Determination method and determination device for air gap breakdown voltage, and computer program product

Abstract

The invention provides an air gap breakdown voltage determination method and device and a computer program product, and the method comprises the steps: obtaining air gap data which comprises an electric field feature set formed by a plurality of electric field feature quantities; inputting the air gap data into a breakdown voltage determination model, and outputting to obtain a target breakdown voltage, the breakdown voltage determination model being a convergence model obtained by training a predetermined model by using multiple groups of training data, each group of training data including a sample electric field feature set and a sample breakdown voltage; and under the condition that the target breakdown voltage is smaller than the set voltage, judging that the insulation characteristic of the air gap does not meet the relay protection requirement. The method solves the problems that the prior art mainly depends on experimental data, and the experimental research of the air gap breakdown characteristic is long in period and high in cost, so that the accuracy of a prediction result is low.

Description

Technical Field

[0001] The present invention relates to the technical field of research on breakdown characteristics of air gaps, and in particular to a method for determining the breakdown voltage of an air gap, a determining device, a computer-readable storage medium, and a computer program product. Background Art

[0002] The breakdown characteristics of air gaps are a key factor in the design of external insulation for UHV power transmission and transformation projects, but current theoretical research cannot fully explain their complex behavior. Therefore, engineering design mainly relies on experimental data, which comes from long-gap discharge tests on typical structural gaps such as rod-plate and actual engineering gaps. This method has obvious limitations: 1. The types of gap structures actually used in power transmission and transformation projects are diverse, and their discharge characteristics are also different accordingly. The standard gap model cannot fully cover all possible engineering application scenarios, thus limiting the universality and scope of application of the model. 2. Factors such as voltage waveform and atmospheric environment have an important influence on the breakdown characteristics of air gaps. In order to ensure the wide applicability of test data, tests need to be carried out under a variety of voltage waveforms and environmental conditions, which increases the complexity of the test. 3. When the gap coefficient is used to infer the breakdown voltage of the actual engineering gap, it usually deviates from the experimental value, resulting in increased uncertainty in the prediction results. The experimental study of the breakdown characteristics of air gaps has the problems of long cycle and high cost. Summary of the invention

[0003] The main purpose of the present application is to provide a method for determining the breakdown voltage of an air gap, a determination device, a computer-readable storage medium and a computer program product, so as to at least solve the problem that the prior art mainly relies on experimental data, and the experimental research on the breakdown characteristics of the air gap has a long cycle and high cost, resulting in low accuracy of the prediction results.

[0004] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for determining an air gap breakdown voltage is provided, comprising: obtaining air gap data, the air gap data comprising an electric field feature set formed by a plurality of electric field feature quantities, the electric field feature set comprising at least the electric field feature quantity of the discharge channel region, the electric field feature quantity of the electrode surface region, and the electric field feature quantity of the external non-breakdown region, the electric field feature quantity comprising at least the electric field intensity, the electric field energy, the energy density, the surface area of ​​the electric field intensity unit, the electric field gradient, the path length and the proportional parameter of the electric field intensity unit; inputting the air gap data into a breakdown voltage determination model, and outputting a target breakdown voltage, the breakdown voltage determination model being a convergence model obtained by training a predetermined model using a plurality of sets of training data, each set of the training data comprising a sample electric field feature set and a sample breakdown voltage; and when the target breakdown voltage is less than the set voltage, determining that the insulation characteristics of the air gap do not meet the relay protection requirements.

[0005] Optionally, before inputting the air gap data into the breakdown voltage determination model and outputting the target breakdown voltage, the method also includes: performing a breakdown test on the air gap of different typical electrodes to obtain breakdown voltage data corresponding to each of the typical electrodes; determining a breakdown interval and a non-breakdown interval corresponding to each of the typical electrodes based on the breakdown voltage data; performing electric field calculations on the corresponding breakdown intervals and non-breakdown intervals for different typical electrodes to obtain a plurality of electric field characteristic quantities; and performing preprocessing operations on the plurality of electric field characteristic quantities to obtain the sample electric field characteristic set.

[0006] Optionally, a preprocessing operation is performed on the multiple electric field feature quantities to obtain the sample electric field feature set, including: normalizing each of the electric field feature quantities to obtain a normalized electric field feature quantity; and using a principal component analysis method to perform dimensionality reduction processing on the normalized electric field feature quantities to obtain the sample electric field feature set.

[0007] Optionally, before the air gap data is input into the breakdown voltage determination model and the target breakdown voltage is outputted, the method further includes: constructing an initial breakdown voltage determination model and initializing model parameters of the initial breakdown voltage determination model, wherein the initial breakdown voltage determination model is an XGBoost model to be trained, and the model parameters include at least the classifier type, the weight of positive samples, the number of decision trees, the maximum depth of the decision trees, the learning rate and the penalty coefficient; a training step, inputting multiple groups of the sample electric field feature sets into the initial breakdown voltage determination model for training to obtain an intermediate breakdown voltage determination model, wherein the intermediate breakdown voltage determination model is the initial breakdown voltage Determine the model obtained after model training; a testing step, inputting multiple groups of test electric field feature sets into the initial breakdown voltage determination model for testing to obtain the accuracy of the intermediate breakdown voltage determination model, each group of the test electric field feature sets includes a test electric field feature quantity and a test breakdown voltage; when the accuracy is less than the set accuracy, re-execute the training step and the testing step at least once until the accuracy is greater than or equal to the set accuracy or the number of iterations reaches the maximum set number of iterations, and the intermediate breakdown voltage determination model is determined as the breakdown voltage determination model, and the number of iterations is the number of iterative training of the initial breakdown voltage determination model.

[0008] Optionally, the air gap data is input into a breakdown voltage determination model, and a target breakdown voltage is obtained by output, including: inputting the air gap data into the breakdown voltage determination model to obtain an interval characteristic value, wherein the interval characteristic value is an intermediate variable of the breakdown voltage determination model in a calculation process, and the interval characteristic value is -1 or 1, and when the interval characteristic value is 1, it indicates that the air gap is broken down, and when the interval characteristic value is -1, it indicates that the air gap is not broken down;

[0009] In the first calculation step, when the interval characteristic value is -1, the loading voltage is calculated according to the first formula, wherein the first formula is U L =U0+dU L , U L represents the loading voltage, U0 represents the initial voltage of the typical electrode at the initial loading, dU L Represents a set adjustment value, the loading voltage is the voltage applied to the typical electrode of the electrical equipment; the first input step, performs electric field calculation and extraction on the air gap of the typical electrode to obtain the current first electric field feature set, and re-inputs the current first electric field feature set into the breakdown voltage determination model to obtain the first current interval characteristic value, the first current interval characteristic value is the interval characteristic value obtained by re-inputting the current first electric field characteristic set into the breakdown voltage determination model; repeats the first calculation step and the first input step in sequence until the current interval characteristic value is 1, and determines the current loading voltage as the target breakdown voltage.

[0010] Optionally, after the air gap data is input into the breakdown voltage determination model to obtain the interval characteristic value, the method further includes: a second calculation step, when the interval characteristic value is 1, calculating the loading voltage according to a second formula, wherein the second formula is U L =U0-dU L ; A second input step, performing electric field calculation on the air gap of the typical electrode to extract the current second electric field feature set, and re-inputting the current second electric field feature set into the breakdown voltage determination model to obtain the current second interval characteristic value, and the current second interval characteristic value is the interval characteristic value obtained by re-inputting the current second electric field characteristic set into the breakdown voltage determination model; repeating the second calculation step and the second input step in sequence until the current interval characteristic value is -1, and determining the sum of the current loading voltage and the set adjustment value as the target breakdown voltage.

[0011] Optionally, after the air gap data is input into a breakdown voltage determination model and a target breakdown voltage is output, the method further comprises: when the target breakdown voltage is greater than or equal to the set voltage, determining that the insulation characteristics of the air gap meet relay protection requirements.

[0012] According to another aspect of the present application, a device for determining an air gap breakdown voltage is provided, the device comprising: an acquisition unit, for acquiring air gap data, the air gap data comprising an electric field feature set formed by a plurality of electric field feature quantities, the electric field feature set comprising at least the electric field feature quantity of a discharge channel region, the electric field feature quantity of an electrode surface region, and the electric field feature quantity of an external non-breakdown region, the electric field feature quantity comprising at least electric field intensity, electric field energy, energy density, surface area of ​​an electric field intensity unit, electric field gradient, path length and proportional parameter of an electric field intensity unit; an input-output unit, for inputting the air gap data into a breakdown voltage determination model, and outputting a target breakdown voltage, the breakdown voltage determination model being a convergence model obtained by training a predetermined model using a plurality of sets of training data, each set of the training data comprising a sample electric field feature set and a sample breakdown voltage; a first determination unit, for determining, when the target breakdown voltage is less than a set voltage, that the insulation characteristics of the air gap do not meet the relay protection requirements.

[0013] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the methods described.

[0014] According to another aspect of the present application, a computer program product is provided, comprising computer instructions, wherein when the computer instructions are executed by a processor, any one of the methods described above is implemented.

[0015] Applying the technical solution of the present application, in a method for determining an air gap breakdown voltage, first, air gap data is obtained, the air gap data includes an electric field feature set formed by multiple electric field feature quantities, the electric field feature set includes at least the electric field feature quantity of the discharge channel area, the electric field feature quantity of the electrode surface area, and the electric field feature quantity of the external non-breakdown area, the electric field feature quantity includes at least the electric field strength, electric field energy, energy density, the surface area of ​​the electric field strength unit, the electric field gradient, the path length and proportional parameter of the electric field strength unit; then, the air gap data is input into a breakdown voltage determination model, and a target breakdown voltage is output, the breakdown voltage determination model is a convergence model obtained by training a predetermined model using multiple groups of training data, and each group of the training data includes a sample electric field feature set and a sample breakdown voltage; finally, when the target breakdown voltage is less than the set voltage, it is determined that the insulation characteristics of the air gap do not meet the relay protection requirements. This application uses the typical electrode air gap data obtained from the experiment as the training set and test set of the model to perform breakdown voltage prediction training, and can obtain the breakdown voltage determination model of the air gap. By obtaining the air gap data to be predicted in real time and inputting it into the breakdown voltage determination model, the prediction result, that is, the target breakdown voltage, is obtained to determine whether the insulation characteristics of the air gap meet the relay protection requirements. Further, it provides guiding suggestions for the insulation protection of power system equipment and the safe and economical operation of the power grid. This application solves the problem that the existing technology mainly relies on experimental data, and the experimental research on the breakdown characteristics of the air gap has a long cycle and high cost, resulting in low accuracy of the prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A hardware structure block diagram of a mobile terminal for performing a method for determining an air gap breakdown voltage provided in an embodiment of the present application is shown;

[0017] Figure 2 A schematic flow chart of a method for determining an air gap breakdown voltage provided in accordance with an embodiment of the present application is shown;

[0018] Figure 3 A prediction flow chart of a breakdown voltage determination model provided according to an embodiment of the present application is shown;

[0019] Figure 4 A structural block diagram of a device for determining an air gap breakdown voltage provided according to an embodiment of the present application is shown.

[0020] The above drawings include the following reference numerals:

[0021] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION

[0022] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] As introduced in the background technology, the prior art has the problem of long cycle and high cost in experimental research on air gap breakdown characteristics. In order to solve the problem that the experimental research on air gap breakdown characteristics mainly relies on experimental data, and the long cycle and high cost lead to low accuracy of prediction results, the embodiments of the present application provide a method for determining the breakdown voltage of an air gap, a determination device, a computer-readable storage medium and a computer program product.

[0026] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0027] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal of a method for determining an air gap breakdown voltage according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0028] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for determining the breakdown voltage of the air gap in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0029] In this embodiment, a method for determining the air gap breakdown voltage running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0030] Figure 2 FIG. 1 is a flow chart of a method for determining an air gap breakdown voltage according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0031] Step S201, obtaining air gap data, the air gap data includes an electric field feature set formed by multiple electric field feature quantities, the electric field feature set includes at least the electric field feature quantity of the discharge channel area, the electric field feature quantity of the electrode surface area, and the electric field feature quantity of the external non-breakdown area, the electric field feature quantity includes at least electric field intensity, electric field energy, energy density, surface area of ​​electric field intensity unit, electric field gradient, path length and proportional parameter of electric field intensity unit.

[0032] Specifically, air gaps of typical electrodes with different structures are tested and electric field calculations are performed to obtain air gap data.

[0033] It should also be noted that the air gap breakdown discharge path has a large degree of randomness and is difficult to accurately determine, so the electric field gradient characteristic class on the shortest path is used to characterize the gap structure and does not represent the discharge path in the actual physical process. Therefore, the specific discharge path does not affect the prediction results of the method of the present invention. The following electric field characteristic quantity classes are defined in terms of physical quantities and dimensions: electric field intensity, electric field energy, energy density, surface area, electric field gradient, path length and proportional parameters, etc. The specific electric field characteristic quantity definitions are as follows: Maximum electric field intensity: E m =maxE i (i=1,2,…,n), where E i is the average value of the electric field strength of the i-th spatial unit, and n is the total number of units. Average value of electric field strength: Electric field strength distortion rate: Total electric field energy W: Where ε0 is the dielectric constant of vacuum, V i is the volume of the i-th space unit. Total volume V: Energy density W d : The volume ratio of the area with a maximum electric field strength exceeding x% V rx : Where V xi is the volume of the i-th unit with an electric field strength exceeding x%, and xn is the total number of units with an electric field strength exceeding x%. The energy ratio of the area with an electric field strength exceeding x% is W rx : Where W xi is the energy of the i-th unit that exceeds x% of the maximum electric field strength. Total surface area S: In the formula, S i is the surface area of ​​the ith unit, and n is the total number of units. The proportion of the surface area occupied by the area with a maximum electric field strength exceeding x% S rx : In the formula, S xiis the surface area of ​​the ith unit with an electric field strength exceeding x%. The electric field strength E′: E′=|-gradE|, where E is the electric field strength at a certain point, a scalar. The proportion of the path length of the area with an electric field strength exceeding x% L rx : Where, L xi is the discharge shortest path length of the i-th unit exceeding x% of the maximum electric field strength, and L is the total discharge shortest path length. The above-mentioned proportional parameters include V rx , W rx , S rx and L rx .

[0034] Step S202, input the above air gap data into a breakdown voltage determination model, and output a target breakdown voltage. The above breakdown voltage determination model is a convergence model obtained by training a predetermined model using multiple sets of training data, and each set of the above training data includes a sample electric field feature set and a sample breakdown voltage.

[0035] Specifically, XGBOOST is used to establish a breakdown voltage prediction model, and training is performed to obtain a breakdown voltage determination model, which takes the electric field feature set as input and the breakdown voltage as output. Therefore, the air gap data is input into , and the breakdown voltage determination model is used for calculation, and the target breakdown voltage can be output.

[0036] Step S203: when the target breakdown voltage is less than the set voltage, it is determined that the insulation characteristics of the air gap do not meet the relay protection requirements.

[0037] Specifically, based on the target breakdown voltage, determine whether the insulation properties of the air gap meet the protection needs. If the predicted breakdown voltage is lower than the design voltage, it indicates that the insulation properties of the air gap may be insufficient, there is a safety risk, and improvement measures need to be taken.

[0038] In this embodiment, first, air gap data is obtained, the air gap data includes an electric field feature set formed by multiple electric field feature quantities, the electric field feature set includes at least the electric field feature quantity of the discharge channel area, the electric field feature quantity of the electrode surface area, and the electric field feature quantity of the external non-breakdown area, the electric field feature quantity includes at least electric field intensity, electric field energy, energy density, surface area of ​​the electric field intensity unit, electric field gradient, path length and proportional parameter of the electric field intensity unit; then, the air gap data is input into a breakdown voltage determination model, and a target breakdown voltage is obtained as an output, the breakdown voltage determination model is a convergence model obtained by training a predetermined model using multiple groups of training data, and each group of the training data includes a sample electric field feature set and a sample breakdown voltage; finally, when the target breakdown voltage is less than the set voltage, it is determined that the insulation characteristics of the air gap do not meet the relay protection requirements. This application uses the typical electrode air gap data obtained from the experiment as the training set and test set of the model to perform breakdown voltage prediction training, and can obtain the breakdown voltage determination model of the air gap. By obtaining the air gap data to be predicted in real time and inputting it into the breakdown voltage determination model, the prediction result, that is, the target breakdown voltage, is obtained to determine whether the insulation characteristics of the air gap meet the relay protection requirements. Further, it provides guiding suggestions for the insulation protection of power system equipment and the safe and economical operation of the power grid. This application solves the problem that the existing technology mainly relies on experimental data, and the experimental research on the breakdown characteristics of the air gap has a long cycle and high cost, resulting in low accuracy of the prediction results.

[0039] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the method for determining the breakdown voltage of an air gap of the present application will be described in detail below in conjunction with specific embodiments.

[0040] In order to reduce the number of tests required for the external insulation design to obtain the electric field feature set, in an optional implementation manner, before the above step S202, the method further includes:

[0041] Step S301, performing a breakdown test on the air gaps of different typical electrodes to obtain breakdown voltage data corresponding to each of the typical electrodes;

[0042] Step S302, determining the breakdown interval and non-breakdown interval corresponding to each of the typical electrodes according to the breakdown voltage data;

[0043] Step S303, respectively loading the corresponding breakdown interval and non-breakdown interval on different typical electrodes to perform electric field calculation to obtain a plurality of electric field characteristic quantities;

[0044] Step S304: performing a preprocessing operation on the plurality of electric field feature quantities to obtain the sample electric field feature set.

[0045] In the above embodiment, the breakdown test is performed on the air gap of typical electrodes with different structures to obtain the breakdown voltage data. For example, the measured breakdown voltage is U, and [90%U, U] is defined as the non-breakdown interval, and the characteristic value is -1; [U, 110%U] is defined as the breakdown interval, and the characteristic value is 1. For the initial loading voltage U0 of typical electrodes with different structures, the corresponding non-breakdown interval and breakdown voltage interval are loaded respectively to perform electric field calculation, and the electric field characteristic quantity is obtained, and then the electric field characteristic set corresponding to each loading voltage is obtained through preprocessing. By exploring the influence of different gap structures, voltage waveforms and environmental factors on the breakdown characteristics in actual power transmission and transformation projects, a data set is obtained, and the breakdown characteristics of the air gap are calculated or predicted, and used to guide the external insulation design of the power transmission and transformation project, so as to achieve the goal of reducing the number of tests required for the external insulation design.

[0046] In order to reduce computational complexity and speed up the convergence of the model, in an optional implementation, the above step S304 includes:

[0047] Step S3041, normalizing each of the above electric field characteristic quantities to obtain a normalized electric field characteristic quantity;

[0048] Step S3042: Use principal component analysis to perform dimensionality reduction processing on the normalized electric field feature quantity to obtain the sample electric field feature set.

[0049] In the above embodiment, in order to reduce the computational complexity and improve the computational efficiency, the electric field feature set can be subjected to dimensionality reduction processing. In order to eliminate the influence of different orders of magnitude and dimensions and to speed up the training and convergence speed of the model, the electric field feature set needs to be normalized. Before the electric field feature set is subjected to dimensionality reduction processing, each feature quantity needs to be normalized to eliminate the influence of different orders of magnitude and dimensions, reduce the influence of improper data processing on the prediction effect, and speed up the training and convergence speed of the prediction model. The normalization method is: In the formula, x′ i is a characteristic quantity x in the electric field characteristic set i The normalized value, x max is the maximum value of the feature value, x min is the minimum value of the feature quantity. At this time, the feature quantity x i By [x max , x min ] is normalized to [0,1].

[0050] Principal component analysis is a commonly used feature dimensionality reduction method. Based on the mathematical idea of dimensionality reduction, it tries to recombine multiple strongly correlated indicators to obtain a few uncorrelated comprehensive indicators and replace the original multiple indicators, which is a multivariate statistical method. Usually, the recombined comprehensive indicators are called principal components. The principal component analysis mainly includes the following steps: (1) Calculate the correlation coefficient matrix R = (r ij ) p×p according to the normalized data table, where p is the feature dimension. (2) Calculate the eigenvalues and eigenvectors of R. Solve the characteristic equation |R - λI| = 0 to obtain the characteristic roots λ, and arrange them from large to small as λ1, λ2,..., λ p , and at the same time, the corresponding eigenvectors u1, u2,..., u p can be obtained. I in the characteristic equation represents the identity matrix. (3) Calculate the variance contribution rate e i and the cumulative variance contribution rate P. (4) Select the first k principal components corresponding to the eigenvalues with the cumulative variance contribution rate reaching the predetermined value P (0.85 < P < 0.95) to obtain the above sample electric field feature set. The calculation formula for the cumulative variance contribution rate of the principal components is: where k is the number of principal components, p is the number of original features, k ≤ p, and λ i is the eigenvalue of the i-th principal component.

[0051] To improve the accuracy of classification and recognition, in an optional implementation, before the above step S202, the method further includes:

[0052] Step S401: Construct an initial breakdown voltage determination model and initialize the model parameters of the above initial breakdown voltage determination model. The above initial breakdown voltage determination model is an XGBoost model to be trained, and the above model parameters at least include the classifier type, the weight of positive samples, the number of decision trees, the maximum depth of the above decision trees, the learning rate, and the penalty coefficient;

[0053] Step S402: Training step. Input multiple groups of the above sample electric field feature sets into the above initial breakdown voltage determination model for training to obtain an intermediate breakdown voltage determination model. The above intermediate breakdown voltage determination model is the model obtained after training the above initial breakdown voltage determination model;

[0054] Step S403: Testing step. Input multiple groups of test electric field feature sets into the above initial breakdown voltage determination model for testing to obtain the accuracy rate of the above intermediate breakdown voltage determination model. Each group of the above test electric field feature sets includes test electric field feature quantities and test breakdown voltages;

[0055] Step S404, when the above-mentioned accuracy rate is less than the set accuracy rate, re-execute the above-mentioned training step and the above-mentioned testing step at least once, until the above-mentioned accuracy rate is greater than or equal to the above-mentioned set accuracy rate or the number of iterations reaches the maximum set number of iterations, and the above-mentioned intermediate breakdown voltage determination model is determined as the above-mentioned breakdown voltage determination model, and the above-mentioned number of iterations is the number of iterative trainings of the above-mentioned initial breakdown voltage determination model.

[0056] In the above embodiment, when training the XGBOOST model, the main purpose is to determine the best tree structure. The core problem is to find an optimal split node. The greedy algorithm used in the splitting is used to calculate the gain before and after the split to determine whether the node needs to be split. Then, the various parameters of the model are iteratively optimized based on the objective function. The XGBOOST model is finally obtained by training according to the above process. The training process is as follows Figure 3 shown.

[0057] The XGBOOST model contains a large number of parameters, which can be generally divided into three categories: the first category is the conventional parameters that control some macro functions, such as the classifier type, the weight of positive samples, etc.; the second category is the model parameters related to the structure of the tree, such as the number of decision trees, the maximum depth of the tree, etc.; the third category is the target parameters for learning in the model, such as the learning rate, the penalty coefficient, etc. When modeling the XGBOOST model, these parameters can be reasonably set to determine the optimal parameters, thereby improving the accuracy of classification and recognition.

[0058] The maximum number of trees is n_estimator. If the number of trees is too small, the learning ability of the model may be insufficient, reducing the prediction ability; if the number of trees is too large, although the learning ability is extremely high, overfitting may occur. In order to quantitatively evaluate the quality of the classification prediction model, the accuracy rate is used as the evaluation index of the model. The calculation formula is as follows: Where n is the total number of test samples; n p is the number of correct classifications. The accuracy is positively correlated with the model classification and recognition effect, that is, the higher the accuracy, the better the model classification effect.

[0059] The maximum depth of the tree, max_depth, also directly affects the prediction results. If the value is too small, the tree depth will be insufficient, which will make the classification less rigorous and reduce the prediction accuracy. If the value is too large, over-learning will occur, and the prediction accuracy will only be slightly improved, but the calculation rate will be greatly reduced. The control variable method can be used to determine this parameter, setting the range of max_depth to 1 to 10, comparing the classification accuracy at each depth, and selecting the max_depth with the highest classification accuracy as the maximum depth of the model tree.

[0060] The learning rate eta is based on the idea that each step is a small step and gradually approaches the result, which is better than taking a big step directly to approach the result. In other words, do not trust a certain tree, but only learn part of the tree. The learning rate is used to control the weight of the leaf node to adjust the influence of the tree on the result. When the learning rate is small, that is, the weight of the current leaf node becomes smaller, the influence of the tree on the final prediction result will also become smaller. Usually, the learning rate will not be too large to prevent overfitting. Select the learning rate value between 0 and 1, with an interval of 0.05, obtain the prediction accuracy under different learning rates, and compare the classification accuracy values ​​to determine the optimal learning rate.

[0061] The minimum weight of the leaf, min_child_weight, is used to determine whether the current leaf node needs to be split. If the current weight of a leaf node is less than the set minimum weight, the split is stopped. The smaller this value is, the more likely it is to overfit. Based on the maximum number of trees, maximum depth, and learning rate determined above, set the value of min_child_weight to vary in the range of 0 to 10, and observe the accuracy under different minimum weights to determine the minimum weight of the leaf.

[0062] It should also be noted that as an integrated tree model, the XGBOOST model contains multiple CART trees, and its output is the sum of multiple trees, and this value is used as the predicted value of the XGBOOST model. Its mathematical expression is as follows: Where K is the number of CART trees; F is a possible CART tree; fk represents a specific CART tree; is the output of the XGBOOST model. For a given sample length of n and the number of features of m, we have: D = {(x i , Y i )}(|D|=n,x i ∈R m ,y i ∈R), where x i represents the i-th sample input; y i represents the output corresponding to the i-th sample input; F is the space of the CART tree, which can be expressed as: F = {f(x) = w q (x)}(q:R m →T, w∈R T ), where q represents the structure of the CART tree; T is the number of child nodes of the CART tree; f(x) is the CART tree structure q and the child node weight w; the establishment of the XGBOOST model is to learn the CART tree and determine the structure and weight of the tree. Bringing the regularization term into the objective function, we have: In the formula, and iRepresent the predicted value and actual label value of the ith sample respectively; γ and λ are weight coefficients; the first half of F(Φ) is the loss error, usually with mean square error and logistic regression, and the second half is the regularization term, which is usually used to constrain the depth of the CART tree, reduce the complexity of the tree, and prevent overfitting. When establishing the XGBOOST model to solve practical problems, the purpose is to obtain the optimal coefficients so that the predicted value is as close to the true value as possible, and the model has good generalization ability and calculation rate, so that the model has good versatility. When training the model, it is promoted in an additive way, then: in, is the t-th round XGBOOST model; for The prediction model of the previous round; f t (x i ) is a newly added function. During training, the newly added function is added to the tth round. At this time, a constant term C is added based on the cumulative difference between the predicted value and the actual value. The objective function at this time can be expressed as: Taylor expansion of the above formula:

[0063]

[0064] Since the residual of the CART tree is obtained by subtracting the t-th tree from the previous tree, the predicted value of the t-1 tree is known to be l That is, the part in the Taylor expansion is a certain value and does not affect the optimization calculation of the objective function. It can be incorporated into the constant term or directly removed. Therefore, the objective function can be expressed as:

[0065]

[0066] The above section explains the relationship between error and objective function. Next, we will explain how the regularization term added in XGBOOST defines the complexity of the CART tree. Transform the objective function:

[0067]

[0068] At this time, two regularization terms, the number of leaf nodes T and the leaf node score w, are added to the objective function. Therefore, the objective function part of the regularization term also adds two cumulative parts, the number of samples and the number of leaf nodes. The two cumulative terms in the above formula are expressed as G j and H j To replace, the above formula can be simplified to: Reverse the above formula to w j Taking the derivative and setting it equal to 0, we get: Finally, w j The optimal solution of is brought into the objective function, and we can get: From the above formula, we can see that if the structure of the tree is determined, the score of the structure is only related to the first-order and second-order derivatives of the structure, and the score is negatively correlated with the structure, that is, the smaller the score, the better the structure, and vice versa. In addition, to determine the structure of a tree, we also need to pay attention to the node division of the tree and the conditions for the tree to stop growing.

[0069] 1) Node division: Regarding node division, XGBOOST does not use the inefficient enumeration method, but uses a greedy algorithm to replace the enumeration method, starting from a single child node and iteratively splitting it into tree nodes. After the node is split, the loss function is as follows: The three items in the above formula are the scores of the left tree, the right tree and the score when no split is performed. The loss function value is determined by these three items. Among them, λ is not only used to control the complexity of the tree, but also used as a threshold to determine whether the split is performed. If the gain after the split is greater than λ at this time, then the split is performed, otherwise it is not performed.

[0070] 2) Stop growing: The tree cannot grow indefinitely, which will increase the complexity of the tree. At this time, certain constraints should be required to constrain the growth of the tree so that the tree stops growing automatically. If the objective function value F of the child node after a new split is loss Less than 0, the split will be abandoned. This is a balance between the loss value and the complexity of the model structure. In addition, when the depth of the tree reaches the set maximum depth, the split of the child node will stop and the tree will no longer be built. The depth of the tree is related to whether the model will be underfitting. It is necessary to optimize the depth of the tree to determine the appropriate depth of the tree. When a child node splits, the weight coefficients of the left and right leaf nodes will be updated. If any child node weight coefficient is less than a set threshold, the split will be abandoned. Here, it is necessary to optimize another parameter of the model, the minimum child node 12-point weight, and then determine the depth of the tree and the weight of the child node.

[0071] In order to accurately determine the breakdown voltage of the air gap, in an optional implementation manner, the above step S202 includes:

[0072] Step S2021, inputting the air gap data into a breakdown voltage determination model to obtain an interval characteristic value, wherein the interval characteristic value is an intermediate variable in the calculation process of the breakdown voltage determination model, and the interval characteristic value is -1 or 1. When the interval characteristic value is 1, it indicates that the air gap is broken down, and when the interval characteristic value is -1, it indicates that the air gap is not broken down;

[0073] Step S2022, the first calculation step, when the above interval characteristic value is -1, the loading voltage is calculated according to the first formula, the above first formula is U L =U0+dUL , U L represents the above-mentioned loading voltage, U0 represents the initial voltage of the above-mentioned typical electrode at the initial loading, dU L represents a set adjustment value, the above-mentioned loading voltage is the voltage applied to the above-mentioned typical electrode of the power equipment;

[0074] Step S2023, a first input step, performing electric field calculation and extraction on the air gap of the typical electrode to obtain a current first electric field feature set, and re-inputting the current first electric field feature set into the breakdown voltage determination model to obtain a first current interval feature value, wherein the first current interval feature value is the interval feature value obtained by re-inputting the current first electric field feature set into the breakdown voltage determination model;

[0075] Step S2024, repeating the first calculation step and the first input step in sequence until the current interval characteristic value is 1, and determining the current loading voltage as the target breakdown voltage.

[0076] In the above embodiment, if the interval characteristic value of the breakdown voltage determination model is -1, it means that the air gap has not been broken down at this time, then the loading voltage is increased, that is, the loading voltage U L =U0+dU L , and then recalculate the electric field of the air gap of the typical electrode, and extract the electric field feature set and input it into the breakdown voltage determination model until the interval eigenvalue of the breakdown voltage determination model is 1. At this time, the loading voltage U is the breakdown voltage of the electrode to be predicted.

[0077] In order to accurately determine the breakdown voltage of the air gap, in an optional implementation manner, after step S2021, the method further includes:

[0078] Step S501, a second calculation step, in which, when the interval characteristic value is 1, the loading voltage is calculated according to a second formula, where U L =U0-dU L ;

[0079] Step S502, a second input step, performing electric field calculation on the air gap of the typical electrode to extract a current second electric field feature set, and re-inputting the current second electric field feature set into the breakdown voltage determination model to obtain a current second interval feature value, wherein the current second interval feature value is the interval feature value obtained by re-inputting the current second electric field feature set into the breakdown voltage determination model;

[0080] Step S503, repeating the second calculation step and the second input step in sequence until the current interval characteristic value is -1, and determining the sum of the current loading voltage and the set adjustment value as the target breakdown voltage.

[0081] In the above embodiment, if the interval characteristic value of the breakdown voltage determination model is 1 when loading U0, the loading voltage is reduced, that is, the loading voltage U L =U0-dU L , the electric field of the air gap of the typical electrode is recalculated, and the electric field feature set is extracted and input into the breakdown voltage determination model until the interval characteristic value of the breakdown voltage determination model is -1. At this time, the loading voltage corresponding to the lower limit of the voltage interval with the interval characteristic value of 1 is the breakdown voltage. That is, the breakdown voltage of the electrode to be predicted is the current loading voltage and dU L The sum of dU L Can be set and adjusted by yourself.

[0082] In order to ensure that the insulation characteristics of the air gap meet the requirements, in an optional implementation manner, after the above step S202, the method further includes:

[0083] Step S601: When the target breakdown voltage is greater than or equal to the set voltage, it is determined that the insulation characteristics of the air gap meet the relay protection requirements.

[0084] In the above embodiment, the breakdown voltage predicted by the breakdown voltage determination model (i.e., the above target breakdown voltage) is compared with the set voltage of the system. If the above target breakdown voltage is higher than or equal to the design voltage, it can be considered that the insulation characteristics of the open gap are sufficient to meet the protection requirements.

[0085] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0086] The embodiment of the present application also provides a device for determining the breakdown voltage of an air gap. It should be noted that the device for determining the breakdown voltage of an air gap in the embodiment of the present application can be used to execute the method for determining the breakdown voltage of an air gap provided in the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and those that have been described will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0087] The following is an introduction to the device for determining the breakdown voltage of an air gap provided in an embodiment of the present application.

[0088] Figure 4 is a structural block diagram of a device for determining an air gap breakdown voltage according to an embodiment of the present application. Figure 4 As shown, the device comprises:

[0089] The acquisition unit 10 is used to acquire air gap data, wherein the air gap data includes an electric field feature set formed by multiple electric field feature quantities, wherein the electric field feature set includes at least the electric field feature quantity of the discharge channel area, the electric field feature quantity of the electrode surface area, and the electric field feature quantity of the external non-breakdown area, wherein the electric field feature quantity includes at least electric field intensity, electric field energy, energy density, surface area of ​​an electric field intensity unit, electric field gradient, path length and proportional parameter of an electric field intensity unit.

[0090] Specifically, air gaps of typical electrodes with different structures are tested and electric field calculations are performed to obtain air gap data.

[0091] It should also be noted that the air gap breakdown discharge path has a large degree of randomness and is difficult to accurately determine, so the electric field gradient characteristic class on the shortest path is used to characterize the gap structure and does not represent the discharge path in the actual physical process. Therefore, the specific discharge path does not affect the prediction results of the method of the present invention. The following electric field characteristic quantity classes are defined in terms of physical quantities and dimensions: electric field intensity, electric field energy, energy density, surface area, electric field gradient, path length and proportional parameters, etc. The specific electric field characteristic quantity definitions are as follows: Maximum electric field intensity: E m =maxE i (i=1,2,…,n), where E i is the average value of the electric field strength of the i-th spatial unit, and n is the total number of units. Average value of electric field strength: Electric field strength distortion rate: Total electric field energy W: Where ε0 is the dielectric constant of vacuum, V i is the volume of the i-th space unit. Total volume V: Energy density W d : The volume ratio of the area with a maximum electric field strength exceeding x% V rx : Where V xi is the volume of the i-th unit with an electric field strength exceeding x%, and xn is the total number of units with an electric field strength exceeding x%. The energy ratio of the area with an electric field strength exceeding x% is W rx : Where W xi is the energy of the i-th unit that exceeds x% of the maximum electric field strength. Total surface area S: In the formula, S i is the surface area of ​​the ith unit, and n is the total number of units. The proportion of the surface area occupied by the area with a maximum electric field strength exceeding x% S rx : In the formula, S xi is the surface area of ​​the ith unit with an electric field strength exceeding x%. The electric field strength E′: E′=|-gradE|, where E is the electric field strength at a certain point, a scalar. The proportion of the path length of the area with an electric field strength exceeding x% L rx : Where, L xi is the discharge shortest path length of the i-th unit exceeding x% of the maximum electric field strength, and L is the total discharge shortest path length. The above-mentioned proportional parameters include V rx , W rx , S rx and L rx .

[0092] The input-output unit 20 is used to input the above-mentioned air gap data into the breakdown voltage determination model and output the target breakdown voltage. The above-mentioned breakdown voltage determination model is a convergence model obtained by training a predetermined model using multiple groups of training data, and each group of the above-mentioned training data includes a sample electric field feature set and a sample breakdown voltage.

[0093] Specifically, XGBOOST is used to establish a breakdown voltage prediction model, and training is performed to obtain a breakdown voltage determination model, which takes the electric field feature set as input and the breakdown voltage as output. Therefore, the air gap data is input into , and the breakdown voltage determination model is used for calculation, and the target breakdown voltage can be output.

[0094] The first determination unit 30 determines that the insulation characteristics of the air gap do not meet the relay protection requirement when the target breakdown voltage is less than the set voltage.

[0095] Specifically, based on the target breakdown voltage, determine whether the insulation properties of the air gap meet the protection needs. If the predicted breakdown voltage is lower than the design voltage, it indicates that the insulation properties of the air gap may be insufficient, there is a safety risk, and improvement measures need to be taken.

[0096] In this embodiment, an acquisition unit is used to acquire air gap data, the air gap data includes an electric field feature set formed by multiple electric field feature quantities, the electric field feature set includes at least the electric field feature quantity of the discharge channel area, the electric field feature quantity of the electrode surface area, and the electric field feature quantity of the external non-breakdown area, the electric field feature quantity includes at least electric field strength, electric field energy, energy density, surface area of ​​the electric field strength unit, electric field gradient, path length and proportional parameter of the electric field strength unit; an input-output unit is used to input the air gap data into a breakdown voltage determination model, and output a target breakdown voltage, the breakdown voltage determination model is a convergence model obtained by training a predetermined model using multiple groups of training data, and each group of the training data includes a sample electric field feature set and a sample breakdown voltage; a first determination unit is used to determine that the insulation characteristics of the air gap do not meet the relay protection requirements when the target breakdown voltage is less than the set voltage. This application uses the typical electrode air gap data obtained from the experiment as the training set and test set of the model to perform breakdown voltage prediction training, and can obtain the breakdown voltage determination model of the air gap. By obtaining the air gap data to be predicted in real time and inputting it into the breakdown voltage determination model, the prediction result, that is, the target breakdown voltage, is obtained to determine whether the insulation characteristics of the air gap meet the relay protection requirements. Further, it provides guiding suggestions for the insulation protection of power system equipment and the safe and economical operation of the power grid. This application solves the problem that the existing technology mainly relies on experimental data, and the experimental research on the breakdown characteristics of the air gap has a long cycle and high cost, resulting in low accuracy of the prediction results.

[0097] In order to reduce the number of tests required for the external insulation design to obtain the electric field feature set, in an optional implementation, the device further includes:

[0098] A test unit, used for inputting the air gap data into a breakdown voltage determination model to output a target breakdown voltage before performing a breakdown test on the air gaps of different typical electrodes to obtain breakdown voltage data corresponding to each of the typical electrodes;

[0099] A determination unit, configured to determine a breakdown interval and a non-breakdown interval corresponding to each of the typical electrodes according to the breakdown voltage data;

[0100] A first calculation unit is used to perform electric field calculation on the breakdown interval and the non-breakdown interval corresponding to different typical electrodes to obtain a plurality of electric field characteristic quantities;

[0101] The preprocessing unit is used to perform a preprocessing operation on the plurality of electric field feature quantities to obtain the sample electric field feature set.

[0102] In the above embodiment, the breakdown test is performed on the air gap of typical electrodes with different structures to obtain the breakdown voltage data. For example, the measured breakdown voltage is U, and [90%U, U] is defined as the non-breakdown interval, and the characteristic value is -1; [U, 110%U] is defined as the breakdown interval, and the characteristic value is 1. For the initial loading voltage U0 of typical electrodes with different structures, the corresponding non-breakdown interval and breakdown voltage interval are loaded respectively to perform electric field calculation, and the electric field characteristic quantity is obtained, and then the electric field characteristic set corresponding to each loading voltage is obtained through preprocessing. By exploring the influence of different gap structures, voltage waveforms and environmental factors on the breakdown characteristics in actual power transmission and transformation projects, a data set is obtained, and the breakdown characteristics of the air gap are calculated or predicted, and used to guide the external insulation design of the power transmission and transformation project, so as to achieve the goal of reducing the number of tests required for the external insulation design.

[0103] In order to reduce the computational complexity and speed up the convergence of the model, in an optional implementation, the preprocessing unit includes:

[0104] A normalization module is used to normalize each of the above electric field characteristic quantities to obtain a normalized electric field characteristic quantity;

[0105] The dimension reduction module uses principal component analysis to perform dimension reduction processing on the normalized electric field feature quantity to obtain the sample electric field feature set.

[0106] In the above embodiment, in order to reduce the computational complexity and improve the computational efficiency, the electric field feature set can be subjected to dimensionality reduction processing. In order to eliminate the influence of different orders of magnitude and dimensions and to speed up the training and convergence speed of the model, the electric field feature set needs to be normalized. Before the electric field feature set is subjected to dimensionality reduction processing, each feature quantity needs to be normalized to eliminate the influence of different orders of magnitude and dimensions, reduce the influence of improper data processing on the prediction effect, and speed up the training and convergence speed of the prediction model. The normalization method is: In the formula, x′ i is a characteristic quantity x in the electric field characteristic set i The normalized value, x max is the maximum value of the feature value, x min is the minimum value of the feature quantity. At this time, the feature quantity x i By [x max , x min ] is normalized to [0,1].

[0107] Principal component analysis is a commonly used feature dimensionality reduction method. It is a multivariate statistical method that tries to regroup multiple indicators with strong correlation based on the mathematical idea of ​​dimensionality reduction to obtain a few independent comprehensive indicators and replace the original multiple indicators. The regrouped comprehensive indicators are usually called principal components. The principal component analysis method mainly includes the following steps: (1) Calculate the correlation coefficient matrix based on the normalized data table: R = (r ij ) p×p , where p is the characteristic dimension. (2) Calculate the eigenvalue and eigenvector of R. Solve the characteristic equation |R-λI|=0 to obtain the characteristic root λ, and arrange them from large to small as λ1, λ2, …, λ p , and the corresponding eigenvectors u1, u2, …, u p , I in the characteristic equation represents the unit matrix. (3) Calculate the variance contribution rate e i And the cumulative variance contribution rate P. (4) Take the first k principal components corresponding to the eigenvalues ​​whose cumulative variance contribution rate reaches a predetermined value P (0.85<P<0.95) to obtain the above sample electric field feature set. The calculation formula for the cumulative variance contribution rate of the principal component is: In the formula, k is the number of principal components, p is the original characteristic number, k≤p, λ i is the eigenvalue of the i-th principal component.

[0108] In order to improve the accuracy of classification and recognition, in an optional implementation manner, the device further includes:

[0109] A construction unit is used to construct an initial breakdown voltage determination model before inputting the air gap data into the breakdown voltage determination model and outputting a target breakdown voltage, and initialize model parameters of the initial breakdown voltage determination model, wherein the initial breakdown voltage determination model is an XGBoost model to be trained, and the model parameters at least include a classifier type, a weight of a positive sample, a number of decision trees, a maximum depth of the decision tree, a learning rate, and a penalty coefficient;

[0110] A training unit, used to perform a training step, inputting a plurality of groups of the above sample electric field feature sets into the above initial breakdown voltage determination model for training, and obtaining an intermediate breakdown voltage determination model, wherein the above intermediate breakdown voltage determination model is a model obtained after the above initial breakdown voltage determination model is trained;

[0111] A testing unit, used for executing the testing step, inputting multiple groups of test electric field feature sets into the above-mentioned initial breakdown voltage determination model for testing, so as to obtain the accuracy of the above-mentioned intermediate breakdown voltage determination model, wherein each group of the above-mentioned test electric field feature sets includes a test electric field feature quantity and a test breakdown voltage;

[0112] The first repetition unit is used to re-execute the above-mentioned training step and the above-mentioned testing step at least once when the above-mentioned accuracy rate is less than the set accuracy rate, until the above-mentioned accuracy rate is greater than or equal to the above-mentioned set accuracy rate or the number of iterations reaches the maximum set number of iterations, and the above-mentioned intermediate breakdown voltage determination model is determined as the above-mentioned breakdown voltage determination model, and the above-mentioned number of iterations is the number of iterative trainings performed on the above-mentioned initial breakdown voltage determination model.

[0113] In the above embodiment, when training the XGBOOST model, the main purpose is to determine the best tree structure. The core problem is to find an optimal split node. The greedy algorithm used in the splitting is used to calculate the gain before and after the split to determine whether the node needs to be split. Then, the various parameters of the model are iteratively optimized based on the objective function. The XGBOOST model is finally obtained by training according to the above process. The training process is as follows Figure 3 shown.

[0114] The XGBOOST model contains a large number of parameters, which can be generally divided into three categories: the first category is the conventional parameters that control some macro functions, such as the classifier type, the weight of positive samples, etc.; the second category is the model parameters related to the structure of the tree, such as the number of decision trees, the maximum depth of the tree, etc.; the third category is the target parameters for learning in the model, such as the learning rate, the penalty coefficient, etc. When modeling the XGBOOST model, these parameters can be reasonably set to determine the optimal parameters, thereby improving the accuracy of classification and recognition.

[0115] The maximum number of trees is n_estimator. If the number of trees is too small, the learning ability of the model may be insufficient, reducing the prediction ability; if the number of trees is too large, although the learning ability is extremely high, overfitting may occur. In order to quantitatively evaluate the quality of the classification prediction model, the accuracy rate is used as the evaluation index of the model. The calculation formula is as follows: Where n is the total number of test samples; n p is the number of correct classifications. The accuracy is positively correlated with the model classification and recognition effect, that is, the higher the accuracy, the better the model classification effect.

[0116] The maximum depth of the tree, max_depth, also directly affects the prediction results. If the value is too small, the tree depth will be insufficient, which will make the classification less rigorous and reduce the prediction accuracy. If the value is too large, over-learning will occur, and the prediction accuracy will only be slightly improved, but the calculation rate will be greatly reduced. The control variable method can be used to determine this parameter, setting the range of max_depth to 1 to 10, comparing the classification accuracy at each depth, and selecting the max_depth with the highest classification accuracy as the maximum depth of the model tree.

[0117] The learning rate eta is based on the idea that each step is a small step and gradually approaches the result, which is better than taking a big step directly to approach the result. In other words, do not trust a certain tree, but only learn part of the tree. The learning rate is used to control the weight of the leaf node to adjust the influence of the tree on the result. When the learning rate is small, that is, the weight of the current leaf node becomes smaller, the influence of the tree on the final prediction result will also become smaller. Usually, the learning rate will not be too large to prevent overfitting. Select the learning rate value between 0 and 1, with an interval of 0.05, obtain the prediction accuracy under different learning rates, and compare the classification accuracy values ​​to determine the optimal learning rate.

[0118] The minimum weight of the leaf, min_child_weight, is used to determine whether the current leaf node needs to be split. If the current weight of a leaf node is less than the set minimum weight, the split is stopped. The smaller this value is, the more likely it is to overfit. Based on the maximum number of trees, maximum depth, and learning rate determined above, set the value of min_child_weight to vary in the range of 0 to 10, and observe the accuracy under different minimum weights to determine the minimum weight of the leaf.

[0119] It should also be noted that as an integrated tree model, the XGBOOST model contains multiple CART trees, and its output is the sum of multiple trees, and this value is used as the predicted value of the XGBOOST model. Its mathematical expression is as follows: Where K is the number of CART trees; F is a possible CART tree; fk represents a specific CART tree; is the output of the XGBOOST model. For a given sample length of n and the number of features of m, we have: D = {(x i ,y i )}(|D|=n,x i ∈R m ,y i ∈R), where x i represents the i-th sample input; y i represents the output corresponding to the i-th sample input; F is the space of the CART tree, which can be expressed as: F = {f(x) = w q (x)}(q:R m →T, w∈R T ), where q represents the structure of the CART tree; T is the number of child nodes of the CART tree; f(x) is the CART tree structure q and the child node weight w; the establishment of the XGBOOST model is to learn the CART tree and determine the structure and weight of the tree. Bringing the regularization term into the objective function, we have: In the formula, and yi represent the predicted value and actual label value of the ith sample respectively; γ and λ are weight coefficients; the first half of F(Φ) is the loss error, usually with mean square error and logistic regression, and the second half is the regularization term, which is usually used to constrain the depth of the CART tree, reduce the complexity of the tree, and prevent overfitting. When establishing the XGBOOST model to solve practical problems, the purpose is to obtain the optimal coefficients so that the predicted value is as close to the true value as possible, and the model has good generalization ability and calculation rate, so that the model has good versatility. When training the model, it is promoted in an additive manner, then: in, is the t-th round XGBOOST model; for The prediction model of the previous round; f t (x i ) is a newly added function. During training, the newly added function is added to the tth round. At this time, a constant term C is added based on the cumulative difference between the predicted value and the actual value. The objective function at this time can be expressed as: Taylor expansion of the above formula:

[0120]

[0121] Since the residual of the CART tree is obtained by subtracting the tth tree from the previous tree, the predicted value of the t-1th tree is known to be l That is, the part in the Taylor expansion is a certain value and does not affect the optimization calculation of the objective function. It can be incorporated into the constant term or directly removed. Therefore, the objective function can be expressed as:

[0122]

[0123] The above section explains the relationship between error and objective function. Next, we will explain how the regularization term added in XGBOOST defines the complexity of the CART tree. Transform the objective function:

[0124]

[0125]

[0126] At this time, two regularization terms, the number of leaf nodes T and the leaf node score w, are added to the objective function. Therefore, the objective function part of the regularization term also adds two cumulative parts, the number of samples and the number of leaf nodes. The two cumulative terms in the above formula are expressed as G j and H j To replace, the above formula can be simplified to: Reverse the above formula to w j Taking the derivative and setting it equal to 0, we get: Finally, w j The optimal solution of is brought into the objective function, and we can get: From the above formula, we can see that if the structure of the tree is determined, the score of the structure is only related to the first-order and second-order derivatives of the structure, and the score is negatively correlated with the structure, that is, the smaller the score, the better the structure, and vice versa. In addition, to determine the structure of a tree, we also need to pay attention to the node division of the tree and the conditions for the tree to stop growing.

[0127] 1) Node division: Regarding node division, XGBOOST does not use the inefficient enumeration method, but uses a greedy algorithm to replace the enumeration method, starting from a single child node and iteratively splitting it into tree nodes. After the node is split, the loss function is as follows: The three items in the above formula are the scores of the left tree, the right tree and the score when no split is performed. The loss function value is determined by these three items. Among them, λ is not only used to control the complexity of the tree, but also used as a threshold to determine whether the split is performed. If the gain after the split is greater than λ at this time, then the split is performed, otherwise it is not performed.

[0128] 2) Stop growing: The tree cannot grow indefinitely, which will increase the complexity of the tree. At this time, certain constraints should be required to constrain the growth of the tree so that the tree stops growing automatically. If the objective function value F of the child node after a new split is loss Less than 0, the split will be abandoned. This is a balance between the loss value and the complexity of the model structure. In addition, when the depth of the tree reaches the set maximum depth, the split of the child node will stop and the tree will no longer be built. The depth of the tree is related to whether the model will be underfitting. It is necessary to optimize the depth of the tree to determine the appropriate depth of the tree. When a child node splits, the weight coefficients of the left and right leaf nodes will be updated. If any child node weight coefficient is less than a set threshold, the split will be abandoned. Here, it is necessary to optimize another parameter of the model, the minimum child node 12-point weight, and then determine the depth of the tree and the weight of the child node.

[0129] In order to accurately determine the breakdown voltage of the air gap, in an optional implementation manner, the input-output unit includes:

[0130] A first input module inputs the air gap data into a breakdown voltage determination model to obtain an interval characteristic value, wherein the interval characteristic value is an intermediate variable in the calculation process of the breakdown voltage determination model, and the interval characteristic value is -1 or 1. When the interval characteristic value is 1, it indicates that the air gap is broken down, and when the interval characteristic value is -1, it indicates that the air gap is not broken down;

[0131] The first calculation module is used to perform the first calculation step. When the characteristic value of the above interval is -1, the loading voltage is calculated according to the first formula. The above first formula is U L =U0+dU L , U L represents the above-mentioned loading voltage, U0 represents the initial voltage of the above-mentioned typical electrode at the initial loading, dU L represents a set adjustment value, the above-mentioned loading voltage is the voltage applied to the above-mentioned typical electrode of the power equipment;

[0132] A second input module is used to execute the first input step, perform electric field calculation and extraction on the air gap of the typical electrode to obtain a current first electric field feature set, and re-input the current first electric field feature set into the breakdown voltage determination model to obtain a first current interval feature value, wherein the first current interval feature value is the interval feature value obtained by re-inputting the current first electric field feature set into the breakdown voltage determination model;

[0133] The repetition module repeats the first calculation step and the first input step in sequence until the current interval characteristic value is 1, and determines the current loading voltage as the target breakdown voltage.

[0134] In the above embodiment, if the interval characteristic value of the breakdown voltage determination model is -1, it means that the air gap has not been broken down at this time, then the loading voltage is increased, that is, the loading voltage U L =U0+dU L , and then recalculate the electric field of the air gap of the typical electrode, and extract the electric field feature set and input it into the breakdown voltage determination model until the interval eigenvalue of the breakdown voltage determination model is 1. At this time, the loading voltage U is the breakdown voltage of the electrode to be predicted.

[0135] In order to accurately determine the breakdown voltage of the air gap, in an optional implementation manner, the device further includes:

[0136] The second calculation unit is used to perform a second calculation step, after inputting the air gap data into the breakdown voltage determination model to obtain the interval characteristic value, when the interval characteristic value is 1, calculate the loading voltage according to a second formula, wherein the second formula is U L =U0-dU L ;

[0137] An input unit, used to execute a second input step, perform electric field calculation on the air gap of the typical electrode to extract a current second electric field feature set, and re-input the current second electric field feature set into the breakdown voltage determination model to obtain a current second interval feature value, wherein the current second interval feature value is the interval feature value obtained by re-inputting the current second electric field feature set into the breakdown voltage determination model;

[0138] The second repeating unit is used to sequentially repeat the second calculation step and the second input step until the current interval characteristic value is -1, and determine the sum of the current loading voltage and the set adjustment value as the target breakdown voltage.

[0139] In the above embodiment, if the interval characteristic value of the breakdown voltage determination model is 1 when loading U0, the loading voltage is reduced, that is, the loading voltage U L =U0-dU L , the electric field of the air gap of the typical electrode is recalculated, and the electric field feature set is extracted and input into the breakdown voltage determination model until the interval characteristic value of the breakdown voltage determination model is -1. At this time, the loading voltage corresponding to the lower limit of the voltage interval with the interval characteristic value of 1 is the breakdown voltage. That is, the breakdown voltage of the electrode to be predicted is the current loading voltage and dU L The sum of dU L Can be set and adjusted by yourself.

[0140] In order to ensure that the insulation properties of the air gap meet the requirements, in an optional implementation, the device further includes:

[0141] The second determination unit is used to input the air gap data into the breakdown voltage determination model, and after outputting the target breakdown voltage, when the target breakdown voltage is greater than or equal to the set voltage, determine that the insulation characteristics of the air gap meet the relay protection requirements.

[0142] In the above embodiment, the breakdown voltage predicted by the breakdown voltage determination model (i.e., the above target breakdown voltage) is compared with the set voltage of the system. If the above target breakdown voltage is higher than or equal to the design voltage, it can be considered that the insulation characteristics of the open gap are sufficient to meet the protection requirements.

[0143] The air gap breakdown voltage determination device includes a processor and a memory, wherein the acquisition unit, the input / output unit, the first determination unit, etc. are stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions. The modules are all located in the same processor; or, the modules are located in different processors in any combination.

[0144] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the kernel parameters can be adjusted to solve the problem that the existing technology mainly relies on experimental data, and the experimental research on the breakdown characteristics of air gaps has a long cycle and high cost, resulting in low accuracy of prediction results.

[0145] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0146] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, a device where the computer-readable storage medium is located is controlled to execute the method for determining the air gap breakdown voltage.

[0147] Specifically, the method for determining the air gap breakdown voltage includes:

[0148] Step S201, acquiring air gap data, the air gap data including an electric field feature set formed by a plurality of electric field feature quantities, the electric field feature set including at least the electric field feature quantity of the discharge channel region, the electric field feature quantity of the electrode surface region, and the electric field feature quantity of the external non-breakdown region, the electric field feature quantity including at least the electric field intensity, the electric field energy, the energy density, the surface area of ​​the electric field intensity unit, the electric field gradient, the path length of the electric field intensity unit and the proportional parameter;

[0149] Step S202, inputting the air gap data into a breakdown voltage determination model, and outputting a target breakdown voltage, wherein the breakdown voltage determination model is a convergence model obtained by training a predetermined model using multiple sets of training data, and each set of the training data includes a sample electric field feature set and a sample breakdown voltage;

[0150] Step S203: when the target breakdown voltage is less than the set voltage, it is determined that the insulation characteristics of the air gap do not meet the relay protection requirements.

[0151] An embodiment of the present invention provides a processor, and the processor is used to run a program, wherein the method for determining the air gap breakdown voltage is executed when the program is run.

[0152] Specifically, the method for determining the air gap breakdown voltage includes:

[0153] Step S201, acquiring air gap data, the air gap data including an electric field feature set formed by a plurality of electric field feature quantities, the electric field feature set including at least the electric field feature quantity of the discharge channel region, the electric field feature quantity of the electrode surface region, and the electric field feature quantity of the external non-breakdown region, the electric field feature quantity including at least the electric field intensity, the electric field energy, the energy density, the surface area of ​​the electric field intensity unit, the electric field gradient, the path length of the electric field intensity unit and the proportional parameter;

[0154] Step S202, inputting the air gap data into a breakdown voltage determination model, and outputting a target breakdown voltage, wherein the breakdown voltage determination model is a convergence model obtained by training a predetermined model using multiple sets of training data, and each set of the training data includes a sample electric field feature set and a sample breakdown voltage;

[0155] Step S203: when the target breakdown voltage is less than the set voltage, it is determined that the insulation characteristics of the air gap do not meet the relay protection requirements.

[0156] An embodiment of the present invention provides an air gap breakdown voltage management system, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, at least the following steps are implemented:

[0157] Step S201, acquiring air gap data, the air gap data including an electric field feature set formed by a plurality of electric field feature quantities, the electric field feature set including at least the electric field feature quantity of the discharge channel region, the electric field feature quantity of the electrode surface region, and the electric field feature quantity of the external non-breakdown region, the electric field feature quantity including at least the electric field intensity, the electric field energy, the energy density, the surface area of ​​the electric field intensity unit, the electric field gradient, the path length of the electric field intensity unit and the proportional parameter;

[0158] Step S202, inputting the air gap data into a breakdown voltage determination model, and outputting a target breakdown voltage, wherein the breakdown voltage determination model is a convergence model obtained by training a predetermined model using multiple sets of training data, and each set of the training data includes a sample electric field feature set and a sample breakdown voltage;

[0159] Step S203: when the target breakdown voltage is less than the set voltage, it is determined that the insulation characteristics of the air gap do not meet the relay protection requirements.

[0160] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initializing at least the following method steps:

[0161] Step S201, acquiring air gap data, the air gap data including an electric field feature set formed by a plurality of electric field feature quantities, the electric field feature set including at least the electric field feature quantity of the discharge channel region, the electric field feature quantity of the electrode surface region, and the electric field feature quantity of the external non-breakdown region, the electric field feature quantity including at least the electric field intensity, the electric field energy, the energy density, the surface area of ​​the electric field intensity unit, the electric field gradient, the path length of the electric field intensity unit and the proportional parameter;

[0162] Step S202, inputting the air gap data into a breakdown voltage determination model, and outputting a target breakdown voltage, wherein the breakdown voltage determination model is a convergence model obtained by training a predetermined model using multiple sets of training data, and each set of the training data includes a sample electric field feature set and a sample breakdown voltage;

[0163] Step S203: when the target breakdown voltage is less than the set voltage, it is determined that the insulation characteristics of the air gap do not meet the relay protection requirements.

[0164] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0165] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0166] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0167] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0168] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0169] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0170] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0171] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0172] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0173] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0174] 1) The method for determining the breakdown voltage of an air gap of the present application comprises: first, obtaining air gap data, wherein the air gap data comprises an electric field feature set formed by a plurality of electric field feature quantities, wherein the electric field feature set comprises at least the electric field feature quantity of the discharge channel region, the electric field feature quantity of the electrode surface region, and the electric field feature quantity of the external non-breakdown region, wherein the electric field feature quantity comprises at least the electric field intensity, the electric field energy, the energy density, the surface area of ​​the electric field intensity unit, the electric field gradient, the path length and the proportional parameter of the electric field intensity unit; then, inputting the air gap data into a breakdown voltage determination model, and outputting a target breakdown voltage, wherein the breakdown voltage determination model is a convergence model obtained by training a predetermined model using a plurality of sets of training data, and each set of the training data comprises a sample electric field feature set and a sample breakdown voltage; finally, when the target breakdown voltage is less than the set voltage, determining that the insulation characteristics of the air gap do not meet the relay protection requirements. This application uses the typical electrode air gap data obtained from the experiment as the training set and test set of the model to perform breakdown voltage prediction training, and can obtain the breakdown voltage determination model of the air gap. By obtaining the air gap data to be predicted in real time and inputting it into the breakdown voltage determination model, the prediction result, that is, the target breakdown voltage, is obtained to determine whether the insulation characteristics of the air gap meet the relay protection requirements. Further, it provides guiding suggestions for the insulation protection of power system equipment and the safe and economical operation of the power grid. This application solves the problem that the existing technology mainly relies on experimental data, and the experimental research on the breakdown characteristics of the air gap has a long cycle and high cost, resulting in low accuracy of the prediction results.

[0175] 2) The air gap breakdown voltage determination device of the present application, an acquisition unit, used to acquire air gap data, the above-mentioned air gap data includes an electric field feature set formed by multiple electric field feature quantities, the above-mentioned electric field feature set includes at least the electric field feature quantity of the discharge channel area, the electric field feature quantity of the electrode surface area, and the electric field feature quantity of the external non-breakdown area, the above-mentioned electric field feature quantity includes at least electric field strength, electric field energy, energy density, surface area of ​​the electric field strength unit, electric field gradient, path length and proportional parameter of the electric field strength unit; an input-output unit, used to input the above-mentioned air gap data into a breakdown voltage determination model, and output a target breakdown voltage, the above-mentioned breakdown voltage determination model is a convergence model obtained by training a predetermined model using multiple groups of training data, and each group of the above-mentioned training data includes a sample electric field feature set and a sample breakdown voltage; a first determination unit, used to determine that the insulation characteristics of the air gap do not meet the relay protection requirements when the above-mentioned target breakdown voltage is less than the set voltage. This application uses the typical electrode air gap data obtained from the experiment as the training set and test set of the model to perform breakdown voltage prediction training, and can obtain the breakdown voltage determination model of the air gap. By obtaining the air gap data to be predicted in real time and inputting it into the breakdown voltage determination model, the prediction result, that is, the target breakdown voltage, is obtained to determine whether the insulation characteristics of the air gap meet the relay protection requirements. Further, it provides guiding suggestions for the insulation protection of power system equipment and the safe and economical operation of the power grid. This application solves the problem that the existing technology mainly relies on experimental data, and the experimental research on the breakdown characteristics of the air gap has a long cycle and high cost, resulting in low accuracy of the prediction results.

[0176] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for determining an air gap breakdown voltage, characterized in that: include: Acquire air gap data, the air gap data including an electric field feature set formed by a plurality of electric field feature quantities, the electric field feature set including at least electric field feature quantities of a discharge channel region, electric field feature quantities of an electrode surface region, and electric field feature quantities of an external non-breakdown region, the electric field feature quantities including at least electric field intensity, electric field energy, energy density, surface area of ​​an electric field intensity unit, electric field gradient, path length of an electric field intensity unit, and a proportional parameter; Inputting the air gap data into a breakdown voltage determination model, and outputting a target breakdown voltage, wherein the breakdown voltage determination model is a convergence model obtained by training a predetermined model using multiple sets of training data, each set of the training data including a sample electric field feature set and a sample breakdown voltage; When the target breakdown voltage is less than the set voltage, it is determined that the insulation characteristics of the air gap do not meet the relay protection requirements.

2. The method according to claim 1, characterized in that Before inputting the air gap data into a breakdown voltage determination model to output a target breakdown voltage, the method further includes: Performing a breakdown test on the air gaps of different typical electrodes to obtain breakdown voltage data corresponding to each of the typical electrodes; Determine the breakdown interval and non-breakdown interval corresponding to each of the typical electrodes according to the breakdown voltage data; Loading the corresponding breakdown interval and non-breakdown interval on different typical electrodes respectively to perform electric field calculation to obtain a plurality of electric field characteristic quantities; A preprocessing operation is performed on the plurality of electric field feature quantities to obtain the sample electric field feature set.

3. The method according to claim 1, characterized in that Performing a preprocessing operation on the plurality of electric field feature quantities to obtain the sample electric field feature set includes: Normalizing each of the electric field characteristic quantities to obtain a normalized electric field characteristic quantity; The principal component analysis method is used to perform dimension reduction processing on the normalized electric field feature quantity to obtain the sample electric field feature set.

4. The method according to claim 1, characterized in that: Before inputting the air gap data into a breakdown voltage determination model to output a target breakdown voltage, the method further includes: Constructing an initial breakdown voltage determination model and initializing model parameters of the initial breakdown voltage determination model, wherein the initial breakdown voltage determination model is an XGBoost model to be trained, and the model parameters include at least a classifier type, a weight of a positive sample, the number of decision trees, a maximum depth of the decision tree, a learning rate, and a penalty coefficient; A training step, inputting a plurality of groups of the sample electric field feature sets into the initial breakdown voltage determination model for training to obtain an intermediate breakdown voltage determination model, wherein the intermediate breakdown voltage determination model is a model obtained after the initial breakdown voltage determination model is trained; A testing step, inputting multiple groups of test electric field feature sets into the initial breakdown voltage determination model for testing to obtain the accuracy of the intermediate breakdown voltage determination model, each group of the test electric field feature sets including a test electric field feature quantity and a test breakdown voltage; When the accuracy rate is lower than the set accuracy rate, the training step and the testing step are re-executed at least once until the accuracy rate is greater than or equal to the set accuracy rate or the number of iterations reaches the maximum set number of iterations, and the intermediate breakdown voltage determination model is determined as the breakdown voltage determination model, and the number of iterations is the number of iterative trainings performed on the initial breakdown voltage determination model.

5. The method according to claim 2, characterized in that: Inputting the air gap data into a breakdown voltage determination model and outputting a target breakdown voltage includes: Inputting the air gap data into a breakdown voltage determination model to obtain an interval characteristic value, wherein the interval characteristic value is an intermediate variable of the breakdown voltage determination model in a calculation process, and the interval characteristic value is -1 or 1. When the interval characteristic value is 1, it indicates that the air gap is broken down, and when the interval characteristic value is -1, it indicates that the air gap is not broken down; In the first calculation step, when the interval characteristic value is -1, the loading voltage is calculated according to the first formula, wherein the first formula is U L =U0+dU L , U L represents the loading voltage, U0 represents the initial voltage of the typical electrode at the initial loading, dU L represents a set adjustment value, wherein the loading voltage is a voltage applied to the typical electrode of the power equipment; A first input step is to perform electric field calculation and extraction on the air gap of the typical electrode to obtain a current first electric field feature set, and re-input the current first electric field feature set into the breakdown voltage determination model to obtain a first current interval feature value, wherein the first current interval feature value is the interval feature value obtained by re-inputting the current first electric field feature set into the breakdown voltage determination model; The first calculation step and the first input step are repeated in sequence until the current interval characteristic value is 1, and the current loading voltage is determined as the target breakdown voltage.

6. The method according to claim 5, characterized in that After inputting the air gap data into a breakdown voltage determination model to obtain interval characteristic values, the method further includes: In the second calculation step, when the interval characteristic value is 1, the loading voltage is calculated according to a second formula, wherein the second formula is U L =U0-dU L ; A second input step is to perform electric field calculation on the air gap of the typical electrode to extract a current second electric field feature set, and re-input the current second electric field feature set into the breakdown voltage determination model to obtain a current second interval feature value, wherein the current second interval feature value is the interval feature value obtained by re-inputting the current second electric field feature set into the breakdown voltage determination model; The second calculation step and the second input step are sequentially repeated until the current interval characteristic value is -1, and the sum of the current loading voltage and the set adjustment value is determined as the target breakdown voltage.

7. The method according to claim 1, characterized in that After inputting the air gap data into a breakdown voltage determination model and outputting a target breakdown voltage, the method further includes: When the target breakdown voltage is greater than or equal to the set voltage, it is determined that the insulation characteristics of the air gap meet the relay protection requirements.

8. A device for determining an air gap breakdown voltage, characterized in that: The device comprises: an acquisition unit, configured to acquire air gap data, wherein the air gap data includes an electric field feature set formed by a plurality of electric field feature quantities, wherein the electric field feature set includes at least electric field feature quantities of a discharge channel region, electric field feature quantities of an electrode surface region, and electric field feature quantities of an external non-breakdown region, wherein the electric field feature quantities include at least electric field intensity, electric field energy, energy density, surface area of ​​an electric field intensity unit, electric field gradient, path length of an electric field intensity unit, and a proportional parameter; An input-output unit, used to input the air gap data into a breakdown voltage determination model and output a target breakdown voltage, wherein the breakdown voltage determination model is a convergence model obtained by training a predetermined model using multiple sets of training data, each set of training data including a sample electric field feature set and a sample breakdown voltage; The first determination unit is used to determine that the insulation characteristics of the air gap do not meet the relay protection requirements when the target breakdown voltage is less than the set voltage.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

10. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images