State monitoring method and device of gas insulated switchgear and electronic equipment

Abstract

The invention discloses a state monitoring method and device for gas insulated switchgear and electronic equipment. The method comprises the steps that operation characteristic parameters of the gas insulated switchgear to be subjected to state monitoring are acquired, and the operation characteristic parameters are used for representing the operation state of the gas insulated switchgear; performing analytic hierarchy process on the operation characteristic parameters to obtain an equipment state evaluation value of the gas insulated switchgear; utilizing a preset switch equipment state prediction model to predict the future equipment state of the gas insulation switch equipment based on the operation characteristic parameters to obtain an equipment state prediction value of the gas insulation switch equipment; and based on the equipment state evaluation value and the equipment state prediction value, determining a state monitoring result of the gas insulated switchgear. According to the invention, the technical problem that the efficiency of monitoring the state of the gas insulated switchgear is low in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of switchgear monitoring, and in particular to a method, a device and an electronic device for monitoring the state of a gas insulated switchgear. Background Art

[0002] In the electric power sector, real-time monitoring and analysis of relevant components and parameters of gas-insulated switchgear, that is, status monitoring of gas-insulated switchgear, is performed to ensure the normal operation, safety and stability of gas-insulated switchgear. Status monitoring of gas-insulated switchgear can realize intelligent management and maintenance of equipment and improve the operating efficiency and safety of the power system.

[0003] At present, the condition monitoring method of gas-insulated switchgear in related technologies mainly relies on regular manual inspections and static tests. This method is not only time-consuming and labor-intensive, but also difficult to reflect the actual status of the equipment in real time. In addition, fault diagnosis and condition assessment based on experience often have a certain degree of subjectivity, and it is difficult to ensure accuracy, resulting in low efficiency in condition monitoring of gas-insulated switchgear.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a method, device and electronic equipment for monitoring the state of a gas insulated switchgear, so as to at least solve the technical problem of low efficiency in monitoring the state of a gas insulated switchgear in the related art.

[0006] According to one aspect of an embodiment of the present invention, a method for state monitoring of a gas insulated switchgear is provided, comprising: obtaining operating characteristic parameters of a gas insulated switchgear to be state monitored, wherein the operating characteristic parameters are used to characterize the operating condition of the gas insulated switchgear; performing hierarchical analysis on the operating characteristic parameters to obtain an equipment state evaluation value of the gas insulated switchgear, wherein the equipment state evaluation value is used to represent an evaluation value obtained by evaluating the current equipment state of the gas insulated switchgear based on the importance corresponding to each characteristic parameter in the operating characteristic parameters; predicting the future equipment state of the gas insulated switchgear based on the operating characteristic parameters using a preset switchgear state prediction model to obtain an equipment state prediction value of the gas insulated switchgear; and determining a state monitoring result of the gas insulated switchgear based on the equipment state evaluation value and the equipment state prediction value.

[0007] Optionally, a hierarchical analysis is performed on the operating characteristic parameters to obtain an equipment status evaluation value of the gas insulated switchgear, including: obtaining weight parameters corresponding to each characteristic parameter in the operating characteristic parameters, wherein the weight parameters are used to characterize the importance corresponding to each characteristic parameter; and determining the equipment status evaluation value based on the operating characteristic parameters and the weight parameters.

[0008] Optionally, based on the operating characteristic parameters and the weight parameters, the device state evaluation value is determined, including: normalizing each characteristic parameter in the operating characteristic parameters to obtain a normalized characteristic parameter; and performing weighted summation on the normalized characteristic parameter and the weight parameter to determine the device state evaluation value.

[0009] Optionally, the preset switchgear state prediction model includes a dimension reduction submodule and a state prediction submodule, and the output end of the state prediction submodule is connected to the input end of the dimension reduction submodule; the preset switchgear state prediction model is used to predict the future equipment state of the gas-insulated switchgear based on the operating characteristic parameters to obtain the equipment state prediction value of the gas-insulated switchgear; including: performing data dimension reduction processing on the operating characteristic parameters based on the dimension reduction submodule to obtain a one-dimensional feature vector; using the state prediction submodule to predict the future equipment state of the gas-insulated switchgear based on the one-dimensional feature vector to obtain the equipment state prediction value.

[0010] Optionally, the dimensionality reduction submodule includes at least a pooling layer and multiple convolution layers, the input end of the pooling layer is connected to the output ends of the multiple convolution layers, and the multiple convolution layers are connected in series; based on the dimensionality reduction submodule, data dimensionality reduction processing is performed on the operating characteristic parameters to obtain a one-dimensional feature vector, including: based on multiple convolution layers, feature extraction is performed on the operating characteristic parameters in turn to obtain a convolution result, wherein the feature correlation degree of the data in the convolution result is greater than the feature correlation degree of the data in the operating characteristic parameters; based on the pooling layer, the convolution result is pooled to obtain a one-dimensional feature vector.

[0011] Optionally, the state prediction submodule is used to predict the future equipment state of the gas-insulated switchgear based on the one-dimensional feature vector to obtain the equipment state prediction value, including: using the multi-head attention mechanism in the state prediction submodule to perform parallel self-attention calculation on the one-dimensional feature vector to obtain multiple self-attention calculation results; splicing the multiple self-attention calculation results to obtain the equipment state prediction value.

[0012] According to another aspect of an embodiment of the present invention, a state monitoring device for a gas insulated switchgear is also provided, comprising: an acquisition module, used to acquire operating characteristic parameters of the gas insulated switchgear to be state-monitored, wherein the operating characteristic parameters are used to characterize the operating status of the gas insulated switchgear; an analysis module, used to perform hierarchical analysis on the operating characteristic parameters to obtain an equipment state evaluation value of the gas insulated switchgear, wherein the equipment state evaluation value is used to represent an evaluation value obtained by evaluating the current equipment state of the gas insulated switchgear based on the importance corresponding to each characteristic parameter in the operating characteristic parameters; a prediction module, used to predict the future equipment state of the gas insulated switchgear based on the operating characteristic parameters using a preset switchgear state prediction model, and obtain an equipment state prediction value of the gas insulated switchgear; and a determination module, used to determine the state monitoring result of the gas insulated switchgear based on the equipment state evaluation value and the equipment state prediction value.

[0013] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the method in each embodiment of the present invention is executed when the program is running.

[0014] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0015] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0016] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0017] According to another aspect of the embodiments of the present invention, a computer program is further provided. When the computer program is executed by a processor, the methods in the embodiments of the present invention are implemented.

[0018] In an embodiment of the present invention, a method for state monitoring of a gas insulated switchgear is provided, comprising: obtaining operating characteristic parameters of a gas insulated switchgear to be state monitored, wherein the operating characteristic parameters are used to characterize the operating condition of the gas insulated switchgear; performing hierarchical analysis on the operating characteristic parameters to obtain an equipment state evaluation value of the gas insulated switchgear, wherein the equipment state evaluation value is used to represent an evaluation value obtained by evaluating the current equipment state of the gas insulated switchgear based on the importance corresponding to each characteristic parameter in the operating characteristic parameters; predicting the future equipment state of the gas insulated switchgear based on the operating characteristic parameters using a preset switchgear state prediction model to obtain an equipment state prediction value of the gas insulated switchgear; and determining a state monitoring result of the gas insulated switchgear based on the equipment state evaluation value and the equipment state prediction value. It is easy to notice that, by obtaining the operating characteristic parameters of the gas-insulated switchgear, the present application can fully understand the operating status of the equipment. Through the hierarchical analysis method, these operating characteristic parameters can be weighted and the importance of each characteristic parameter to the equipment status can be determined, thereby obtaining the equipment status evaluation value. By using the preset switchgear status prediction model, the future equipment status can be predicted based on the operating characteristic parameters, which can detect possible problems and faults in advance and provide timely reference for equipment maintenance and repair. Finally, based on the equipment status evaluation value and the equipment status prediction value, the status monitoring results of the gas-insulated switchgear are determined, which can comprehensively and objectively evaluate the current status and future trends of the equipment and provide a scientific basis for equipment management and maintenance. Through the above steps, the efficiency and accuracy of the status monitoring of the gas-insulated switchgear can be effectively improved, potential problems can be discovered and solved in time, and the safe and stable operation of the equipment can be ensured, thereby solving the technical problem of low efficiency of status monitoring of gas-insulated switchgear in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0020] Figure 1 is a flow chart of a method for monitoring the state of a gas insulated switchgear according to an embodiment of the present invention;

[0021] Figure 2 is a flow chart of an optional method for monitoring the state of a gas-insulated switchgear according to an embodiment of the present invention;

[0022] Figure 3 is a schematic diagram of an optional data type of an optional operating characteristic parameter according to an embodiment of the present invention;

[0023] Figure 4is a schematic diagram of an optional method of performing state prediction using a preset switch device state prediction model according to an embodiment of the present invention;

[0024] Figure 5 is a schematic diagram of a state monitoring device for a gas insulated switchgear according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] According to one aspect of an embodiment of the present invention, a condition monitoring method for a gas insulated switchgear is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0028] Figure 1 is a flow chart of a method for monitoring the state of a gas insulated switchgear according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0029] Step S102, obtaining operating characteristic parameters of the gas insulated switchgear to be state monitored.

[0030] Among them, the operating characteristic parameters are used to characterize the operating conditions of the gas insulated switchgear.

[0031] The above-mentioned gas insulated switchgear (GIS) can be a device used for interrupting and isolating circuits in power systems. Gas, usually sulfide gas, can be used as an insulating medium to isolate circuits. The gas insulated switchgear can be composed of components such as circuit breakers, disconnectors, earthing switches and mutual inductors. These components are encapsulated in a closed metal casing through gas insulation technology, thereby effectively protecting the equipment from the influence of the external environment. It has the advantages of small footprint, compact structure, and easy maintenance, and is widely used in modern power systems.

[0032] In an optional embodiment, obtaining the operating characteristic parameters of the gas-insulated switchgear to be state-monitored can be achieved through the following steps. Sensors suitable for monitoring the operating characteristic parameters of the gas-insulated switchgear can be selected, such as temperature sensors, humidity sensors, pressure sensors, etc., and the selected sensors can be installed on the gas-insulated switchgear to ensure that the position of the sensor can accurately reflect the operating status of the equipment. The sensor is connected to a data acquisition device to ensure that the sensor can transmit real-time data to the monitoring system. The data returned by the sensor is collected in real time by the data acquisition device, including parameters such as temperature, humidity, and pressure. The collected data can be processed and analyzed, and data mining, machine learning, and other methods can be used to identify the operating characteristic parameters of the equipment. Through the above steps, the operating characteristic parameters of the gas-insulated switchgear to be state-monitored can be obtained, which is convenient for subsequent real-time monitoring and analysis of the equipment status, timely discovery and processing of problems, and provides a data basis for subsequent steps.

[0033] Step S104: Perform hierarchical analysis on the operating characteristic parameters to obtain an equipment state evaluation value of the gas insulated switchgear.

[0034] The device state evaluation value is used to represent an evaluation value obtained by evaluating the current device state of the gas insulated switchgear based on the importance level corresponding to each characteristic parameter in the operating characteristic parameters.

[0035] The above-mentioned current device status may refer to the device status at the current monitoring time. The current monitoring time may change with the monitoring real time, which is not limited here.

[0036] In an optional embodiment, when monitoring and evaluating the status of the gas-insulated switchgear, a hierarchical analysis can be performed on the operating characteristic parameters to determine the importance and interrelationships between the various parameters. This can be done through expert experience, data analysis and other methods. When performing the hierarchical analysis, the analytic hierarchy process (AHP) or other multi-criteria decision-making methods can be used. Through the hierarchical analysis, the influence weight of each characteristic parameter on the equipment status, that is, the importance of each characteristic parameter, can be obtained. These weights can be used to calculate the equipment status evaluation value, which indicates the degree of goodness or badness of the current status of the equipment. The evaluation value can be a comprehensive numerical value or a grade or descriptive result. Finally, the operating status of the equipment can be evaluated and judged based on the equipment status evaluation value. If the evaluation value is high, it means that the equipment is in good condition; if the evaluation value is low, it may indicate that there is a problem with the equipment or that maintenance is required. Through continuous monitoring and evaluation, equipment problems can be discovered in time and corresponding measures can be taken to ensure the normal operation and safety of the equipment.

[0037] Step S106, using a preset switchgear state prediction model to predict the future state of the gas-insulated switchgear based on the operating characteristic parameters, to obtain a predicted value of the state of the gas-insulated switchgear.

[0038] The above-mentioned future device state may refer to the device state at a preset time point after the current monitoring time, for example, 1 second, 1 hour or one week after the current monitoring time, which can be determined according to actual needs and is not limited here.

[0039] The above-mentioned preset switch device state prediction model may refer to a preset neural network model for predicting the future device state of the switch device. The preset switch device state prediction model may be specifically determined according to actual needs and is not limited here.

[0040] In an optional embodiment, a preset switchgear state prediction model can be used to predict the future equipment state of the gas-insulated switchgear based on the operating characteristic parameters to obtain the equipment state prediction value of the gas-insulated switchgear. Specifically, a gas-insulated switchgear state prediction model can be established based on the collected historical characteristic parameter data, and machine learning, neural network and other methods can be used to establish and train the model to achieve the prediction of the equipment state; during the monitoring process, the established preset switchgear state prediction model can be used to predict the future equipment state, and the real-time operating characteristic parameters of the equipment can be input into the model for calculation to obtain the future state prediction value of the equipment, and the predicted equipment state prediction value can be output to the monitoring system or operator. By monitoring the difference between the equipment state prediction value and the actual equipment state in real time, equipment abnormalities can be discovered in time, and corresponding measures can be taken for maintenance and repair. Through the above steps, the preset switchgear state prediction model can be used to predict the future equipment state of the gas-insulated switchgear based on the operating characteristic parameters to obtain the equipment state prediction value.

[0041] Step S108, determining a state monitoring result of the gas insulated switchgear based on the equipment state evaluation value and the equipment state prediction value.

[0042] In an optional embodiment, the equipment state evaluation value and the equipment state prediction value can be combined to comprehensively consider the current state of the equipment and future development trends. Specifically, the equipment state evaluation value and the equipment state prediction value can be fused to comprehensively consider the actual operating state and possible future state of the equipment to obtain the final state monitoring result. Data fusion can be carried out in a variety of ways. The equipment state evaluation value and the equipment state prediction value can be weighted respectively, and then the weighted average is used to obtain the final result, or logical operations such as AND, OR, and NOT can be used according to the logical relationship between the equipment state evaluation value and the equipment state prediction value to obtain the final result to determine the state monitoring result of the gas insulated switchgear. According to the monitoring results, corresponding measures can be taken in time to ensure the normal operation and safety of the equipment. By implementing the above steps, the state of the gas insulated switchgear can be effectively monitored and evaluated, the reliability and safety of the equipment can be improved, and the occurrence of failures and accidents can be reduced.

[0043] In an embodiment of the present invention, a method for state monitoring of a gas insulated switchgear is provided, comprising: obtaining operating characteristic parameters of a gas insulated switchgear to be state monitored, wherein the operating characteristic parameters are used to characterize the operating condition of the gas insulated switchgear; performing hierarchical analysis on the operating characteristic parameters to obtain an equipment state evaluation value of the gas insulated switchgear, wherein the equipment state evaluation value is used to represent an evaluation value obtained by evaluating the current equipment state of the gas insulated switchgear based on the importance corresponding to each characteristic parameter in the operating characteristic parameters; predicting the future equipment state of the gas insulated switchgear based on the operating characteristic parameters using a preset switchgear state prediction model to obtain an equipment state prediction value of the gas insulated switchgear; and determining a state monitoring result of the gas insulated switchgear based on the equipment state evaluation value and the equipment state prediction value. It is easy to notice that, by obtaining the operating characteristic parameters of the gas-insulated switchgear, the present application can fully understand the operating status of the equipment. Through the hierarchical analysis method, these operating characteristic parameters can be weighted and the importance of each characteristic parameter to the equipment status can be determined, thereby obtaining the equipment status evaluation value. By using the preset switchgear status prediction model, the future equipment status can be predicted based on the operating characteristic parameters, which can detect possible problems and faults in advance and provide timely reference for equipment maintenance and repair. Finally, based on the equipment status evaluation value and the equipment status prediction value, the status monitoring results of the gas-insulated switchgear are determined, which can comprehensively and objectively evaluate the current status and future trends of the equipment and provide a scientific basis for equipment management and maintenance. Through the above steps, the efficiency and accuracy of the status monitoring of the gas-insulated switchgear can be effectively improved, potential problems can be discovered and solved in time, and the safe and stable operation of the equipment can be ensured, thereby solving the technical problem of low efficiency of status monitoring of gas-insulated switchgear in related technologies.

[0044] Optionally, a hierarchical analysis is performed on the operating characteristic parameters to obtain an equipment status evaluation value of the gas insulated switchgear, including: obtaining weight parameters corresponding to each characteristic parameter in the operating characteristic parameters, wherein the weight parameters are used to characterize the importance corresponding to each characteristic parameter; and determining the equipment status evaluation value based on the operating characteristic parameters and the weight parameters.

[0045] In an optional embodiment, weight parameters corresponding to each characteristic parameter in the operating characteristic parameters can be obtained, and the equipment status evaluation value can be determined based on these parameters. The importance of each characteristic parameter to the equipment status, that is, the weight parameters, can be determined through expert experience or data analysis methods. These weight parameters can be empirical values ​​or obtained through data analysis algorithms. Then, according to the operating characteristic parameters of the equipment and the corresponding weight parameters, a suitable algorithm such as weighted average, principal component analysis, etc. can be used to calculate the equipment status evaluation value. The equipment status evaluation value can be used to reflect the current operating status of the equipment so as to perform maintenance and troubleshooting in a timely manner. According to the actual situation and needs of the equipment, the standard for equipment status evaluation can be set to determine the equipment status level corresponding to different status evaluation values ​​for subsequent status monitoring and early warning. Through the above steps, the weight parameters of each characteristic parameter in the operating characteristic parameters can be obtained, and the equipment status evaluation value can be determined based on these parameters to achieve monitoring and evaluation of the status of gas insulated switchgear.

[0046] Optionally, based on the operating characteristic parameters and the weight parameters, the device state evaluation value is determined, including: normalizing each characteristic parameter in the operating characteristic parameters to obtain a normalized characteristic parameter; and performing weighted summation on the normalized characteristic parameter and the weight parameter to determine the device state evaluation value.

[0047] In an optional embodiment, the various collected operating characteristic parameters can be normalized to perform a unified weighted calculation. The normalization can be performed by linear transformation or other mathematical methods. The weight parameters of the various operating characteristic parameters can be determined according to the actual situation and importance of the equipment. The weight parameters can be determined based on experience, or calculated by expert evaluation or mathematical model. The normalized operating characteristic parameters and the corresponding weight parameters can be weighted summed to obtain the equipment status evaluation value. Finally, the calculated equipment status evaluation value can be used to determine whether the equipment is operating normally. The closer the equipment status evaluation value is to 1, the better the equipment operation status is. Otherwise, it means that there may be problems with the equipment. Through the above steps, the process of determining the equipment status evaluation value based on the operating characteristic parameters and weight parameters can be realized, thereby monitoring and evaluating the status of the gas insulated switchgear.

[0048] Optionally, the preset switchgear state prediction model includes a dimension reduction submodule and a state prediction submodule, and the output end of the state prediction submodule is connected to the input end of the dimension reduction submodule; the preset switchgear state prediction model is used to predict the future equipment state of the gas-insulated switchgear based on the operating characteristic parameters to obtain the equipment state prediction value of the gas-insulated switchgear; including: performing data dimension reduction processing on the operating characteristic parameters based on the dimension reduction submodule to obtain a one-dimensional feature vector; using the state prediction submodule to predict the future equipment state of the gas-insulated switchgear based on the one-dimensional feature vector to obtain the equipment state prediction value.

[0049] In an optional embodiment, the preset switch device state prediction model includes a dimensionality reduction submodule and a state prediction submodule. The output end of the state prediction submodule is connected to the input end of the dimensionality reduction submodule. The dimensionality reduction submodule can be used to perform data dimensionality reduction processing on the operating characteristic parameters to obtain a one-dimensional feature vector. The dimensionality reduction method can include principal component analysis, linear discriminant analysis, etc. The trained state prediction model can be used to predict the future equipment state of the gas-insulated switchgear to obtain the equipment state prediction value. The prediction value can reflect the operating status of the equipment and possible failure risks. Through the above steps, the state of the gas-insulated switchgear can be predicted and monitored, which helps to discover equipment problems in advance and perform maintenance in time to ensure the safe and stable operation of the equipment.

[0050] Optionally, the dimensionality reduction submodule includes at least a pooling layer and multiple convolution layers, the input end of the pooling layer is connected to the output ends of the multiple convolution layers, and the multiple convolution layers are connected in series; based on the dimensionality reduction submodule, data dimensionality reduction processing is performed on the operating characteristic parameters to obtain a one-dimensional feature vector, including: based on multiple convolution layers, feature extraction is performed on the operating characteristic parameters in turn to obtain a convolution result, wherein the feature correlation degree of the data in the convolution result is greater than the feature correlation degree of the data in the operating characteristic parameters; based on the pooling layer, the convolution result is pooled to obtain a one-dimensional feature vector.

[0051] In an optional embodiment, the operating characteristic parameters can be passed as input data to the convolution layer, and features are extracted through the convolution operation. The output of the last convolution layer will be connected to the input of the pooling layer. The pooling layer performs pooling on the convolution result to obtain the pooled output. In each convolution layer, data with a higher degree of feature correlation can be obtained through the convolution operation, that is, after feature extraction of each convolution result, a group of data with more significant features can be obtained. Finally, the convolution result is pooled based on the pooling layer to obtain a one-dimensional feature vector. The pooling layer is after the convolution layer, and the convolution result can be reduced in dimensionality to reduce the data dimension while maintaining the quality. Important feature information is retained. Pooling operations can include maximum pooling and average pooling. Maximum pooling selects the maximum value of each area in the feature map as the pooling result, and average pooling calculates the average value of each area. Pooling operations can reduce the number of parameters and reduce model complexity, while improving the robustness and generalization ability of the model. The obtained one-dimensional feature vector contains important features extracted by multiple convolution and pooling operations, which can be used for subsequent state monitoring and analysis tasks. Through the above steps, the operating characteristic parameters of the gas-insulated switchgear can be processed by data dimensionality reduction to obtain a one-dimensional feature vector, thereby better performing state monitoring and analysis.

[0052] Optionally, the state prediction submodule is used to predict the future equipment state of the gas-insulated switchgear based on the one-dimensional feature vector to obtain the equipment state prediction value, including: using the multi-head attention mechanism in the state prediction submodule to perform parallel self-attention calculation on the one-dimensional feature vector to obtain multiple self-attention calculation results; splicing the multiple self-attention calculation results to obtain the equipment state prediction value.

[0053] In an optional embodiment, a state prediction submodule can be used to predict the future equipment state based on a one-dimensional feature vector. Specifically, a multi-head attention mechanism can be used to perform parallel self-attention calculations on the one-dimensional feature vector. The multi-head attention mechanism maps the input one-dimensional feature vector to multiple subspaces respectively, and then calculates the attention weight in each subspace. Finally, the attention weights of all subspaces are added to obtain the final attention weight; then, the self-attention calculation results calculated by multiple subspaces can be spliced ​​to obtain a predicted value of the equipment state. The spliced ​​results can be further processed through a fully connected layer to obtain a final equipment state prediction value. The obtained equipment state prediction value can be compared with the actual observation value to evaluate the accuracy and reliability of the prediction model. According to the evaluation results, the model can be adjusted and optimized to improve the accuracy and stability of the state prediction. Through the above steps, the state prediction submodule is used to predict the future equipment state of the gas-insulated switchgear based on the one-dimensional feature vector, which can improve the efficiency and accuracy of equipment state monitoring and provide more accurate guidance for equipment operation and maintenance.

[0054] The technical solution proposed in this application is explained below in combination with an optional application scenario. Gas insulated switchgear (GIS) is a relatively critical equipment in modern power systems. Gas insulated switchgear is widely used in substations and distribution systems. Gas insulated switchgear can effectively reduce the size of the equipment and improve the electrical performance of the equipment by using sulfur hexafluoride (SF6) gas as an insulating medium. However, during the long-term operation of gas insulated switchgear, it may be affected by various factors such as environmental changes, material aging and operating load, resulting in equipment performance degradation, insulation failure and even equipment failure. In severe cases, it may cause power accidents, resulting in equipment damage and economic losses. Therefore, accurately predicting the operating status of gas insulated switchgear is relatively important to ensure the safe, stable and economical operation of the power system.

[0055] In recent years, with the development of sensor technology, online monitoring systems can collect real-time operating data of gas-insulated switchgear such as temperature and vibration. The introduction of these data provides relatively rich information for state prediction. At the same time, the rapid development of deep learning technology has provided new solutions for the analysis and state prediction of time series data. Convolutional neural networks (CNN) have shown excellent performance in processing images and time series data, while the Transformer model has a relatively powerful self-attention mechanism that can effectively capture long-distance dependencies and global information. This makes the combination of convolutional neural networks (CNN) and models (Transformer) very suitable for state prediction of gas-insulated switchgear.

[0056] The present application provides a gas-insulated switchgear state prediction method based on a combined model of a model (Transformer) and a convolutional neural network (CNN). By combining the advantages of the convolutional neural network and the model (Transformer), the prediction accuracy and real-time performance of the gas-insulated switchgear state are improved, thereby achieving early warning of equipment failures.

[0057] To achieve the above purpose, the technical solution adopted in this application includes a gas insulated switchgear state prediction method combining a model (Transformer) and a convolutional neural network (CNN), comprising the following steps:

[0058] The sensors are used to collect various state parameter data of gas-insulated switchgear, including temperature, vibration, SF6 gas decomposition products, trace water and partial discharge, that is, to obtain the operating characteristic parameters, and to build a gas-insulated switchgear state indicator system; the collected various state parameter data are preprocessed; a comprehensive state evaluation result is obtained based on multiple parameter data of online detection and non-online detection; a convolutional neural network (CNN)-Trans combined prediction model of gas-insulated switchgear state is constructed, which can be the above-mentioned preset switchgear state prediction model, and the trained convolutional neural network (CNN)-Trans model is used to predict the state of gas-insulated switchgear in real time, and output the future state parameter change trend of the equipment and fault warning information.

[0059] In the steps of the gas-insulated switchgear state prediction method based on convolutional neural network (CNN)-Trans, SF6 decomposition products, partial discharge, temperature, vibration and micro-water content of the gas-insulated switchgear in the state performance data can be selected to construct a state prediction feature set, and the influence of different state parameters can be weighted analyzed using the analytic hierarchy process (AHP), and the importance of each parameter to the equipment operation state can be evaluated to obtain a comprehensive state evaluation result, that is, the equipment state evaluation value can be obtained; the membership of the operation time is used as input, and the state reliability interval to be predicted at the next moment is used as output, that is, the equipment state prediction value can be obtained; data preprocessing can be performed, which can include missing value processing, outlier processing, removal of duplicate data, data cleaning, and normalization of state parameters; the input signal is first extracted through a convolutional neural network (CNN) Feature set and state evaluation result, the intrinsic relationship between the state prediction feature set and the state evaluation score is mined, a one-dimensional time series is constructed, and the feature vector is optimized and trained using a model (Transformer), and finally the output gas-insulated switchgear state prediction result is obtained, that is, the state monitoring result can be obtained.

[0060] This application can embed the trained model into the gas-insulated switchgear monitoring system to achieve online monitoring and status prediction; regularly collect new sensor data and retrain the model to ensure that the model can adapt to changes in equipment status and improve prediction accuracy.

[0061] The present application combines a convolutional neural network (CNN) with a Transformer model to effectively extract local features and global dependency features from multi-dimensional sensor data of gas-insulated switchgear, thereby significantly improving the accuracy of state prediction. The method can handle complex nonlinear relationships in time series data and performs relatively well in state prediction of long series data, and is suitable for real-time monitoring and fault warning of gas-insulated switchgear. The method of the present application has high computational efficiency and is suitable for large-scale industrial applications, especially for gas-insulated switchgear state prediction scenarios with complex multi-dimensional data.

[0062] Specifically, five parameters closely related to the operating state of the gas insulated switchgear may be selected according to the operating characteristics of the gas insulated switchgear, namely, operating characteristic parameters, which may include but are not limited to:

[0063] Temperature: The temperature data around the equipment is obtained through the temperature sensor. The change of ambient temperature will directly affect the performance of the gas-insulated switchgear, which is defined as:

[0064] T env (t);

[0065] Among them, T env (t) represents the ambient temperature at time point t.

[0066] Vibration: Use temperature sensors to monitor the vibration of the equipment. Abnormal vibration may indicate looseness or damage of the mechanical mechanism. It is defined as the vibration amplitude:

[0067]

[0068] Where x(t) 2 ,y(t) 2 、z(t) 2 are the components of the device vibration in three directions at time point t.

[0069] Sulfur hexafluoride (SF6) decomposition products are detected by gas detection equipment. The increase of SF6 decomposition products often means the occurrence of arc or partial discharge in the equipment. The concentration of decomposition products can be defined as:

[0070]

[0071] in, Indicates the concentration of SF6 decomposition products at time t.

[0072] Trace water content: The trace water content in SF6 gas is detected by a trace water sensor. Exceeding the limit of trace water content may lead to a decrease in insulation performance. It is defined as:

[0073]

[0074] in, Represents the micro-water content at time point t.

[0075] Partial discharge, through the ultra-high frequency (UHF) detection technology to obtain the relevant parameters of partial discharge, including the number of partial discharge, amplitude and its phase, reflecting the internal insulation degradation of the equipment, the total partial discharge energy can be defined as:

[0076]

[0077] Among them, V i (t) is the voltage of the ith discharge, Δt is the time interval, E PD (t) is expressed as the total partial discharge energy.

[0078] The operating characteristic parameters in the present application may include at least one of the above-mentioned temperature, vibration, sulfur hexafluoride (SF6) decomposition products, trace water content and partial discharge. The operating characteristic parameters can also be determined according to actual needs and are not limited here.

[0079] Next, the status assessment can be carried out based on the analytic hierarchy process (AHP). The gas-insulated switchgear is mainly composed of circuit breakers, disconnectors, earthing switches, lightning arresters, voltage transformers, current transformers and busbars. There are many indicators that affect and reflect the operating status of the gas-insulated switchgear. Through the analysis of the operating history, maintenance and fault data of the gas-insulated switchgear, at the same time, the operating mechanism, disconnectors and earthing switches, accessories, operating years, maintenance records and operating records are included in the gas-insulated switchgear operating status evaluation system, and multiple key status quantities of each component of the gas-insulated switchgear are collected and integrated.

[0080] Optionally, the analytic hierarchy process can be used to comprehensively evaluate the above five operating characteristic parameters. First, the weight of each parameter is defined:

[0081] W=[w1,w2,w3,w4,w5]=[0.25,0.20,0.25,0.15,0.15];

[0082] Then, each parameter is normalized, and then according to the above weight coefficient, the comprehensive status evaluation score H, that is, the equipment status evaluation value can be expressed as:

[0083]

[0084] In the formula, g ij represents the score of the jth evaluation index in the i-th comprehensive state, w i Represents the weight coefficient of the i-th comprehensive state quantity.

[0085] Next, a convolutional neural network (CNN)-Trans combined neural network can be established, and the normalized operating characteristic parameters can be input into the convolutional neural network for feature extraction. The structure of the convolutional neural network (CNN) network includes three convolutional layers and one pooling layer.

[0086] First, the first layer of convolution uses 8 3×3 convolution kernels with a step size of 1. The main function of this layer is to extract low-level features of the input data, such as edges and simple patterns; then, the second layer of convolution uses 16 3×3 convolution kernels to continue to capture deeper features of the low-level features extracted in the previous layer. The increase in the number of convolution kernels in this layer is to enhance the network's ability to capture complex features, such as higher-level geometric structures and local patterns; the third layer of convolution uses 32 3×3 convolution kernels to further expand the feature space of the data, so that the network can understand the deep associations between different features in the input data. The above convolution operation can be expressed as the following formula:

[0087]

[0088] After each layer of convolution operation, the convolution result is processed nonlinearly through the ReLU activation function. The formula can be as follows:

[0089] f(x)=max(0,max);

[0090] Where x is the output of the convolution operation.

[0091] After three layers of convolution, Valid maximum pooling is performed, that is, no padding is performed, and the step size of the pooling kernel is equal to the size of the pooling kernel. The role of maximum pooling is to reduce the size of the feature map and retain the most significant features in each local area. The formula can be expressed as:

[0092] Y pool (i,j)=maxX(i+m,j+n);

[0093] Among them, X is the input feature map, Y pool is the feature map after pooling, (i, j) represents the position of the pooling window, and m, n are the sizes of the pooling kernel.

[0094] After a series of convolution and pooling operations, the original multi-dimensional data is converted into several one-dimensional feature vectors of length 288 and input into the model (Transformer) for prediction.

[0095] First, position encoding is performed on the feature vector P obtained just now so that the model can understand the position information in the sequence. The encoding formula can be:

[0096]

[0097] Among them, pos represents the position of the feature in the sequence, i represents the dimension of the feature, and d model is the dimension of the embedding vector.

[0098] Then, the multi-head attention mechanism can be used to capture the feature dependencies of different time steps. The formula of the attention mechanism is:

[0099]

[0100] Among them, Q (query), K (key), and V (value) are obtained by linear transformation of input features, respectively. k The dimension of the key.

[0101] The multi-head attention mechanism calculates multiple attention heads in parallel, and each head extracts features from different subspaces. The specific steps are: divide the input feature vector into multiple heads, and each head performs independent self-attention calculation; the results of each head are spliced ​​through linear transformation to finally form a fused global feature.

[0102] After being processed by the multi-head attention mechanism, the output feature vector is input into a feedforward neural network. The feedforward neural network consists of two fully connected layers, with a nonlinear transformation performed by the ReLU activation function in the middle. The calculation formula is as follows:

[0103] FFN(x)=max(0,xW1+b1)W2+b2;

[0104] Among them, W1 and W2 are weight matrices, and b1 and b2 are bias vectors. The feedforward neural network is used to further extract and process the global features from the attention mechanism, so that the model can deeply model the complex nonlinear relationship of the time series.

[0105] In order to avoid the gradient vanishing problem and speed up training, the model (Transformer) introduces residual connection (ResidualConnection) and layer normalization (LayerNormalization) after each self-attention layer and feedforward neural network layer. The residual connection formula can be as follows:

[0106] output=LayerNorm(x+SubLayer(x));

[0107] Where x is the input vector, and SubLayer(x) is the self-attention mechanism or feedforward network output. Through residual connections, the input can be directly passed to subsequent layers, avoiding information loss in deep networks. Layer normalization ensures that the output of each layer has a uniform distribution, accelerating model convergence.

[0108] The final output is a predicted state score sequence, which represents the operating state of the gas-insulated switchgear at the future moment. The output value is processed by the fully connected layer and then denormalized. The formula can be as follows:

[0109] D pred =D norm ·(D max -D min )+D min ;

[0110] Among them, D pred is the denormalized predicted value, that is, the equipment status predicted value, D norm is the normalized model (Transformer) output value, D max and D min are the maximum and minimum values ​​of the original data. After denormalization, the true state prediction value of the gas-insulated switchgear is obtained, that is, the equipment state prediction value can be obtained.

[0111] The present application provides a method for predicting the state of a gas-insulated switchgear based on a convolutional neural network (CNN)-Trans combined neural network. First, the influencing factors of the operation of the gas-insulated switchgear are analyzed, and the performance index data obtained by monitoring are used to construct a hierarchical gas-insulated switchgear operation state prediction feature set; then, a gas-insulated switchgear state evaluation model is established by using a hierarchical analysis method to evaluate and quantify the operation state of the gas-insulated switchgear, and the final result is used as a neural network label. Finally, a convolutional neural network (CNN)-Trans combined neural network is used for processing and analysis. Finally, the following conclusions are drawn: the convolutional neural network (CNN) neural network can fully extract the feature quantity of the original data, and the model (Transformer) can better process long sequence data than GRU and LSTM, and the training speed is better than these two. The combination of the two has a better processing effect on the multi-dimensional state quantity gas-insulated switchgear operation data. The convolutional neural network (CNN)-Trans joint neural network model combines the advantages of the convolutional neural network (CNN) network and the model (Transformer), and has better prediction accuracy and efficiency than the traditional artificial intelligence prediction model.

[0112] Figure 2 is a flow chart of an optional method for monitoring the state of a gas-insulated switchgear according to an embodiment of the present invention, such as Figure 2As shown, it includes: S202, obtaining the operating characteristic parameters of the gas-insulated switchgear to be state-monitored; S204, obtaining the weight parameters corresponding to each characteristic parameter in the operating characteristic parameters, wherein the weight parameters are used to characterize the importance of each characteristic parameter; determining the equipment state evaluation value based on the operating characteristic parameters and the weight parameters; S206, performing data dimensionality reduction processing on the operating characteristic parameters based on the dimensionality reduction submodule in the preset switchgear state prediction model to obtain a one-dimensional feature vector; using the state prediction submodule to predict the future equipment state of the gas-insulated switchgear based on the one-dimensional feature vector to obtain the equipment state prediction value; S208, determining the state monitoring result of the gas-insulated switchgear based on the equipment state evaluation value and the equipment state prediction value.

[0113] Figure 3 is a schematic diagram of an optional data type of an optional operating characteristic parameter according to an embodiment of the present invention, such as Figure 3 As shown, the operating characteristic parameters may include online monitoring data, operating mechanism, disconnect and earthing switches, operating records and data on operating records, wherein the online monitoring data may include data on sulfur hexafluoride temperature, sulfur hexafluoride gas pressure, sulfur hexafluoride micro-water content and partial discharge; the operating mechanism may include data on energy storage circuits, motors and oil pumps, opening and closing coils and mechanical properties; the disconnect and earthing switches may include data on insulation resistance, mechanical action parts and number of operations; the operating records may include data on appearance, load conditions and fault conditions; the operating records may include data on operating years, family defects and defects and maintenance records.

[0114] The above-mentioned family defects may refer to common defects or problems existing in the design, manufacturing or use of the same type of switchgear. The family defects of gas-insulated switchgear may include unreasonable design, substandard material quality, process defects, mismatched parts and accessories, etc. Manufacturers and users should pay close attention to these family defects, make timely improvements and maintenance, and ensure the safe and reliable operation of the equipment.

[0115] Figure 4 is a schematic diagram of an optional state prediction using a preset switch device state prediction model according to an embodiment of the present invention, such as Figure 4 As shown, the process of state prediction using the preset switchgear state prediction model can include feature normalization and matrix processing of online monitoring data such as vibration and temperature, and non-online monitoring data such as sulfur hexafluoride decomposition products, micro-water content, and partial discharge, and then three convolutions and maximum pooling. Then, position encoding, multi-head attention mechanism and feedforward neural network are performed to obtain the prediction result.

[0116] The prediction result here may be the above-mentioned device state prediction value, and the method for determining the device state prediction value may also be determined according to actual needs, which is not limited here.

[0117] According to another aspect of an embodiment of the present invention, a state monitoring device for a gas insulated switchgear is also provided, which can execute the state monitoring method for a gas insulated switchgear of the above embodiment. The specific implementation method and preferred application scenario are the same as those of the above embodiment and will not be repeated here.

[0118] Figure 5 is a schematic diagram of a state monitoring device for a gas insulated switchgear according to an embodiment of the present application, such as Figure 5 As shown, the device includes the following: an acquisition module 502 , an analysis module 504 , a prediction module 506 and a determination module 508 .

[0119] Among them, the acquisition module is used to obtain the operating characteristic parameters of the gas-insulated switchgear to be state-monitored, wherein the operating characteristic parameters are used to characterize the operating status of the gas-insulated switchgear; the analysis module is used to perform hierarchical analysis on the operating characteristic parameters to obtain the equipment state evaluation value of the gas-insulated switchgear, wherein the equipment state evaluation value is used to represent the evaluation value obtained by evaluating the current equipment state of the gas-insulated switchgear based on the importance corresponding to each characteristic parameter in the operating characteristic parameters; the prediction module is used to predict the future equipment state of the gas-insulated switchgear based on the operating characteristic parameters using a preset switchgear state prediction model, and obtain the equipment state prediction value of the gas-insulated switchgear; the determination module is used to determine the state monitoring result of the gas-insulated switchgear based on the equipment state evaluation value and the equipment state prediction value.

[0120] The analysis module is further used to obtain weight parameters corresponding to each characteristic parameter in the operating characteristic parameters, wherein the weight parameters are used to characterize the importance of each characteristic parameter; and determine the equipment status evaluation value based on the operating characteristic parameters and the weight parameters.

[0121] The analysis module is also used to normalize each characteristic parameter in the operating characteristic parameter to obtain a normalized characteristic parameter; and to perform weighted summation on the normalized characteristic parameter and the weight parameter to determine the equipment status evaluation value.

[0122] Among them, the preset switchgear state prediction model includes a dimensionality reduction submodule and a state prediction submodule, and the output end of the state prediction submodule is connected to the input end of the dimensionality reduction submodule; the prediction module is also used to perform data dimensionality reduction processing on the operating characteristic parameters based on the dimensionality reduction submodule to obtain a one-dimensional feature vector; the state prediction submodule is used to predict the future equipment state of the gas-insulated switchgear based on the one-dimensional feature vector to obtain the equipment state prediction value.

[0123] Among them, the dimensionality reduction submodule at least includes a pooling layer and multiple convolutional layers, the input end of the pooling layer is connected to the output ends of the multiple convolutional layers, and the multiple convolutional layers are connected in series; the prediction module is also used to extract features of the operating characteristic parameters in sequence based on the multiple convolutional layers to obtain a convolution result, wherein the feature correlation degree of the data in the convolution result is greater than the feature correlation degree of the data in the operating characteristic parameters; the convolution result is pooled based on the pooling layer to obtain a one-dimensional feature vector.

[0124] Among them, the prediction module is also used to utilize the multi-head attention mechanism in the state prediction submodule to perform parallel self-attention calculation on the one-dimensional feature vector to obtain multiple self-attention calculation results; and splice multiple self-attention calculation results to obtain the device state prediction value.

[0125] An embodiment of the present application further provides an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of the present invention when running.

[0126] The above-mentioned memory may refer to a device inside a computer for storing data and programs, and may include memory, hard disk, etc., wherein the memory may be used to temporarily store running programs and data, the hard disk may be used to store programs and data for a long time, and the memory may be used to enable the computer to read and write data, and execute programs; the above-mentioned processor may be responsible for executing instructions in computer programs and performing data processing, and may be responsible for controlling and executing various operations, including arithmetic operations, logical operations, data transmission, etc.

[0127] An embodiment of the present application further provides a computer-readable storage medium, which includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0128] The above-mentioned computer storage medium may refer to a medium in a computer memory used to store certain discontinuous physical quantities. Computer storage media mainly include semiconductors, magnetic cores, magnetic drums, magnetic tapes, laser disks, etc.; the stored program included in the computer-readable storage medium may be a set of instructions that can be recognized and executed by a computer, running on an electronic computer, and is an information tool that meets certain needs of people.

[0129] An embodiment of the present application further provides a computer program product, including a computer program, which implements the methods in various embodiments of the present invention when executed by a processor.

[0130] The above-mentioned computer program product may refer to a software program that has been written, tested and released and can be run on a computer or other device. The computer program product may include an application, an operating system, tool software, etc., which is used to implement specific functions or solve specific problems.

[0131] An embodiment of the present application further provides a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0132] The above-mentioned non-volatile computer-readable storage medium may refer to a medium for storing data. The non-volatile computer-readable storage medium can keep the data from being lost when the power is off, and can be used to store long-term data, such as operating systems, applications, and user files. The non-volatile storage medium may include hard disk drives, solid-state drives, optical disks, and flash memory storage devices, etc.

[0133] The embodiments of the present application further provide a computer program, which implements the methods in the above-mentioned embodiments of the present invention when executed by a processor.

[0134] The above-mentioned computer program may refer to a collection of instructions used to tell a computer to perform a specific task or operation. A computer program may be written by a programmer using a specific programming language and may include algorithms, data structures, logic, and control flows. A computer program may be used for a variety of purposes, including application software, operating systems, and the like.

[0135] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0136] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0137] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0138] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0139] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0140] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for monitoring the state of a gas insulated switchgear, characterized in that: include: Acquiring operating characteristic parameters of a gas-insulated switchgear to be condition-monitored, wherein the operating characteristic parameters are used to characterize the operating condition of the gas-insulated switchgear; Performing hierarchical analysis on the operating characteristic parameters to obtain an equipment state evaluation value of the gas insulated switchgear, wherein the equipment state evaluation value is used to represent an evaluation value obtained by evaluating the current equipment state of the gas insulated switchgear based on the importance corresponding to each characteristic parameter in the operating characteristic parameters; Using a preset switchgear state prediction model to predict the future device state of the gas-insulated switchgear based on the operating characteristic parameters, and obtaining a device state prediction value of the gas-insulated switchgear; Based on the equipment state evaluation value and the equipment state prediction value, a state monitoring result of the gas insulated switchgear is determined.

2. The method for monitoring the state of a gas insulated switchgear according to claim 1, characterized in that: Performing hierarchical analysis on the operating characteristic parameters to obtain an equipment state evaluation value of the gas insulated switchgear includes: Obtaining a weight parameter corresponding to each characteristic parameter in the operating characteristic parameter, wherein the weight parameter is used to characterize the importance corresponding to each characteristic parameter; The device state evaluation value is determined based on the operating characteristic parameter and the weight parameter.

3. The method for monitoring the state of a gas insulated switchgear according to claim 2, characterized in that: Determining the device state evaluation value based on the operating characteristic parameter and the weight parameter includes: Normalizing each characteristic parameter in the operating characteristic parameter to obtain a normalized characteristic parameter; The normalized characteristic parameter and the weight parameter are weighted and summed to determine the device state evaluation value.

4. The method for monitoring the state of a gas insulated switchgear according to claim 1, characterized in that: The preset switchgear state prediction model includes a dimension reduction submodule and a state prediction submodule, wherein the output end of the state prediction submodule is connected to the input end of the dimension reduction submodule; using the preset switchgear state prediction model to predict the future device state of the gas-insulated switchgear based on the operating characteristic parameters, and obtaining the device state prediction value of the gas-insulated switchgear; including: Performing data dimensionality reduction processing on the operating characteristic parameter based on the dimensionality reduction submodule to obtain a one-dimensional feature vector; The state prediction submodule is used to predict the future device state of the gas insulated switchgear based on the one-dimensional feature vector to obtain the device state prediction value.

5. The method for monitoring the state of a gas insulated switchgear according to claim 4, characterized in that: The dimension reduction submodule at least includes a pooling layer and a plurality of convolutional layers, the input end of the pooling layer is connected to the output ends of the plurality of convolutional layers, and the plurality of convolutional layers are connected in series; The operating characteristic parameter is subjected to data dimensionality reduction processing based on the dimensionality reduction submodule to obtain a one-dimensional feature vector, including: Based on the multiple convolution layers, feature extraction is performed on the operating characteristic parameters in sequence to obtain a convolution result, wherein a feature correlation degree of data in the convolution result is greater than a feature correlation degree of data in the operating characteristic parameters; The convolution result is pooled based on the pooling layer to obtain the one-dimensional feature vector.

6. The method for monitoring the state of a gas insulated switchgear according to claim 4, characterized in that: Using the state prediction submodule to predict the future device state of the gas insulated switchgear based on the one-dimensional feature vector to obtain the device state prediction value includes: Utilizing the multi-head attention mechanism in the state prediction submodule, parallel self-attention calculation is performed on the one-dimensional feature vector to obtain multiple self-attention calculation results; The multiple self-attention calculation results are concatenated to obtain the device state prediction value.

7. A state monitoring device for a gas insulated switchgear, characterized in that: include: An acquisition module, used for acquiring operating characteristic parameters of a gas-insulated switchgear to be state-monitored, wherein the operating characteristic parameters are used for characterizing the operating status of the gas-insulated switchgear; An analysis module, used for performing hierarchical analysis on the operation characteristic parameters to obtain an equipment state evaluation value of the gas insulated switchgear, wherein the equipment state evaluation value is used to represent an evaluation value obtained by evaluating the current equipment state of the gas insulated switchgear based on the importance corresponding to each characteristic parameter in the operation characteristic parameters; A prediction module, configured to predict the future device state of the gas-insulated switchgear based on the operating characteristic parameters by using a preset switchgear state prediction model, and obtain a device state prediction value of the gas-insulated switchgear; A determination module is used to determine the state monitoring result of the gas insulated switchgear based on the equipment state evaluation value and the equipment state prediction value.

8. An electronic device, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein the program, when running, executes the condition monitoring method of the gas insulated switchgear according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the storage medium is located is controlled to execute the condition monitoring method for gas-insulated switchgear according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises a computer program, which, when executed by a processor, implements the condition monitoring method of a gas-insulated switchgear according to any one of claims 1 to 6.

Images