Method, device, equipment and medium for determining optimization strategy of electric field intensity of switchgear

Abstract

The present invention relates to the field of power electronics technology, and specifically discloses a method, device, equipment and medium for determining an electric field strength optimization strategy for a switchgear cabinet. The method includes: obtaining target data of a target component in the switchgear cabinet; wherein, the target data includes at least one of the following: average dielectric strength, average thermal resistance, average comprehensive mechanical strength, average insulation thickness and average frequency response; inputting the target data into an electric field strength optimization strategy model to obtain a corresponding optimization strategy; wherein, the optimization strategy includes at least one of the following: parameters to be adjusted for average dielectric strength, parameters to be adjusted for average thermal resistance, parameters to be adjusted for average comprehensive mechanical strength, parameters to be adjusted for average insulation thickness and parameters to be adjusted for average frequency response. By using the target data of the target component in the switchgear cabinet for different dimensions and the electric field strength optimization strategy model, the decision-making accuracy of the electric field strength optimization strategy can be improved.

Description

Technical Field

[0001] The present invention relates to the field of power electronics technology, and particularly to a method, device, equipment and medium for determining an optimization strategy for the electric field strength of a switch cabinet. Background Art

[0002] With the rapid development of the national power grid and the wide use of switch cabinets, switch cabinet accidents are not uncommon. Among them, insulation accidents are a very prominent factor in switch cabinet accidents. Since the switch cabinet operates under high electric field strength for a long time, local electric field distortion is serious, and faults such as surface flashover and breakdown are likely to occur, thus reducing the operation safety and reliability of the switch cabinet.

[0003] Existing methods for optimizing the electric field strength of switch cabinets have certain limitations. They often rely on fixed optimization strategies, and at the same time, the dimensions of the parameters affecting the electric field strength considered are less, unable to adapt to environmental changes and diverse application requirements, resulting in poor optimization effects of the electric field strength of the switch cabinet. Summary of the Invention

[0004] The present invention provides a method, device, equipment and medium for determining an optimization strategy for the electric field strength of a switch cabinet to solve the problem of poor optimization effect of the electric field strength in the existing methods.

[0005] According to one aspect of the present invention, there is provided a method for determining an optimization strategy for the electric field strength of a switch cabinet, the method comprising:

[0006] Obtaining target data of a target component in the switch cabinet; wherein the target data includes at least one of the following: average dielectric strength, average thermal resistance, average comprehensive mechanical strength, average insulation thickness and average frequency response; the target component includes at least one of the following switch components: load switch, circuit breaker switch and earthing switch;

[0007] Inputting the target data into an electric field strength optimization strategy model to obtain a corresponding optimization strategy; wherein the optimization strategy includes at least one of the following: parameters to be adjusted for the average dielectric strength, parameters to be adjusted for the average thermal resistance, parameters to be adjusted for the average comprehensive mechanical strength, parameters to be adjusted for the average insulation thickness and parameters to be adjusted for the average frequency response; the electric field strength optimization strategy model is obtained by adversarial training based on a dual deep Q-network with an attention mechanism.

[0008] According to another aspect of the present invention, there is provided a device for determining an optimization strategy for the electric field strength of a switch cabinet, the device comprising:

[0009] A data acquisition module for acquiring target data of a target component in a switchgear cabinet; wherein the target data includes at least one of the following: average dielectric strength, average thermal resistance, average comprehensive mechanical strength, average insulation thickness, and average frequency response; the target component includes at least one of the following switch components: load switch, circuit breaker switch, and earthing switch;

[0010] An optimization strategy determination module for inputting the target data into an electric field strength optimization strategy model to obtain a corresponding optimization strategy; wherein the optimization strategy includes at least one of the following: the parameter to be adjusted for the average dielectric strength, the parameter to be adjusted for the average thermal resistance, the parameter to be adjusted for the average comprehensive mechanical strength, the parameter to be adjusted for the average insulation thickness, and the parameter to be adjusted for the average frequency response; the electric field strength optimization strategy model is obtained through adversarial training based on a dual deep Q-network with an attention mechanism.

[0011] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising:

[0012] At least one processor; and

[0013] A memory communicatively connected to the at least one processor; wherein,

[0014] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the switchgear cabinet electric field strength optimization strategy determination method according to any embodiment of the present invention.

[0015] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the switchgear cabinet electric field strength optimization strategy determination method according to any embodiment of the present invention when executed.

[0016] In the technical solution of the embodiment of the present invention, target data of a target component in a switch cabinet is obtained; wherein, the target data includes at least one of the following: average dielectric strength, average thermal resistance, average comprehensive mechanical strength, average insulation thickness, and average frequency response; the target data is input into an electric field strength optimization strategy model to obtain a corresponding optimization strategy; wherein, the optimization strategy includes at least one of the following: parameters to be adjusted for average dielectric strength, parameters to be adjusted for average thermal resistance, parameters to be adjusted for average comprehensive mechanical strength, parameters to be adjusted for average insulation thickness, and parameters to be adjusted for average frequency response; the electric field strength optimization strategy model is obtained through adversarial training based on a dual deep Q-network with an attention mechanism. By obtaining the target data of the target component in the switch cabinet for different dimensions and then using the pre-trained electric field strength optimization strategy model to output the optimization strategy that can achieve the optimal electric field strength and insulation system margin in the current state of the switch cabinet, the technical solution solves the problem of poor optimization effect of the electric field strength in the existing method, improves the decision-making accuracy of the electric field strength optimization strategy, and further improves the operation safety and reliability of the switch cabinet.

[0017] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0019] Figure 1 is a flowchart of a method for determining an electric field strength optimization strategy for a switch cabinet according to Embodiment 1 of the present invention;

[0020] Figure 2 is a flowchart of a method for determining an electric field strength optimization strategy for a switch cabinet according to Embodiment 2 of the present invention;

[0021] Figure 3 is a training flowchart of an electric field strength optimization strategy model according to Embodiment 3 of the present invention;

[0022] Figure 4 is a dielectric strength distribution diagram according to Embodiment 3 of the present invention;

[0023] Figure 5 is a temperature distribution diagram according to Embodiment 3 of the present invention;

[0024] Figure 6 is a graph showing the variation of mechanical strength with electric field strength provided in Embodiment 3 of the present invention;

[0025] Figure 7 is a 3D surface map of the insulation layer thickness of the target component provided in Embodiment 3 of the present invention;

[0026] Figure 8 is a correlation heat map provided in Embodiment 3 of the present invention;

[0027] Figure 9 is a schematic diagram of the model structure and training provided in Embodiment 3 of the present invention;

[0028] Figure 10 is a schematic structural diagram of a device for determining an optimized strategy for the electric field strength of a switchgear cabinet provided in Embodiment 4 of the present invention;

[0029] Figure 11 is a schematic structural diagram of an electronic device for implementing the method for determining an optimized strategy for the electric field strength of a switchgear cabinet according to the embodiments of the present invention. Detailed Embodiments

[0030] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0031] 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 do not have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances 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 "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0032] Embodiment 1

[0033] Figure 1FIG. 0 is a flowchart of a method for determining an optimized strategy for the electric field intensity of a switchgear cabinet according to Embodiment 1 of the present invention. This embodiment is applicable to determining a corresponding optimized strategy for the electric field intensity according to target data of different dimensions of target components in the switchgear cabinet to assist a user (such as an operation and maintenance personnel) in optimizing the electric field intensity of the switchgear cabinet. This method can be executed by a device for determining an optimized strategy for the electric field intensity of the switchgear cabinet, which can be implemented in the form of hardware and / or software. The device for determining an optimized strategy for the electric field intensity of the switchgear cabinet can be configured in an electronic device, which can include, but is not limited to, devices with data processing capabilities such as a computer, a computer, a terminal, and a server. As Figure 1 shown, a method for determining an optimized strategy for the electric field intensity of a switchgear cabinet provided in Embodiment 1 specifically includes the following steps:

[0034] S110. Obtain target data of target components in the switchgear cabinet; wherein, the target data includes at least one of the following: average dielectric strength, average thermal resistance, average comprehensive mechanical strength, average insulation thickness, and average frequency response; the target components include at least one of the following switch components: load switch, circuit breaker switch, and grounding switch.

[0035] Among them, the target components may include, but are not limited to, various switches, operating mechanisms, current-carrying devices, etc. in the switchgear cabinet. In one embodiment, the target components include at least one of the following switch components: load switch, circuit breaker switch, and grounding switch.

[0036] The target data can be understood as multi-dimensional parameter data that will affect the electric field distribution and insulation system margin of the switchgear cabinet. The target data may include at least one of the following: average dielectric strength, average thermal resistance, average comprehensive mechanical strength, average insulation thickness, and average frequency response; wherein, the average dielectric strength is used to characterize the overall dielectric strength performance of multiple measurement points on the target component; the average thermal resistance is used to characterize the overall heat dissipation performance of multiple measurement points on the target component; the average comprehensive mechanical strength is used to characterize the overall mechanical strength and electric field distribution of multiple measurement points on the target component; the average insulation thickness is used to characterize the overall insulation layer thickness distribution of multiple measurement points on the target component; the average frequency response is used to characterize the overall frequency response distribution of multiple measurement points on the target component.

[0037] It can be understood that the target data may include parameter data of more dimensions in addition to the above-mentioned dimensions, and can be specifically set according to the actual application scenario and business requirements of the switchgear cabinet. The embodiments of the present invention do not limit this.

[0038] In an embodiment of the present invention, when it is necessary to optimize the electric field strength of a switchgear cabinet, for example, when a preset electric field strength optimization period is reached or an electric field strength optimization instruction from a user is received, target data of target components in the switchgear cabinet for different dimensions can be obtained, so that a corresponding electric field strength optimization strategy can be determined according to the above target data. The target data includes at least one of the following: average dielectric strength, average thermal resistance, average comprehensive mechanical strength, average insulation thickness, and average frequency response.

[0039] It can be understood that the number of selected target components and their distribution positions in the switchgear cabinet are not specifically limited in this embodiment, and can be set accordingly according to the actual application scenario and business requirements of the switchgear cabinet. Among them, the more the number of selected target components, the more accurate the finally determined electric field strength optimization strategy and the better the optimization effect; the distribution positions of the target components in the switchgear cabinet can be selected from, but not limited to, the following positions: the sharp corner positions of the switchgear cabinet (such as the edges of partitions, connection points of bus bridges, etc.), the positions of components directly exposed to the air (such as current-carrying devices), etc.

[0040] S120. Input the target data into the electric field strength optimization strategy model to obtain a corresponding optimization strategy; the optimization strategy includes at least one of the following: the parameter to be adjusted for the average dielectric strength, the parameter to be adjusted for the average thermal resistance, the parameter to be adjusted for the average comprehensive mechanical strength, the parameter to be adjusted for the average insulation thickness, and the parameter to be adjusted for the average frequency response; the electric field strength optimization strategy model is obtained through adversarial training based on a dual deep Q network with an attention mechanism.

[0041] Among them, the electric field strength optimization strategy model can be understood as a network model for determining a corresponding electric field strength optimization strategy according to the target data. The output optimization strategy can refer to the best action output by the electric field strength optimization strategy model in the current state, that is, the parameters to be adjusted corresponding to the target data in each dimension, so as to achieve the optimal goal of the electric field strength (as small as possible) and the insulation system margin (as large as possible) of the switchgear cabinet. The electric field strength optimization strategy model can be obtained in advance through adversarial training based on a dual deep Q network with an attention mechanism.

[0042] The Double Deep Q Network (DDQN), as a reinforcement learning algorithm, is an improvement and extension of the Deep Q Network (DQN), aiming to solve the problem of overestimation existing in the DQN model when estimating the Q value. The DDQN model consists of an evaluation network and a target network with the same network structure but different network parameters. Its basic idea is to separate the selection and evaluation of actions, that is, the evaluation network is used to select the best action, and the target network is used to estimate the Q value of this action, so as to reduce the impact of overestimation.

[0043] The attention mechanism is a mechanism that enables the model to focus on important information in the input features. By adaptively adjusting the model's attention to different features, the model can concentrate on the information most relevant to the current task, improve the model's ability to capture key features, and thereby enhance the decision-making accuracy of the model.

[0044] Adversarial training refers to a training method that can improve the robustness of the model. By introducing adversarial samples during the model training process, it forces the model to learn how to identify and resist the influence of adversarial samples, thereby enhancing the robustness and generalization ability of the model. Among them, adversarial samples refer to samples that cause the model to make incorrect decisions by adding tiny perturbations to the original sample data. Such perturbations are usually imperceptible to humans but have a serious impact on the model.

[0045] In the embodiment of the present invention, after obtaining the target data of the target component in the switch cabinet for different dimensions, it can be input into the pre-trained electric field strength optimization strategy model. Using this model to decide the best actions that the switch cabinet can achieve the optimal electric field strength and insulation system margin in the current state, that is, the adjustment parameters corresponding to the target data of each dimension. Then, each adjustment parameter is used as the final optimization strategy. Subsequently, the user can adjust the relevant parameters of the switch cabinet based on this optimization strategy, such as adjusting the insulating material, optimizing the heat dissipation structure, improving the mechanical design, etc., to achieve the goal of optimizing the electric field strength and enhancing the insulation system margin, thereby improving the operation safety and reliability of the switch cabinet.

[0046] The technical solution of the embodiment of the present invention includes obtaining the target data of the target component in the switch cabinet; where the target data includes at least one of the following: average dielectric strength, average thermal resistance, average comprehensive mechanical strength, average insulation thickness, and average frequency response; the target component includes at least one of the following switch components: load switch, circuit breaker switch, and grounding switch; inputting the target data into the electric field strength optimization strategy model to obtain the corresponding optimization strategy; where the optimization strategy includes at least one of the following: adjustment parameters of the average dielectric strength, adjustment parameters of the average thermal resistance, adjustment parameters of the average comprehensive mechanical strength, adjustment parameters of the average insulation thickness, and adjustment parameters of the average frequency response; the electric field strength optimization strategy model is obtained by adversarial training based on the attention mechanism double deep Q network. This technical solution solves the problem of poor electric field strength optimization effect in the existing methods by obtaining the target data of the target component in the switch cabinet for different dimensions and then using the pre-trained electric field strength optimization strategy model to output the optimization strategy that the switch cabinet can achieve the optimal electric field strength and insulation system margin in the current state, improves the decision-making accuracy of the electric field strength optimization strategy, and thereby improves the operation safety and reliability of the switch cabinet.

[0047] Embodiment Two

[0048] Figure 2 This is a flowchart of a method for determining an optimized strategy for the electric field strength of a switchgear cabinet provided in the second embodiment of the present invention. It is further optimized and extended based on the above-described embodiment and can be combined with various optional technical solutions in the above-described embodiment. As Figure 2 shown, a method for determining an optimized strategy for the electric field strength of a switchgear cabinet provided in the second embodiment specifically includes the following steps:

[0049] S210. Obtain the target data of the target component in the switchgear cabinet.

[0050] In the embodiment of the present invention, the target data corresponding to the target component can be found from preset data storage locations such as, but not limited to, a database, an Excel file, etc. according to identification information such as the number of the target component, and the target data includes at least one of the following: average dielectric strength, average thermal resistance, average comprehensive mechanical strength, average insulation thickness, and average frequency response.

[0051] Among them, the average dielectric strength is the average value of the dielectric strengths corresponding to multiple measurement points on the target component. The dielectric strength is determined by the breakdown voltage collected at the corresponding measurement points and the insulation layer thickness of the target component. The breakdown voltage and the insulation layer thickness of the target component are respectively collected by an electrode test device and a thickness measurement device.

[0052] Specifically, measurement points can be set at different positions on the target component, and the positions of the measurement points can be evenly distributed on the target component according to actual needs, or several positions can be randomly selected as measurement points. This embodiment does not limit this. The breakdown voltage of each measurement point and the insulation layer thickness of the target component can be respectively collected by using an electrode test device and a thickness measurement device, and then the following formula is called to determine the dielectric strength of each measurement point:

[0053]

[0054] In the formula, represents the dielectric strength of the i-th measurement point, with the unit of kV / mm; represents the breakdown voltage of the i-th measurement point, with the unit of kV; represents the insulation layer thickness of the target component at the i-th measurement point, with the unit of mm; represents the electric field uniformity factor.

[0055] Finally, the average value of the dielectric strengths corresponding to all measurement points is used as the average dielectric strength.

[0056] Further, the average thermal resistance is the average of the thermal resistances corresponding to multiple measurement points on the target component. The thermal resistance is determined by the heating power applied at the corresponding measurement points and the collected temperature difference. The heating power is collected by the thermal test device, and the initial temperature and the final temperature corresponding to the temperature difference are collected by the infrared thermal imager.

[0057] Specifically, the corresponding heat can be applied to the target component by setting the heating power of the thermal test device, and then the temperature differences (the difference between the initial temperature and the final temperature) of each measurement point are respectively collected by the infrared thermal imager. Then, the following formula is called to determine the thermal resistance of each measurement point:

[0058]

[0059] In the formula, represents the thermal resistance of the i-th measurement point, with the unit of K / W (Kelvin / Watt); represents the temperature difference of the i-th measurement point, with the unit of K (Kelvin); P represents the heating power, with the unit of W.

[0060] Finally, the average of the thermal resistances corresponding to all measurement points is used as the average thermal resistance.

[0061] Further, the average comprehensive mechanical strength is the average of the comprehensive mechanical strengths corresponding to multiple measurement points on the target component. The comprehensive mechanical strength is determined by the actual stress and the electric field strength collected at the corresponding measurement points. The actual stress and the electric field strength are respectively collected by the stress sensor and the electric field sensor.

[0062] Specifically, mechanical stress and voltage can be applied to the target component by using the stress test device and the electric field generator respectively, and then the actual stress and the electric field strength of each measurement point are respectively collected by the stress sensor and the electric field sensor. Then, the following formula is called to determine the comprehensive mechanical strength of each measurement point:

[0063]

[0064] In the formula, represents the comprehensive mechanical strength of the i-th measurement point, with the unit of N / mm 2 ; represents the actual stress of the i-th measurement point, with the unit of N / mm 2 ; represents the electric field strength of the i-th measurement point, with the unit of kV / mm; represents the elastic modulus of the material of the target component, with the unit of N / mm 2 ; represents the temperature of the i-th measurement point, with the unit of °C; represents the dielectric constant; k 1 -k 5 respectively represent the regression coefficients; Represents a constant.

[0065] Finally, the average value of the comprehensive mechanical strength corresponding to all measurement points is used as the average comprehensive mechanical strength.

[0066] Furthermore, the average insulation thickness is the average value of the insulation layer thicknesses of the target component corresponding to multiple measurement points on the target component, and the insulation thickness is acquired by a thickness measuring device.

[0067] Specifically, the thickness measuring device can be used to acquire the insulation layer thicknesses of the target component at each measurement point on the target component, and then the average value of the insulation layer thicknesses of the target component corresponding to all measurement points is used as the average insulation thickness.

[0068] Furthermore, the average frequency response is the average value of the frequency responses corresponding to multiple measurement points on the target component, and the frequency response is acquired by a frequency response analyzer.

[0069] Specifically, by applying a frequency to the target component using a frequency response analyzer, the frequency response (value) at each measurement point can be obtained, and then the average value of the frequency responses corresponding to all measurement points is used as the average frequency response.

[0070] S220. Preprocess the target data to obtain normalized target data, and input the normalized target data into the convolutional neural network layer to extract the target feature representation corresponding to the normalized target data.

[0071] In the embodiments of the present invention, a pre-trained electric field strength optimization strategy model can be obtained from a storage location such as a local or cloud server, and the model is deployed to the actual switchgear application environment to ensure that it can process and optimize the electric field strength and insulation system margin in real time. At the same time, the computational efficiency and hardware compatibility of the model need to be considered during the deployment process to ensure that the model can operate efficiently in actual applications. The electric field strength optimization strategy model specifically includes: a convolutional neural network layer, an attention layer, a target network, and an evaluation network. Among them, the convolutional neural network layer is used to extract the high-dimensional representation of the input features (i.e., target data in different dimensions) to enhance the expression ability of the model; the attention layer is used to adaptively adjust the model's attention to different features, enabling the model to focus on the information most relevant to the current task, improving the model's ability to capture key features, and thus enhancing the decision-making accuracy of the model; the target network and the evaluation network are used to decide the best actions that the switchgear can achieve the optimal electric field strength and insulation system margin in the current state.

[0072] Specifically, preprocessing operations such as noise anomaly removal, missing value filling, and normalization processing can be sequentially performed on the obtained target data to obtain the normalized target data after preprocessing. Then, by inputting the normalized target data into the convolutional neural network layer in the electric field strength optimization strategy model for multiple iterations, the target feature representation corresponding to the normalized target data can be extracted. Among them, the convolutional neural network layer can be expressed as follows:

[0073]

[0074] In the formula, represents the output after the convolution operation; x represents the input feature, that is, the multi-dimensional target data; W represents the convolution kernel weight; b represents the bias; ReLU represents the activation function.

[0075] S230. Input the target feature representation into the attention layer, and output the target attention matrix corresponding to the target feature representation.

[0076] In the embodiment of the present invention, the target feature representation output by the convolutional neural network layer can be used as the input of the attention layer in the electric field strength optimization strategy model. By calculating the similarity scores between the three matrices of query (Query), key (Key), and value (Value), and normalizing these scores to obtain the attention weights, the model can perform weighted processing on the input features (the target feature representation output by the convolutional neural network layer) according to these weights, so as to form attention to specific information and output the corresponding target attention matrix. Among them, the target attention matrix output by the attention layer can be expressed as follows:

[0077]

[0078] In the formula, Q represents the query matrix; K represents the key matrix, represents the transpose of the matrix K; V represents the value matrix; represents the dimension of the key matrix; softmax represents the normalization function.

[0079] S240. Process the target attention matrix by using the target network and the evaluation network, output the adjustment parameters corresponding to each target data respectively, and use each adjustment parameter as the optimization strategy.

[0080] Among them, the adjustment parameters may include the adjustment amounts or adjustment weights corresponding to the target data in each dimension, etc.

[0081] In the embodiments of the present invention, since after the model training is completed, the target network and the evaluation network have learned how to select the best action according to the current state to maximize the cumulative reward, the attention matrix containing the correlations between the input features can be input into the target network and the evaluation network respectively for decision-making processing, so as to output the best action that can achieve the optimal electric field strength and insulation system margin of the switchgear under the current state, that is, the adjustment parameters corresponding to the respective target data, such as the adjustment amount or the adjustment weight, and use the respective adjustment parameters as the final optimization strategy for optimizing the electric field strength of the switchgear.

[0082] Among them, the best action output by the model can be expressed as:

[0083]

[0084] In the formula, represents the current state the best action selected under; represents the Q value corresponding to taking action a in state under.

[0085] Furthermore, on the basis of the above-mentioned embodiments of the invention, after obtaining the adjustment parameters for each target data output by the model, the processing results between each target data and the corresponding adjustment parameters can also be used as the final optimization strategy. Exemplarily, if the adjustment parameter is the adjustment amount corresponding to each target data, the sum of each target data and the corresponding adjustment amount can be used as the final optimization strategy for optimizing the electric field strength of the switchgear; if the adjustment parameter is the adjustment weight corresponding to each target data, the product of each target data and the corresponding adjustment weight can be used as the final optimization strategy for optimizing the electric field strength of the switchgear.

[0086] Furthermore, the user can dynamically adjust the relevant parameters of the switchgear according to the optimization strategy output by the model, such as adjusting the insulation material and thickness, optimizing the heat dissipation structure, improving the mechanical design, improving the manufacturing process, etc., so as to achieve the goal of optimizing the electric field strength and improving the insulation system margin, thereby improving the operation safety and reliability of the switchgear.

[0087] Furthermore, on the basis of the above-mentioned embodiments of the invention, after the electric field strength optimization strategy model is deployed to the actual switchgear application environment, the performance of the model can be monitored regularly to ensure its continuous optimization effect in actual applications. If it is found that the model performance deteriorates or the environment changes, the model needs to be retrained or fine-tuned to adapt to the new application scenario. Among them, the model performance can be expressed as follows:

[0088]

[0089] Wherein, Performance represents the average performance of the model; represents the reward for each decision; represents the total number of decisions. If the average performance Performance of the model is lower than the preset performance threshold, the model needs to be retrained or fine-tuned.

[0090] The technical solution of the embodiment of the present invention obtains the target data of the target component in the switch cabinet; preprocesses the target data to obtain the normalized target data, and inputs the normalized target data into the convolutional neural network layer to extract the target feature representation corresponding to the normalized target data; inputs the target feature representation into the attention layer to output the target attention matrix corresponding to the target feature representation; uses the target network and the evaluation network to process the target attention matrix, outputs the parameters to be adjusted corresponding to each target data respectively, and uses each parameter to be adjusted as an optimization strategy. This technical solution takes the multi-dimensional parameters that affect the electric field strength of the switch cabinet as data input, and then uses the pre-trained electric field strength optimization strategy model to process the target data of different dimensions, so as to output the optimization strategy that can achieve the optimal electric field strength and insulation system margin in the current state of the switch cabinet, solves the problem of poor electric field strength optimization effect in the existing methods, improves the decision-making accuracy of the electric field strength optimization strategy, and further improves the operation safety and reliability of the switch cabinet, ensuring the stability and efficiency of the system.

[0091] Embodiment III

[0092] Figure 3 is a training flow chart of an electric field strength optimization strategy model provided by Embodiment III of the present invention. As Figure 3 shown, the training process of the electric field strength optimization strategy model includes the following steps:

[0093] S310. Obtain the historical data of the target component.

[0094] In the embodiment of the present invention, the historical data of the target component for different dimensions can be obtained from preset data storage locations such as, but not limited to, databases and Excel files; wherein, the historical data includes at least one of the following: average dielectric strength historical data, average thermal resistance historical data, average comprehensive mechanical strength historical data, average insulation thickness historical data, and average frequency response historical data. The acquisition processes of the historical data of each dimension are introduced separately below:

[0095] ① Collect average dielectric strength historical data

[0096] First, prepare the target component and experimental equipment. Ensure that the surface of the target component is clean and free of impurities, place the target component in the electrode test device, ensure that the target component is in close contact with the electrode plate, and set measurement points at different positions on the target component.

[0097] Then, voltage application and breakdown detection are carried out. By gradually increasing the voltage applied to the target component and recording the changes on the surface of the target component in real time until the target component breaks down. Record the breakdown voltage of each measurement point and the thickness of the insulating layer of the target component, and determine the dielectric strength of each measurement point according to the breakdown voltage and the thickness of the insulating layer of the target component .

[0098] Next, data augmentation techniques can be used to generate more samples to solve the problem of small samples, while increasing the diversity of sample data, thereby improving the generalization ability of the model. Specifically, the data augmentation model can be used to simulate different test environments of the target component, and output the breakdown voltage and the thickness of the insulating layer of the target component after n times of data augmentation simulation experiments for each measurement point (n also represents the number of samples of the subsequent model). Then, the average value of the enhanced dielectric strength obtained in the jth ( ) data augmentation simulation experiment is determined by calling the following formula:

[0099]

[0100] In the formula, represents the average value of the enhanced dielectric strength obtained in the jth data augmentation simulation experiment, with the unit of kV / mm; m represents the number of measurement points; represents the breakdown voltage obtained at the ith measurement point in the jth data augmentation simulation experiment, with the unit of kV; represents the thickness of the insulating layer of the target component obtained at the ith measurement point in the jth data augmentation simulation experiment, with the unit of mm; represents the electric field uniformity factor of the jth data augmentation simulation experiment.

[0101] After the above data augmentation processing, the average value of the enhanced dielectric strength of the n times of data augmentation simulation experiments corresponding to the target component can be used as the historical data of the average dielectric strength, that is, n sample data are obtained.

[0102] Furthermore, before using the dielectric strength as the influencing parameter of the electric field strength of the switchgear, the frequency distribution of the dielectric strength can be determined through the following data analysis process, so as to understand the influence of the dielectric strength on the electric field strength of the switchgear. The weighted standard deviation combined with the attention mechanism can be used to assign weights to different samples and calculate the dispersion degree of the experimental data:

[0103]

[0104] In the formula, represents the weighted standard deviation, with the unit of kV / mm; It represents the attention weight of the j-th sample, reflecting the importance of this sample in the overall data.

[0105] Figure 4 It is the dielectric strength distribution map after multiple experiments and data augmentation. This map shows the dielectric strength distribution of the sample data. Among them, the horizontal axis represents the dielectric strength (unit: kV / mm), and the vertical axis represents the frequency. Through this map, the overall distribution and central tendency of the dielectric strength data can be intuitively observed, and the dielectric strength performance of the target component under different experimental conditions can be understood, so as to evaluate its stability and reliability.

[0106] ②Collect historical data of average thermal resistance

[0107] First, ensure that the surface of the target component is clean and free of impurities, and fix the target component in the thermal test device. Use an infrared thermal imager to arrange multiple measurement points on the surface of the target component to ensure that the temperature distribution on the surface of the target component can be comprehensively captured.

[0108] Then conduct a heating experiment and real-time monitoring. Use a high-precision heat source device to gradually increase the power applied to the target component, and at the same time, use an infrared thermal imager to monitor the temperature distribution on the surface of the target component in real time. Record the temperature changes (temperature differences) and heating power of each measurement point, and determine the thermal resistance of each measurement point according to the heating power and temperature difference 。

[0109] Next, perform data processing and data augmentation on the collected data. An automated data acquisition system can be used to continuously record the temperature data of each measurement point and conduct preliminary analysis through data processing software. In order to improve the accuracy and diversity of the data, data augmentation techniques are used to generate more samples. For example, by simulating temperature changes under different environmental conditions to expand the dataset, it is determined that the average enhanced thermal resistance obtained in the j-th data augmentation simulation experiment is:

[0110]

[0111] In the formula, represents the average enhanced thermal resistance obtained in the j-th data augmentation simulation experiment, with the unit of K / W; represents the temperature difference obtained by the i-th measurement point in the j-th data augmentation simulation experiment; represents the heating power obtained in the j-th data augmentation simulation experiment.

[0112] After the above data augmentation processing, the average enhanced thermal resistance of the n data augmentation simulation experiments corresponding to the target component can be used as the historical data of the average thermal resistance, that is, n sample data are obtained.

[0113] Further, before taking the average thermal resistance as the parameter affected by the electric field strength, the key factors affecting the heat dissipation performance can be determined through the following data analysis process. Big data analysis and machine learning algorithms can be used to deeply analyze the collected temperature data. Through cluster analysis and regression modeling, the key factors affecting the heat dissipation performance are identified, and a prediction model is established:

[0114]

[0115] In the formula, represents the standard deviation, with the unit of K / W.

[0116] Figure 5 is the temperature distribution map generated by recording the temperature data of different temperature measurement points on the surface of the target component through an infrared thermal imager. This map shows the temperature distribution on the surface of the sample data during the heating process, and different colors represent different temperature ranges. Through this map, the temperature differences in each area on the surface of the target component can be intuitively observed, and then the heat dissipation performance and heat conduction characteristics of the target component can be analyzed.

[0117] ③ Collect historical data of the average comprehensive mechanical strength

[0118] First, fix the target component in the stress test device, and arrange high-precision stress sensors and electric field sensors at different positions of the target component to ensure that the conditions of the target component under different mechanical stresses and electric fields can be comprehensively captured.

[0119] Then, apply mechanical stress and electric field. Gradually increase the pressure applied to the target component through the automated loading system, and at the same time apply an electric field through the electric field generator. Record the stress changes and electric field strength at each measurement point in real time. Among them, the actual stress corresponding to each measurement point can be expressed as follows:

[0120]

[0121] In the formula, represents the actual stress at the i-th measurement point, with the unit of N / mm 2 ; represents the mechanical stress (pressure) applied to the i-th measurement point; represents the cross-sectional area of the i-th measurement point, with the unit of mm 2 ; represents the angle between the stress direction and the normal direction corresponding to the i-th measurement point.

[0122] The electric field strength corresponding to each measurement point can be expressed as follows:

[0123]

[0124] In the formula, represents the electric field strength at the i-th measurement point, with the unit of kV / mm; V represents the applied voltage, with the unit of kV; represents the electrode spacing at the i-th measurement point, with the unit of mm; represents the dielectric constant.

[0125] Afterwards, an automated data acquisition system can be used to continuously record the data collected by the stress sensors and electric field sensors, and preliminary analysis can be carried out through data processing software. The comprehensive mechanical strength of each measurement point is expressed as follows:

[0126]

[0127] Similarly, data augmentation techniques can also be used to generate more samples, and the average value of the enhanced comprehensive mechanical strength of the n-fold data augmentation simulation experiments corresponding to the target component is used as the average comprehensive mechanical strength historical data.

[0128] Further, before taking the comprehensive mechanical strength as the electric field strength influence parameter, the key factors affecting the mechanical strength and electric field distribution can be determined through the following data analysis process. Through multiple experiments, the average value of the comprehensive mechanical strength can be calculated, the key factors affecting the mechanical strength and electric field distribution can be found, and a prediction model can be established:

[0129]

[0130] In the formula, represents the average value of the comprehensive mechanical strength, with the unit of N / mm 2 .

[0131] Figure 6 is the curve graph of the mechanical strength varying with the electric field strength. This graph shows the mechanical strength distribution of the target component material under different electric field strength conditions. Through analysis, the influence relationship between the electric field strength and the mechanical strength can be observed. Specifically, the horizontal axis represents the electric field strength (unit: kV / mm), and the vertical axis represents the mechanical strength (unit: N / mm 2 ), and the curve in the graph shows the change trend of the mechanical strength of the target component material under different electric field strengths. Through this graph, the influence of the electric field on the mechanical properties of the target component material can be intuitively analyzed, which helps to optimize the performance of the target component material in practical applications.

[0132] ④ Collect historical data of the average insulation thickness

[0133] First, ensure that the surface of the target component is clean and free of impurities, and use a high-precision ultrasonic thickness gauge or optical microscope to measure the insulation layer thickness of the target component. Measurement points are arranged at different positions of the target component to ensure that the insulation layer thickness distribution of the target component can be comprehensively captured.

[0134] Then, the insulation layer thickness measurement is carried out. The ultrasonic thickness gauge is used to gradually scan each measurement point on the surface of the target component, and the insulation layer thickness of each measurement point is recorded. Similarly, data augmentation techniques can be used to generate more samples, obtain the average insulation thickness of the augmented data, and use the average insulation thickness of the augmented data as the historical data of the average insulation thickness.

[0135] Furthermore, before using the average insulation thickness as the influence parameter of the electric field strength, the key factors affecting the insulation thickness can be determined through the following data analysis process. By comparing the thickness data of each measurement point, the thickness uniformity of the target component is evaluated:

[0136]

[0137] In the formula, represents the standard deviation of the insulation layer thickness, with the unit of mm; m represents the total number of measurement points; represents the insulation layer thickness of the target component at the i-th measurement point, with the unit of mm; represents the average insulation thickness of the augmented data, with the unit of mm.

[0138] Through cluster analysis and regression modeling, the key factors affecting the insulation thickness are found, and a prediction model is established. Figure 7 is the 3D surface map of the insulation layer thickness of the target component, which shows the insulation layer thickness distribution of the target component at different measurement points. Through Figure 7 the different color regions in, the differences in the insulation layer thickness at each position on the surface of the target component can be visually observed. Among them, the horizontal axis and the vertical axis respectively represent the X position and the Y position (i.e., the position coordinates) of the target component, and the Z axis represents the insulation layer thickness (unit: mm). Based on Figure 7 it can help analyze the insulation layer thickness uniformity of the target component and evaluate the insulation performance of the material, thereby helping to optimize the manufacturing process and improve the product quality.

[0139] ⑤Collect historical data of average frequency response

[0140] First, the frequency response analyzer is used to gradually increase the frequency applied to the target component, and the frequency response values of each measurement point are recorded, such as the dielectric constant, loss factor, etc.

[0141]

[0142] In the formula, represents the frequency response value at the i-th measurement point; represents the frequency applied at the i-th measurement point, with the unit of Hz; represents the response amplitude; t represents time; represents the phase.

[0143] Similarly, data augmentation techniques can also be used to generate more samples, and the average of the enhanced frequency responses of the n - time data augmentation simulation experiments corresponding to the target component is obtained as the average frequency response historical data.

[0144] Furthermore, before using the frequency response value as the electric - field - strength influence parameter, the key factors affecting the frequency response can be determined through the following data - analysis process. The response data of the target component at different frequencies can be analyzed by Fourier transform to evaluate the influence of frequency on the performance of the target component:

[0145]

[0146] In the formula, represents the response function in the frequency domain; represents the response value in the time domain.

[0147] Finally, in - depth analysis is performed on the collected frequency - response data. Through cluster analysis and regression modeling, the key factors affecting the frequency response are found, and a prediction model is established:

[0148]

[0149] In the formula, represents the predicted frequency - response value; represents the temperature at the i - th measurement point; represents the pressure at the i - th measurement point, with the unit of Pa; represents the permittivity at the i - th measurement point; NN represents the neural - network model.

[0150] Figure 8 is the correlation heat map of the influence of relevant factors on the frequency response. This figure shows the correlations between various factors, including frequency, temperature, pressure, permittivity, and (frequency) response value. Through the colors and values in the figure, the correlation degrees between these factors can be intuitively observed. The horizontal axis and the vertical axis respectively represent different factors. The redder the color (the greater the correlation), the stronger the positive correlation, and the bluer the color (the smaller the correlation), the stronger the negative correlation. Through this figure, it can be found that there is a strong positive correlation between frequency and response value, while the correlations between other factors are relatively weak.

[0151] S320. Pre - process the historical data to obtain normalized historical data.

[0152] In the embodiments of the present invention, the obtained historical data can be successively subjected to noise - anomaly elimination, missing - value filling, and standardization processing to obtain the pre - processed normalized historical data. Among them, the data - standardization formula is as follows:

[0153]

[0154] In the formula, X represents the standardized data; x represents the original data; represents the average value of the original data; represents the standard deviation of the original data; max(X) and min(X) respectively represent the maximum and minimum values of the standardized data; n represents the number of samples.

[0155] S330. Perform feature mapping encoding on the normalized historical data to obtain a normalized data set.

[0156] In the embodiment of the present invention, feature mapping encoding can be performed on the normalized historical data to obtain a corresponding normalized data set, that is, map the historical data of each dimension to specific values to ensure that all states and factors can be accurately encoded and analyzed. The specific mapping method is as follows: {average dielectric strength: 1, average thermal resistance: 2, average comprehensive mechanical strength: 3, average insulation thickness: 4, average frequency response: 5}. Through this mapping method, it can be ensured that each feature has a unique encoding, which is convenient for subsequent data analysis and model training.

[0157] S340. Divide the normalized data set into a training set, a validation set, and a test set according to a preset data set splitting ratio, and initialize and construct an initial model of the electric field strength optimization strategy.

[0158] In the embodiment of the present invention, the above-mentioned normalized data set can be divided into a training set, a validation set, and a test set according to a preset data set splitting ratio of 70%:15%:15%, and initialize the initial model of the electric field strength optimization strategy that needs to be trained to initialize the model parameters; among them, the electric field strength optimization strategy model includes: a convolutional neural network layer, an attention layer, a target network, and an evaluation network. It can be understood that the above-mentioned preset data set splitting ratio is only an example, and other splitting ratios can also be adopted in practical applications, such as 6:3:1, etc., and this embodiment does not limit this.

[0159] S350. Add adversarial perturbations to the sample data of the training set and the validation set, and train the initial model of the electric field strength optimization strategy according to the training set and the validation set to obtain a basic model of the electric field strength optimization strategy.

[0160] In the embodiment of the present invention, in order to enhance the robustness and generalization ability of the model, this embodiment introduces an adversarial training technology, that is, add small perturbations to the sample data of the training set and the validation set, and then use the training set and the validation set with perturbations to train the initial model of the electric field strength optimization strategy, so as to obtain the corresponding basic model of the electric field strength optimization strategy (not tested by the model). Among them, the adversarial training can be expressed as follows:

[0161]

[0162] In the formula, represents the adversarial loss; represents the expectation under the joint distribution of state s and action a; represents the policy; represents the Q value corresponding to taking action a in state s; represents the adversarial perturbation; represents the perturbation set.

[0163] By adding adversarial perturbations during the model training process to simulate possible attacks or environmental changes, the performance of the model in the face of unknown and changing environments can be enhanced.

[0164] Further, on the basis of the above-mentioned invention embodiments, S350 specifically includes the following steps:

[0165] S3501. Input the sample data in the training set into the convolutional neural network layer of the initial model of the electric field strength optimization strategy respectively, and extract the sample feature representations corresponding to the respective sample data;

[0166] S3502. Input the respective sample feature representations into the attention layer of the initial model of the electric field strength optimization strategy respectively, and obtain the sample attention matrices corresponding to the respective sample feature representations;

[0167] S3503. Use the respective sample attention matrices as the states in the state space corresponding to the target network and the evaluation network of the initial model of the electric field strength optimization strategy, and obtain the action space and the reward function corresponding to the configuration of the initial model of the electric field strength optimization strategy;

[0168] S3504. Select a state from the state space as the current state, and select the current action in the action space based on the current state using a preset dynamic exploration strategy, so as to interact with the environment according to the current action to obtain an updated state;

[0169] S3505. Determine the updated action according to the updated state through the evaluation network; wherein, the updated action is used to interact with the environment to obtain a new updated state;

[0170] S3506. Determine the actual Q value corresponding to the current state and the current action through the evaluation network and the reward function;

[0171] S3507. Determine the target Q value corresponding to the updated state and the updated action through the target network;

[0172] S3508. Update the network parameters of the evaluation network according to the loss function values corresponding to the actual Q value and the target Q value;

[0173] S3509. Copy the network parameters of the evaluation network to the target network every preset time period;

[0174] S35010. When the number of model iterations of the initial model of the electric field strength optimization strategy reaches the preset number of iterations, or when the value of the loss function reaches the preset threshold, use the current initial model of the electric field strength optimization strategy as the target model of the electric field strength optimization strategy.

[0175] S35011. Use the validation set to verify the target model of the electric field strength optimization strategy, and adjust the model parameters until the target model of the electric field strength optimization strategy meets the preset model verification index, so as to obtain the trained basic model of the electric field strength optimization strategy.

[0176] In the embodiments of the present invention, each action in the action space includes at least one of the following: the adjustment parameter for adjusting the average dielectric strength, the adjustment parameter for adjusting the average thermal resistance, the adjustment parameter for adjusting the average comprehensive mechanical strength, the adjustment parameter for adjusting the average insulation thickness, and the adjustment parameter for adjusting the average frequency response. Among them, the adjustment parameter can be an adjustment amount or an adjustment weight. Exemplarily, the action can be represented in the following form: {(1, the adjustment parameter for adjusting the average dielectric strength); (2, the adjustment parameter for adjusting the average thermal resistance); (3, the adjustment parameter for adjusting the average comprehensive mechanical strength); (4, the adjustment parameter for adjusting the average insulation thickness); (5, the adjustment parameter for adjusting the average frequency response)}, where 1, 2, 3, 4, and 5 are the mapping values corresponding to the respective electric field strength influence parameters after the above-mentioned feature mapping encoding.

[0177] Based on the goal of reducing the electric field strength and increasing the margin of the insulation system, the following reward function can be designed:

[0178]

[0179] In the formula, represents the reward value corresponding to taking action a in state s; A represents the average dielectric strength; B represents the average thermal resistance; C represents the average comprehensive mechanical strength; D represents the average insulation thickness; E represents the average frequency response; , , , and are the weights of the respective electric field strength influence parameters, specifically as follows:

[0180] : The average dielectric strength should be maximized (positive weight);

[0181] : The average thermal resistance should be minimized (negative weight);

[0182] : The average comprehensive mechanical strength should be maximized (positive weight);

[0183] : The average insulation thickness should be maximized (positive weight);

[0184] : The average frequency response should be minimized (negative weight).

[0185] See Figure 9 , the specific training process of the model is as follows:

[0186] In the embodiments of the present invention, a prioritized experience replay mechanism can be used to train the initial model of the electric field strength optimization strategy. Each state in the state space is respectively input into the evaluation network that stores and estimates the Q value in the experience replay buffer. The evaluation grid outputs the current action according to the preset dynamic exploration strategy network, i.e., the ε-greedy strategy into the environment. On the one hand, the state of the environment changes from to (i.e., update the state). On the other hand, the environment will immediately feedback the reward corresponding to the action to the experience replay buffer of the agent according to the reward function. When a certain number of experience samples are stored in the experience replay buffer, a small batch of samples are extracted from the experience replay buffer by using the prioritized experience replay mechanism and input into the evaluation network and the target network respectively. The target network outputs the target Q value corresponding to the updated state . After adding it to the current reward in the experience sample, the root mean square value is calculated together with the actual Q value output by the evaluation network, which is the loss function value of the network. The loss function value is fed back to the evaluation network, and the network parameters of the evaluation network are updated according to the principle of minimizing the loss and by using the gradient descent method, so that the output action can obtain the maximum cumulative reward. This process will be repeated in each training episode until the final convergence or the preset number of training rounds is reached, that is, the preset model training termination condition is satisfied. At the same time, during the model training process, the network parameters of the evaluation network will be periodically copied to the target network, so as to slow down the update frequency of the parameters, stabilize the training process, and prevent the model from falling into a local optimal solution.

[0187] Among them, the calculation formula of the Q value is as follows:

[0188]

[0189] In the formula, represents the Q value corresponding to taking action a in state s; r represents the reward value; represents the discount factor; represents the target Q value corresponding to taking the best action in the updated state (the next state).

[0190] By introducing a prioritized experience replay mechanism, the training frequency of important samples is increased. In the experience replay buffer, the following formula is used:

[0191]

[0192] In the formula, represents the priority of sample j; represents the TD error of sample j (the difference between the target Q value and the current actual Q value); represents a small constant used to avoid the case where the priority is zero. By introducing the prioritized experience replay mechanism, it can be ensured that high-priority samples are trained more frequently, thereby improving the learning efficiency and effect of the model.

[0193] By using the experience replay buffer to store and reuse past experience samples, the utilization efficiency of samples is improved:

[0194]

[0195] In the formula, represents the experience replay buffer; represents the current state; represents the current action; represents the current reward; represents the updated state (i.e., the next state). By introducing the experience replay buffer, it can be ensured that the model can learn from past experience and repeatedly use these samples for training, thereby improving the training efficiency.

[0196] By adopting a preset dynamic exploration strategy, using the ε-greedy strategy, and gradually reducing the value of ε, gradually decreasing from the initial high exploration rate to a low exploration rate, to balance exploration and exploitation:

[0197]

[0198] In the formula, ε represents the exploration rate; and represent the lowest and highest exploration rates respectively; represents the decay rate; t represents the time step. By adopting the preset dynamic exploration strategy to gradually reduce the exploration rate, the model explores different state and action combinations more in the initial stage and gradually focuses on using the learned knowledge for optimization in the later stage.

[0199] During the training process of the initial model of the electric field strength optimization strategy, when it meets the preset model training termination conditions, such as the model iteration times reaching the preset iteration times, or the loss function value reaching the preset threshold, the current initial model of the electric field strength optimization strategy is used as the target model of the electric field strength optimization strategy.

[0200] Using the validation set and preset model validation metrics such as the model execution time and the model execution success rate, the target model of the electric field strength optimization strategy obtained from the foregoing training is verified. The model parameters are continuously adjusted until the target model of the electric field strength optimization strategy meets the preset model validation metrics, thereby obtaining the trained basic model of the electric field strength optimization strategy.

[0201] S360. Perform a performance test on the basic model of the electric field strength optimization strategy using the test set.

[0202] In an embodiment of the present invention, after obtaining the trained basic model of the electric field strength optimization strategy, the test set can be used to perform a performance test on it to evaluate its model performance.

[0203] S370. If the test result of the performance test meets the preset model test passing condition, then use the basic model of the electric field strength optimization strategy as the electric field strength optimization strategy model.

[0204] In an embodiment of the present invention, measurement metrics such as, but not limited to, the reward value change trend, the Q-value change trend, the average reward, the cumulative reward, and the final reward can be used to determine whether the test result of the performance test of the basic model of the electric field strength optimization strategy meets the preset model test passing condition, such as whether it reaches the preset average reward threshold, etc. If the performance test passes, then use the above-trained basic model of the electric field strength optimization strategy as the final electric field strength optimization strategy model; otherwise, retrain the model until the retrained basic model of the electric field strength optimization strategy meets the preset model test passing condition.

[0205] The technical solution of the embodiment of the present invention performs model training by using multi-dimensional historical data of the target component, and sets a prioritized experience replay buffer during the model training process to increase the training frequency of important samples, ensuring that high-priority samples are trained more frequently, thereby improving the learning efficiency and effect of the model; by introducing an attention mechanism, adaptively adjusting the model's attention to different features, and improving the ability to capture key features; by introducing an adversarial training technique, enhancing the robustness and generalization ability of the model. The electric field strength optimization strategy model trained by using this technical solution can improve the accuracy of the model's decision-making output in the face of unknown and changing environments, and enhance the performance of the model in optimizing the electric field strength and improving the insulation system margin.

[0206] Embodiment 4

[0207] Figure 10 FIG. is a schematic structural diagram of a device for determining an electric field strength optimization strategy of a switch cabinet provided in Embodiment 4 of the present invention. As Figure 10 shown, the device includes:

[0208] A data acquisition module 41, configured to acquire target data of a target component in a switch cabinet; wherein, the target data includes at least one of the following: average dielectric strength, average thermal resistance, average comprehensive mechanical strength, average insulation thickness, and average frequency response; the target component includes at least one of the following switch components: load switch, circuit breaker switch, and earthing switch;

[0209] An optimization strategy determination module 42, configured to input the target data into an electric field strength optimization strategy model to obtain a corresponding optimization strategy; wherein, the optimization strategy includes at least one of the following: adjustment parameters of the average dielectric strength, adjustment parameters of the average thermal resistance, adjustment parameters of the average comprehensive mechanical strength, adjustment parameters of the average insulation thickness, and adjustment parameters of the average frequency response; the electric field strength optimization strategy model is obtained through adversarial training based on a dual deep Q network with an attention mechanism.

[0210] The technical solution of the embodiment of the present invention acquires the target data of the target component in the switch cabinet through the data acquisition module; wherein, the target data includes at least one of the following: average dielectric strength, average thermal resistance, average comprehensive mechanical strength, average insulation thickness, and average frequency response; the target component includes at least one of the following switch components: load switch, circuit breaker switch, and earthing switch; inputs the target data into the electric field strength optimization strategy model through the optimization strategy determination module to obtain a corresponding optimization strategy; wherein, the optimization strategy includes at least one of the following: adjustment parameters of the average dielectric strength, adjustment parameters of the average thermal resistance, adjustment parameters of the average comprehensive mechanical strength, adjustment parameters of the average insulation thickness, and adjustment parameters of the average frequency response; the electric field strength optimization strategy model is obtained through adversarial training based on a dual deep Q network with an attention mechanism. This technical solution acquires the target data of the target component in the switch cabinet for different dimensions, and then uses the pre-trained electric field strength optimization strategy model to output an optimization strategy that can achieve the optimal electric field strength and insulation system margin in the current state of the switch cabinet, solves the problem of poor electric field strength optimization effect in the existing methods, improves the decision-making accuracy of the electric field strength optimization strategy, and further improves the operation safety and reliability of the switch cabinet.

[0211] Further, on the basis of the above-mentioned embodiment of the invention, the average dielectric strength is the average value of the dielectric strengths corresponding to multiple measurement points on the target component, and the dielectric strength is determined by the breakdown voltage collected at the corresponding measurement points and the insulation layer thickness of the target component. The breakdown voltage and the insulation layer thickness of the target component are respectively collected by an electrode test device and a thickness measurement device;

[0212] The average thermal resistance is the average value of the thermal resistances corresponding to multiple measurement points on the target component, and the thermal resistance is determined by the heating power applied at the corresponding measurement points and the collected temperature difference. The heating power is collected by a thermal test device, and the initial temperature and the final temperature corresponding to the temperature difference are collected by an infrared thermal imager;

[0213] The average comprehensive mechanical strength is the average value of the comprehensive mechanical strengths corresponding to multiple measurement points on the target component. The comprehensive mechanical strength is determined by the actual stress and electric field strength collected at the corresponding measurement points, and the actual stress and electric field strength are respectively collected by a stress sensor and an electric field sensor;

[0214] The average insulation thickness is the average value of the insulation layer thicknesses of the target component corresponding to multiple measurement points on the target component;

[0215] The average frequency response is the average value of the frequency responses corresponding to multiple measurement points on the target component, and the frequency response is collected by a frequency response analyzer.

[0216] Further, on the basis of the above-mentioned invention embodiments, the electric field strength optimization strategy model includes: a convolutional neural network layer, an attention layer, a target network, and an evaluation network; correspondingly, the optimization strategy determination module 42 includes:

[0217] A data processing unit, configured to preprocess the target data to obtain normalized target data, and input the normalized target data into the convolutional neural network layer to extract the target feature representation corresponding to the normalized target data;

[0218] An attention matrix determination unit, configured to input the target feature representation into the attention layer and output the target attention matrix corresponding to the target feature representation;

[0219] An optimization strategy determination unit, configured to process the target attention matrix by using the target network and the evaluation network, output the parameters to be adjusted corresponding to each target data, and use each parameter to be adjusted as an optimization strategy.

[0220] Further, on the basis of the above-mentioned invention embodiments, the training process of the electric field strength optimization strategy model includes:

[0221] Obtain the historical data of the target component; wherein, the historical data includes at least one of the following: average dielectric strength historical data, average thermal resistance historical data, average comprehensive mechanical strength historical data, average insulation thickness historical data, and average frequency response historical data;

[0222] Preprocess the historical data to obtain normalized historical data;

[0223] Perform feature mapping encoding on the normalized historical data to obtain a normalized data set;

[0224] Divide the normalized data set into a training set, a validation set, and a test set according to a preset data set division ratio, and initialize and construct an initial electric field strength optimization strategy model;

[0225] Add adversarial perturbations to the sample data of the training set and the validation set, and train the initial model of the electric field strength optimization strategy according to the training set and the validation set to obtain the basic model of the electric field strength optimization strategy;

[0226] Use the test set to perform performance testing on the basic model of the electric field strength optimization strategy;

[0227] If the test result of the performance test meets the preset model test passing condition, then use the basic model of the electric field strength optimization strategy as the electric field strength optimization strategy model.

[0228] Furthermore, based on the above-mentioned invention embodiments, training the initial model of the electric field strength optimization strategy according to the training set and the validation set to obtain the basic model of the electric field strength optimization strategy includes:

[0229] Input the sample data in the training set into the convolutional neural network layer of the initial model of the electric field strength optimization strategy respectively, and extract the sample feature representations corresponding to each sample data;

[0230] Input each sample feature representation into the attention layer of the initial model of the electric field strength optimization strategy respectively to obtain the sample attention matrix corresponding to each sample feature representation;

[0231] Use each sample attention matrix as the state in the state space corresponding to the target network and the evaluation network of the initial model of the electric field strength optimization strategy, and obtain the action space and the reward function corresponding to the configuration of the initial model of the electric field strength optimization strategy;

[0232] Select a state from the state space as the current state, and select the current action in the action space based on the current state using a preset dynamic exploration strategy to obtain an updated state by interacting with the environment according to the current action;

[0233] Determine the updated action according to the updated state through the evaluation network; wherein, the updated action is used to interact with the environment to obtain a new updated state;

[0234] Determine the actual Q value corresponding to the current state and the current action through the evaluation network and the reward function;

[0235] Determine the target Q value corresponding to the updated state and the updated action through the target network;

[0236] Update the network parameters of the evaluation network according to the loss function values corresponding to the actual Q value and the target Q value;

[0237] Copy the network parameters of the evaluation network to the target network every preset time period;

[0238] When the number of model iterations of the initial model of the electric field strength optimization strategy reaches the preset number of iterations, or when the value of the loss function reaches the preset threshold, the current initial model of the electric field strength optimization strategy is used as the target model of the electric field strength optimization strategy;

[0239] Use the validation set to verify the target model of the electric field strength optimization strategy, and adjust the model parameters until the target model of the electric field strength optimization strategy meets the preset model verification index, so as to obtain the trained basic model of the electric field strength optimization strategy.

[0240] Further, on the basis of the above-mentioned invention embodiments, the actions in the action space include at least one of the following: adjusting the adjustment parameter of the average dielectric strength, adjusting the adjustment parameter of the average thermal resistance, adjusting the adjustment parameter of the average comprehensive mechanical strength, adjusting the adjustment parameter of the average insulation thickness, and adjusting the adjustment parameter of the average frequency response.

[0241] Further, on the basis of the above-mentioned invention embodiments, training the initial model of the electric field strength optimization strategy according to the training set and the validation set to obtain the basic model of the electric field strength optimization strategy further includes:

[0242] Adjust the priority of the sample data in the training set and the validation set based on the prioritized experience replay mechanism.

[0243] The switchgear electric field strength optimization strategy determination device provided by the embodiments of the present invention can execute the switchgear electric field strength optimization strategy determination method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0244] Embodiment Five

[0245] Figure 11 FIG. shows a schematic structural diagram of an electronic device 50 that can be used to implement the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0246] As Figure 11As shown, the electronic device 50 includes at least one processor 51 and a memory communicatively connected to the at least one processor 51, such as a read-only memory (ROM) 52, a random access memory (RAM) 53, etc. Among them, the memory stores a computer program executable by the at least one processor. The processor 51 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 52 or the computer program loaded from the storage unit 58 into the random access memory (RAM) 53. In the RAM 53, various programs and data required for the operation of the electronic device 50 can also be stored. The processor 51, the ROM 52, and the RAM 53 are connected to each other through a bus 54. An input / output (I / O) interface 55 is also connected to the bus 54.

[0247] Multiple components in the electronic device 50 are connected to the I / O interface 55, including: an input unit 56, such as a keyboard, a mouse, etc.; an output unit 57, such as various types of displays, speakers, etc.; a storage unit 58, such as a magnetic disk, an optical disc, etc.; and a communication unit 59, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 59 allows the electronic device 50 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0248] The processor 51 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 51 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 51 executes the various methods and processes described above, such as the method for determining the switchgear electric field strength optimization strategy.

[0249] In some embodiments, the method for determining the switchgear electric field strength optimization strategy can be implemented as a computer program, which is tangibly included in a computer-readable storage medium, such as the storage unit 58. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 50 via the ROM 52 and / or the communication unit 59. When the computer program is loaded into the RAM 53 and executed by the processor 51, one or more steps of the method for determining the switchgear electric field strength optimization strategy described above can be executed. Alternatively, in other embodiments, the processor 51 can be configured to execute the method for determining the switchgear electric field strength optimization strategy in any other appropriate way (e.g., by means of firmware).

[0250] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), systems on chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0251] The computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0252] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0253] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0254] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0255] The computing system can include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0256] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0257] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for determining a switch cabinet electric field strength optimization strategy, characterized in that: The method comprises: Obtain target data of a target component in a switch cabinet; wherein the target data is data that affects the electric field distribution and insulation system margin of the switch cabinet, and the target data includes at least one of the following: average dielectric strength, average thermal resistance, average comprehensive mechanical strength, average insulation thickness, and average frequency response; the target component includes at least one of the following switch components: a load switch, a circuit breaker switch, and a grounding switch; the average dielectric strength is an average value of dielectric strengths corresponding to multiple measurement points on the target component, the average thermal resistance is an average value of thermal resistances corresponding to multiple measurement points on the target component, the average comprehensive mechanical strength is an average value of comprehensive mechanical strengths corresponding to multiple measurement points on the target component, the average insulation thickness is an average value of insulation layer thicknesses corresponding to multiple measurement points on the target component, and the average frequency response is an average value of frequency responses corresponding to multiple measurement points on the target component; The target data is input into the electric field strength optimization strategy model to obtain a corresponding optimization strategy; wherein the optimization strategy includes at least one of the following: an adjusted parameter of average dielectric strength, an adjusted parameter of average thermal resistance, an adjusted parameter of average comprehensive mechanical strength, an adjusted parameter of average insulation thickness and an adjusted parameter of average frequency response; the electric field strength optimization strategy model is obtained by adversarial training of a dual deep Q network based on an attention mechanism.

2. The method for determining the switch cabinet electric field strength optimization strategy according to claim 1, characterized in that: The dielectric strength is determined by the breakdown voltage and the thickness of the insulation layer of the target component collected at the corresponding measurement points, and the breakdown voltage and the thickness of the insulation layer of the target component are collected by an electrode testing device and a thickness measuring device respectively; The thermal resistance is determined by the heating power applied at the corresponding measuring point and the collected temperature difference, the heating power is collected by a thermal testing device, and the initial temperature and final temperature corresponding to the temperature difference are collected by an infrared thermal imager; The comprehensive mechanical strength is determined by the actual stress and electric field strength collected at the corresponding measuring points, and the actual stress and the electric field strength are collected by the stress sensor and the electric field sensor respectively; The frequency response is acquired by a frequency response analyzer.

3. The method for determining the switch cabinet electric field strength optimization strategy according to claim 1, characterized in that: The electric field strength optimization strategy model includes: a convolutional neural network layer, an attention layer, a target network and an evaluation network; The step of inputting the target data into the electric field strength optimization strategy model to obtain a corresponding optimization strategy includes: Preprocessing the target data to obtain normalized target data, and inputting the normalized target data into the convolutional neural network layer to extract target feature representation corresponding to the normalized target data; Input the target feature representation into the attention layer, and output the target attention matrix corresponding to the target feature representation; The target attention matrix is ​​processed using the target network and the evaluation network, and the parameters to be adjusted corresponding to each of the target data are output, and each of the parameters to be adjusted is used as the optimization strategy.

4. The method for determining the switch cabinet electric field strength optimization strategy according to claim 1, characterized in that: Before acquiring the target data of the target component in the switch cabinet, a training process of the electric field strength optimization strategy model is also included, and the training process includes: Acquire historical data of the target component; wherein the historical data includes at least one of the following: average dielectric strength historical data, average thermal resistance historical data, average comprehensive mechanical strength historical data, average insulation thickness historical data, and average frequency response historical data; Preprocessing the historical data to obtain normalized historical data; Performing feature mapping encoding on the normalized historical data to obtain a normalized data set; Dividing the normalized data set into a training set, a validation set, and a test set according to a preset data set segmentation ratio, and initially constructing an initial model of the electric field strength optimization strategy; Adding adversarial disturbances to the sample data of the training set and the verification set, and training the initial model of the electric field strength optimization strategy according to the training set and the verification set to obtain a basic model of the electric field strength optimization strategy; Using the test set to perform performance testing on the basic model of the electric field strength optimization strategy; If the test result of the performance test meets the preset model test pass condition, the electric field strength optimization strategy basic model is used as the electric field strength optimization strategy model.

5. The method for determining the switch cabinet electric field strength optimization strategy according to claim 4, characterized in that: The electric field strength optimization strategy initial model is trained according to the training set and the verification set to obtain the electric field strength optimization strategy basic model, including: Inputting the sample data in the training set into the convolutional neural network layer of the initial model of the electric field strength optimization strategy respectively, and extracting the sample feature representation corresponding to each of the sample data; Inputting each of the sample feature representations into the attention layer of the initial model of the electric field strength optimization strategy respectively, to obtain a sample attention matrix corresponding to each of the sample feature representations; Using each of the sample attention matrices as the state in the state space corresponding to the target network and the evaluation network of the initial model of the electric field strength optimization strategy, and obtaining the action space and reward function corresponding to the configuration of the initial model of the electric field strength optimization strategy; Selecting a state from the state space as the current state, and selecting a current action in the action space based on the current state using a preset dynamic exploration strategy, so as to obtain an updated state according to the interaction between the current action and the environment; Determining an update action according to the update state through the evaluation network; wherein the update action is used to interact with the environment to obtain a new update state; Determine the actual Q value corresponding to the current state and the current action through the evaluation network and the reward function; Determine the target Q value corresponding to the update state and the update action through the target network; Updating the network parameters of the evaluation network according to the loss function values ​​corresponding to the actual Q value and the target Q value; Copying the network parameters of the evaluation network to the target network at intervals of a preset time period; When the model iteration number of the electric field strength optimization strategy initial model reaches a preset iteration number, or the loss function value reaches a preset threshold, the current electric field strength optimization strategy initial model is used as the electric field strength optimization strategy target model; The electric field strength optimization strategy target model is verified using the verification set, and model parameters are adjusted until the electric field strength optimization strategy target model meets preset model verification indicators to obtain the trained electric field strength optimization strategy basic model.

6. The method for determining the switch cabinet electric field strength optimization strategy according to claim 5, characterized in that: The actions in the action space include at least one of the following: an adjustment parameter for adjusting average dielectric strength, an adjustment parameter for adjusting average thermal resistance, an adjustment parameter for adjusting average comprehensive mechanical strength, an adjustment parameter for adjusting average insulation thickness, and an adjustment parameter for adjusting average frequency response.

7. The method for determining the switch cabinet electric field strength optimization strategy according to claim 4, characterized in that: The training of the electric field strength optimization strategy initial model according to the training set and the verification set to obtain the electric field strength optimization strategy basic model also includes: The priorities of the sample data in the training set and the validation set are adjusted based on a priority experience replay mechanism.

8. A device for determining an optimization strategy for electric field strength of a switch cabinet, characterized in that: The device comprises: A data acquisition module, used to acquire target data of a target component in a switch cabinet; wherein the target data is data that affects the electric field distribution and insulation system margin of the switch cabinet, and the target data includes at least one of the following: average dielectric strength, average thermal resistance, average comprehensive mechanical strength, average insulation thickness and average frequency response; the target component includes at least one of the following switch components: a load switch, a circuit breaker switch and an earthing switch; the average dielectric strength is an average value of dielectric strengths corresponding to multiple measurement points on the target component, the average thermal resistance is an average value of thermal resistances corresponding to multiple measurement points on the target component, the average comprehensive mechanical strength is an average value of comprehensive mechanical strengths corresponding to multiple measurement points on the target component, the average insulation thickness is an average value of insulation layer thicknesses corresponding to multiple measurement points on the target component, and the average frequency response is an average value of frequency responses corresponding to multiple measurement points on the target component; An optimization strategy determination module is used to input the target data into an electric field strength optimization strategy model to obtain a corresponding optimization strategy; wherein the optimization strategy includes at least one of the following: an adjusted parameter of average dielectric strength, an adjusted parameter of average thermal resistance, an adjusted parameter of average comprehensive mechanical strength, an adjusted parameter of average insulation thickness, and an adjusted parameter of average frequency response; the electric field strength optimization strategy model is obtained by adversarial training of a dual deep Q network based on an attention mechanism.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for determining the switch cabinet electric field strength optimization strategy according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining the switch cabinet electric field strength optimization strategy according to any one of claims 1 to 7 when executed.

Images