy of emergency processing.

[0100] In summary, the situational awareness-based explosion-proof distribution cabinet control method can monitor and manage more effectively, improve the safety, stability and reliability of the system, and ensure the normal operation of the power system and the safety of equipment.

[0101] Based on the same inventive concept as the explosion-proof power distribution cabinet control method based on situation awareness in the aforementioned embodiment, Figure 2 As shown, the present application provides an explosion-proof distribution cabinet control system based on situational awareness, the system comprising:

[0102] An associated power equipment information acquisition module 10, wherein the associated power equipment information acquisition module 10 is used to acquire associated power equipment information of a target power distribution cabinet through the power equipment management system, wherein the target power distribution cabinet is connected to a plurality of associated power equipment;

[0103] A network topology structure generating module 20, the network topology structure generating module 20 is used to classify the plurality of associated power devices based on the associated power device information, analyze the connection relationship of the devices at the same level according to the classification result, and generate a device network topology structure;

[0104] An operation configuration parameter acquisition module 30, the operation configuration parameter acquisition module 30 is used to acquire usage scenario information of the plurality of associated power devices, perform operation parameter configuration of the device network topology structure based on the usage scenario information, and generate an operation configuration parameter set;

[0105] An operating condition data acquisition module 40, the operating condition data acquisition module 40 is used to collect the operating condition data of the plurality of related power devices through the data monitoring system to acquire an operating condition data set;

[0106] A judgment module 50, the judgment module 50 is used to judge whether the operating condition data set satisfies the operating configuration parameter set;

[0107] A real-time status monitoring module 60, wherein the real-time status monitoring module 60 is used to perform real-time status monitoring on the target power distribution cabinet when conditions are met, and obtain status monitoring information of the target power distribution cabinet;

[0108] An abnormal state prediction module 70, the abnormal state prediction module 70 is used to input the target distribution cabinet state monitoring information and the operating condition data set into a situation awareness prediction model to perform abnormal state prediction and obtain an abnormal state prediction coefficient;

[0109] The emergency processing module 80 is used to determine whether the abnormal state prediction coefficient meets the abnormal state prediction coefficient threshold. If it does, a first emergency processing instruction is generated, and emergency processing of the target distribution cabinet is performed based on the first emergency processing instruction.

[0110] Furthermore, the system further includes a second emergency processing module to perform the following operation steps:

[0111] When the operating condition data set does not satisfy the operating configuration parameter set, generating a second emergency processing instruction;

[0112] The abnormal state emergency plan of the target power distribution cabinet is read, and based on the abnormal state emergency plan and the second emergency processing instruction, emergency processing of the target power distribution cabinet is performed.

[0113] Furthermore, the system further includes a running configuration parameter set acquisition module to perform the following operation steps:

[0114] According to the usage scenario information, obtain working characteristics, workload, operation mode, and powered equipment;

[0115] generating a first configuration constraint according to the working characteristic, the workload, the operating mode, and the powered device;

[0116] generating a second configuration constraint according to a connection relationship between devices of the same level in the device network topology structure;

[0117] generating a third configuration constraint based on the rated parameters of the plurality of associated electrical devices;

[0118] The operation configuration parameter set is generated based on the first configuration constraint, the second configuration constraint, and the third configuration constraint, wherein the operation configuration parameter set includes power equipment operation mode configuration, equipment connection status configuration, and power equipment parameter configuration.

[0119] Furthermore, the system further includes an abnormal state prediction coefficient acquisition module to perform the following operation steps:

[0120] Inputting the target distribution cabinet state monitoring information into the distribution cabinet explosion-proof performance evaluation channel of the situation awareness prediction model to obtain the distribution cabinet explosion-proof grade;

[0121] The explosion-proof grade of the power distribution cabinet and the operating condition data set are input into the abnormal state prediction channel of the situation awareness prediction model to obtain the abnormal state prediction coefficient.

[0122] Furthermore, the system further includes an abnormal state prediction coefficient extraction module to perform the following operation steps:

[0123] The abnormal state prediction channel includes an initial digital twin model of the distribution cabinet, and the explosion-proof grade of the distribution cabinet is rendered to the initial digital twin model of the distribution cabinet to obtain the digital twin model of the distribution cabinet;

[0124] Based on the digital twin model of the power distribution cabinet, simulate the operation of the operating condition data set to obtain a number of simulated operation abnormality data of a number of abnormality-related power equipment that have abnormalities within a preset time zone, wherein the simulated operation abnormality data includes the time node and degree of abnormality when the abnormality occurs;

[0125] Anomaly assessment is performed based on the plurality of simulated operation abnormal data to obtain a plurality of abnormality assessment coefficients, and a maximum value among the plurality of abnormality assessment coefficients is extracted as the abnormal state prediction coefficient.

[0126] Furthermore, the system further includes an abnormal state prediction coefficient threshold correction module to perform the following operation steps:

[0127] By using the mobile image acquisition device, the gas transportation pipeline within the preset range of the target power distribution cabinet is inspected to obtain an inspection pipeline image set;

[0128] Based on the inspection pipeline image set, identify gas leakage hazards and obtain multiple hazard points, wherein the multiple hazard points correspond to multiple hazard coefficients;

[0129] Acquire multiple distance information between the multiple potential danger points and the target power distribution cabinet;

[0130] Comprehensively calculating the multiple hidden danger coefficients based on the multiple distance information to obtain a comprehensive hidden danger coefficient;

[0131] The abnormal state prediction coefficient threshold is corrected based on the comprehensive hidden danger coefficient.

[0132] Furthermore, the system further includes a first hidden danger coefficient acquisition module to perform the following operation steps:

[0133] Acquire a set of standard pipeline images, and establish a first twin recognition pair of a first inspection pipeline image in the inspection pipeline image set and a first standard pipeline image in the standard pipeline image set;

[0134] Based on the similarity twin network, perform similarity recognition on the first twin recognition pair to obtain the first image similarity;

[0135] Wherein, the similarity twin network includes a first feature extraction channel and a second feature extraction channel, and the first feature extraction channel and the second feature extraction channel have the same structure and shared parameters;

[0136] Determining whether the first inspection pipeline image has a potential hazard point based on the first image similarity;

[0137] When the similarity of the first image is less than a preset similarity threshold, a synchronous search is performed in the first twin recognition pair based on a preset anchor frame pair to obtain an area whose search similarity is less than the preset similarity threshold as a first hidden danger point;

[0138] A first search similarity of the first hidden danger point is obtained, and a first hidden danger coefficient is obtained based on the first search similarity, wherein the first search similarity is inversely proportional to the first hidden danger coefficient.

[0139] Through the above-mentioned detailed description of the explosion-proof distribution cabinet control method based on situation awareness in this specification, those skilled in the art can clearly understand the explosion-proof distribution cabinet control system based on situation awareness in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0140] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus, wherein the processor of the computer device is used to provide computing and control capabilities; the memory of the computer device includes a non-volatile storage medium and an internal memory, wherein the non-volatile storage medium stores an operating system, a computer program and a database, and 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 computer device is used to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement an explosion-proof distribution cabinet control method based on situational awareness.

[0141] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0142] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0143] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. The explosion-proof distribution cabinet control method based on situation awareness is characterized in that: The method is applied to an explosion-proof power distribution cabinet control system, the system is communicatively connected with an electric power equipment management system and a data monitoring system, and the method comprises: Acquiring associated power equipment information of a target power distribution cabinet through the power equipment management system, wherein the target power distribution cabinet is connected to a plurality of associated power equipment; Classify the plurality of associated power devices based on the associated power device information, analyze the connection relationship of devices of the same level according to the classification result, and generate a device network topology structure; Acquire usage scenario information of the plurality of associated power devices, configure operation parameters of the device network topology structure based on the usage scenario information, and generate an operation configuration parameter set; Through the data monitoring system, the operating condition data of the plurality of related power devices are collected to obtain an operating condition data set; Determining whether the operating condition data set satisfies the operating configuration parameter set; When the conditions are met, real-time status monitoring is performed on the target power distribution cabinet to obtain status monitoring information of the target power distribution cabinet; Inputting the target distribution cabinet state monitoring information and the operating condition data set into a situation awareness prediction model to perform abnormal state prediction and obtain an abnormal state prediction coefficient; Determine whether the abnormal state prediction coefficient meets the abnormal state prediction coefficient threshold, and if so, generate a first emergency processing instruction, and perform emergency processing on the target distribution cabinet based on the first emergency processing instruction.

2. The method according to claim 1, characterized in that Also includes: When the operating condition data set does not satisfy the operating configuration parameter set, generating a second emergency processing instruction; The abnormal state emergency plan of the target power distribution cabinet is read, and based on the abnormal state emergency plan and the second emergency processing instruction, emergency processing of the target power distribution cabinet is performed.

3. The method according to claim 1, characterized in that Acquiring usage scenario information of the plurality of associated power devices, configuring operation parameters of the device network topology structure based on the usage scenario information, and generating an operation configuration parameter set, including: According to the usage scenario information, obtain working characteristics, workload, operation mode, and powered equipment; generating a first configuration constraint according to the working characteristic, the workload, the operating mode, and the powered device; generating a second configuration constraint according to a connection relationship between devices of the same level in the device network topology structure; generating a third configuration constraint based on the rated parameters of the plurality of associated electrical devices; The operation configuration parameter set is generated based on the first configuration constraint, the second configuration constraint, and the third configuration constraint, wherein the operation configuration parameter set includes power equipment operation mode configuration, equipment connection status configuration, and power equipment parameter configuration.

4. The method according to claim 1, characterized in that Inputting the target distribution cabinet state monitoring information and the operating condition data set into the situation awareness prediction model to perform abnormal state prediction and obtain an abnormal state prediction coefficient, including: Inputting the target distribution cabinet state monitoring information into the distribution cabinet explosion-proof performance evaluation channel of the situation awareness prediction model to obtain the distribution cabinet explosion-proof grade; The explosion-proof grade of the power distribution cabinet and the operating condition data set are input into the abnormal state prediction channel of the situation awareness prediction model to obtain the abnormal state prediction coefficient.

5. The method according to claim 4, characterized in that Inputting the explosion-proof grade of the power distribution cabinet and the operating condition data set into the abnormal state prediction channel of the situation awareness prediction model to obtain the abnormal state prediction coefficient includes: The abnormal state prediction channel includes an initial digital twin model of the distribution cabinet, and the explosion-proof grade of the distribution cabinet is rendered to the initial digital twin model of the distribution cabinet to obtain the digital twin model of the distribution cabinet; Based on the digital twin model of the power distribution cabinet, simulate the operation of the operating condition data set to obtain a number of simulated operation abnormality data of a number of abnormality-related power equipment that have abnormalities within a preset time zone, wherein the simulated operation abnormality data includes the time node and degree of abnormality when the abnormality occurs; Anomaly assessment is performed based on the plurality of simulated operation abnormal data to obtain a plurality of abnormality assessment coefficients, and a maximum value among the plurality of abnormality assessment coefficients is extracted as the abnormal state prediction coefficient.

6. The method according to claim 1, characterized in that The data monitoring system also includes a mobile image acquisition device, and the method includes: By using the mobile image acquisition device, the gas transportation pipeline within the preset range of the target power distribution cabinet is inspected to obtain an inspection pipeline image set; Based on the inspection pipeline image set, identify gas leakage hazards and obtain multiple hazard points, wherein the multiple hazard points correspond to multiple hazard coefficients; Acquire multiple distance information between the multiple potential danger points and the target power distribution cabinet; Comprehensively calculating the multiple hidden danger coefficients based on the multiple distance information to obtain a comprehensive hidden danger coefficient; The abnormal state prediction coefficient threshold is corrected based on the comprehensive hidden danger coefficient.

7. The method according to claim 6, characterized in that Based on the inspection pipeline image set, gas leakage hidden dangers are identified to obtain multiple hidden danger points, including: Acquire a set of standard pipeline images, and establish a first twin recognition pair of a first inspection pipeline image in the inspection pipeline image set and a first standard pipeline image in the standard pipeline image set; Based on the similarity twin network, perform similarity recognition on the first twin recognition pair to obtain the first image similarity; Wherein, the similarity twin network includes a first feature extraction channel and a second feature extraction channel, and the first feature extraction channel and the second feature extraction channel have the same structure and shared parameters; Determining whether the first inspection pipeline image has a potential hazard point based on the first image similarity; When the similarity of the first image is less than a preset similarity threshold, a synchronous search is performed in the first twin recognition pair based on a preset anchor frame pair to obtain an area whose search similarity is less than the preset similarity threshold as a first hidden danger point; A first search similarity of the first hidden danger point is obtained, and a first hidden danger coefficient is obtained based on the first search similarity, wherein the first search similarity is inversely proportional to the first hidden danger coefficient.

8. The explosion-proof distribution cabinet control system based on situational awareness is characterized by: The system is connected in communication with the power equipment management system and the data monitoring system, and is used to implement the explosion-proof distribution cabinet control method based on situation awareness according to any one of claims 1 to 7. The system includes: An associated power equipment information acquisition module, the associated power equipment information acquisition module is used to acquire associated power equipment information of a target power distribution cabinet through the power equipment management system, wherein the target power distribution cabinet is connected to a plurality of associated power equipment; A network topology structure generating module, the network topology structure generating module is used to classify the plurality of associated power devices based on the associated power device information, analyze the connection relationship of the devices at the same level according to the classification result, and generate a device network topology structure; An operation configuration parameter acquisition module, the operation configuration parameter acquisition module is used to acquire usage scenario information of the plurality of associated power devices, perform operation parameter configuration of the device network topology structure based on the usage scenario information, and generate an operation configuration parameter set; An operating condition data acquisition module, the operating condition data acquisition module is used to collect the operating condition data of the plurality of related power devices through the data monitoring system to acquire an operating condition data set; A judgment module, the judgment module is used to judge whether the operating condition data set meets the operating configuration parameter set; A real-time status monitoring module, wherein the real-time status monitoring module is used to perform real-time status monitoring on the target power distribution cabinet when conditions are met, and obtain status monitoring information of the target power distribution cabinet; An abnormal state prediction module, the abnormal state prediction module is used to input the target distribution cabinet state monitoring information and the operating condition data set into a situation awareness prediction model to perform abnormal state prediction and obtain an abnormal state prediction coefficient; An emergency processing module is used to determine whether the abnormal state prediction coefficient meets the abnormal state prediction coefficient threshold. If so, a first emergency processing instruction is generated, and emergency processing of the target distribution cabinet is performed based on the first emergency processing instruction.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the explosion-proof distribution cabinet control method based on situation awareness described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the explosion-proof distribution cabinet control method based on situation awareness described in any one of claims 1 to 7 are implemented.

Images