Polynomial vehicle-based insulator structure optimization method and device

Abstract

The invention provides an insulator structure optimization method and device based on a polynomial vehicle, and relates to the technical field of electrical engineering, and the method comprises the steps: obtaining first information and second information; carrying out correlation analysis on the icing thickness of the insulator in the first information and the second information; inputting preset target meteorological observation data into the insulator model, and optimizing the icing thickness of the insulator by adopting an optimization algorithm to obtain optimized initial insulator structure parameters and corresponding target icing layer thickness; and taking the initial insulator structure parameter as a target insulator structure parameter. According to the method, the meteorological data, the insulator structure parameters and the insulator icing thickness data are analyzed, the insulator structure model is constructed by using the polynomial proxy model, and training optimization is performed, so that the insulator structure can be effectively optimized, and accurate control of the target icing thickness is realized; and the structural performance of the insulator is evaluated through the physical model, so that the structural design reliability of the insulator is ensured, and the risk of icing flashover is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the field of electrical engineering technology, and in particular to a polynomial-based insulator structure optimization method, device, equipment and readable storage medium. Background Art

[0002] In the power system, the roof insulator is a key electrical component, and its performance directly affects the stability and safety of the power system. Especially in cold and snowy areas, the roof insulator is easily affected by icing, which leads to the degradation of insulation performance and even flashover accidents, posing a serious threat to the normal operation of the power system. Therefore, optimizing the structure of the roof insulator and improving its anti-icing ability have become issues that need to be solved urgently.

[0003] Traditionally, the design of roof insulators mainly relies on empirical formulas and experimental verification. This method is not only time-consuming and costly, but also difficult to fully consider the influence of multiple physical fields such as electric field distribution, thermal conduction, mechanical stress and ice thickness of insulators under different conditions. The accuracy of insulator structure optimization is not high. Therefore, we propose a structural optimization method for roof insulators to prevent ice flashover based on polynomials. Summary of the invention

[0004] The purpose of the present invention is to provide a polynomial-based insulator structure optimization method, device, equipment and readable storage medium to improve the above problems. In order to achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0005] In a first aspect, the present application provides an insulator structure optimization method based on a polynomial car, comprising:

[0006] Acquire first information and second information, wherein the first information includes meteorological observation data of an insulator working area, and the second information includes insulator structural parameters and insulator ice thickness;

[0007] Performing a correlation analysis on the ice thickness of the insulator in the first information and the second information to obtain analyzed first information, wherein the analyzed first information includes meteorological observation data that has a significant impact on the ice thickness of the insulator;

[0008] Training a preset polynomial proxy model based on the analyzed first information and the second information, and stopping the training when a preset loss function satisfies a set condition to obtain an insulator model;

[0009] The preset target meteorological observation data is input into the insulator model and the insulator ice thickness is optimized by using the optimization algorithm to obtain the optimized initial insulator structural parameters and the corresponding target ice thickness;

[0010] The initial insulator structural parameters and the target ice coating thickness are verified based on a preset physical model to obtain a verification result. When the verification result meets a preset condition, the initial insulator structural parameters are used as target insulator structural parameters.

[0011] In a second aspect, the present application also provides an insulator structure optimization device based on a polynomial vehicle, comprising:

[0012] an acquisition unit, configured to acquire first information and second information, wherein the first information includes meteorological observation data of an insulator working area, and the second information includes insulator structural parameters and insulator ice thickness;

[0013] an analysis unit, configured to perform a correlation analysis on the ice thickness of the insulator in the first information and the second information to obtain analyzed first information, wherein the analyzed first information includes meteorological observation data having a significant impact on the ice thickness of the insulator;

[0014] A training unit, used for training a preset polynomial proxy model based on the analyzed first information and the second information, and stopping the training when a preset loss function satisfies a set condition to obtain an insulator model;

[0015] An optimization unit is used to input preset target meteorological observation data into the insulator model and optimize the ice thickness of the insulator using an optimization algorithm to obtain optimized initial insulator structural parameters and corresponding target ice thickness;

[0016] A verification unit is used to verify the initial insulator structural parameters and the target ice coating thickness based on a preset physical model to obtain a verification result, and when the verification result meets a preset condition, the initial insulator structural parameters are used as target insulator structural parameters.

[0017] The beneficial effects of the present invention are:

[0018] The present invention analyzes meteorological data, insulator structural parameters and insulator ice thickness data, uses a polynomial proxy model to construct an insulator structural model and performs training optimization, which can effectively optimize the insulator structure to achieve precise control of the target ice thickness; and evaluates the insulator structural performance through a physical model, thereby ensuring the reliability of the insulator structural design and effectively reducing the risk of ice flashover.

[0019] Other features and advantages of the present invention will be set forth in the following description, and in part will become apparent from the description, or may be understood by practicing embodiments of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 It is a schematic flow chart of the insulator structure optimization method based on polynomial vehicle described in an embodiment of the present invention;

[0022] Figure 2 It is a schematic structural diagram of an insulator structure optimization device based on a polynomial car described in an embodiment of the present invention.

[0023] Markings in the figure:

[0024] 10. Acquisition unit; 20. Analysis unit; 30. Training unit; 40. Optimization unit; 50. Verification unit. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0026] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0027] Embodiment 1:

[0028] This embodiment provides an insulator structure optimization method based on a polynomial.

[0029] See also Figure 1 , the figure shows that the method includes step S10, step S20, step S30, step S40 and step S50.

[0030] Step S10. Acquire first information and second information, the first information including meteorological observation data of the insulator working area, and the second information including insulator structural parameters and insulator ice thickness;

[0031] Specifically, the corresponding ice thickness of insulators is collected when different insulator structural parameters work in different climate environments to provide data support for subsequent model training. The climate environment is the meteorological observation data that can be obtained from the public data of the meteorological station, usually including ambient temperature, ambient humidity, wind speed, wind direction, precipitation, and air pressure, etc.; the insulator structural parameters include the insulator shed curvature radius, shed upper inclination angle, shed lower inclination angle, shed spacing, and pole diameter; the insulator ice thickness is usually collected using an ultrasonic thickness gauge, and a camera can also be used to regularly shoot the icing of the roof insulator to record the shape changes of the icing.

[0032] Step S20: performing correlation analysis on the ice thickness of the insulator in the first information and the second information to obtain the analyzed first information, wherein the analyzed first information includes meteorological observation data having a significant impact on the ice thickness of the insulator;

[0033] Specifically, the meteorological observation data includes multiple meteorological related data, but in this application, only the meteorological related data that has a significant impact on the ice thickness of insulators is considered for subsequent model establishment, thereby effectively improving the accuracy and calculation efficiency of the model.

[0034] Specifically, step S20 specifically includes step S21, step S22, step S23, step S24, step S25 and step S26:

[0035] Step S21. The plurality of meteorological related data included in the first information are divided using a predetermined division strategy to obtain a plurality of division combinations, wherein the division strategy ensures that the combination of meteorological related data in each division combination is unique, and each meteorological related data can appear in a plurality of division combinations;

[0036] Specifically, a predetermined partitioning strategy is used to partition the meteorological data to form multiple unique partitioning combinations. The combination of meteorological data contained in each combination is unique, but each meteorological data can appear in multiple partitioning combinations. This partitioning strategy helps to comprehensively consider the impact of different meteorological data combinations on ice thickness, while avoiding ignoring certain specific data combinations.

[0037] Step S22. Bring each division combination into a preset feature conversion model for feature conversion to obtain a plurality of first feature vectors;

[0038] Specifically, through feature transformation, each partition combination can be effectively reduced in dimension and key features can be extracted, so as to better reflect the characteristic vector corresponding to the meteorological-related data contained in each partition combination, and provide more valuable data for subsequent correlation analysis and insulator structure optimization.

[0039] Step S23: Bring the ice coating thickness of the insulator in each second information into a preset feature extraction model to perform feature extraction, and obtain multiple second feature vectors;

[0040] Specifically, feature extraction of insulator ice thickness can capture the meteorological-related data that most significantly affects the insulator ice thickness, thereby helping to establish a more accurate insulator model.

[0041] Specifically, step S23 specifically includes step S231, step S232, step S233 and step S234:

[0042] Step S231: Divide the second information into multiple levels, and compare the importance of data corresponding to each level to construct a judgment matrix, where there is an inclusion relationship between the multiple levels;

[0043] Step S232. Calculate the weight of each level in the judgment matrix based on the hierarchical analysis method to determine the importance value of each data;

[0044] Step S233. Sort the data from large to small based on multiple importance values, and use the ice coating thickness of the insulators before the preset sorting position as feature information;

[0045] Step S234. Normalize all feature information to obtain multiple second feature vectors;

[0046] Specifically, the present application divides the insulator ice thickness data into multiple levels, and calculates the weights in combination with the hierarchical analysis method, so as to screen out the insulator ice thickness information that contributes the most to the features; extracts the key feature information by sorting, and normalizes it to generate a second feature vector for model training; thereby effectively highlighting important data, reducing redundant information, improving the accuracy of feature extraction and training efficiency, and ensuring the predictive performance and generalization ability of the constructed model.

[0047] Step S24. Perform correlation analysis based on the first feature vector of each partition combination and the second feature vector corresponding to each second information to obtain multiple correlation values;

[0048] Step S25. Determine the maximum correlation value from the multiple correlation values, and use all meteorological related data in the division combination corresponding to the maximum correlation value as target related data;

[0049] Step S26. Deleting the meteorological related data except the target related data in the first information to obtain the analyzed first information;

[0050] Specifically, some meteorological data that have a significant impact on the thickness of insulator ice coating are screened out through correlation analysis, and by deleting meteorological data that have a smaller impact on the thickness of insulator ice coating, the first information is optimized, redundant information is reduced, and accurate capture of key meteorological data is ensured.

[0051] Step S30. Based on the analyzed first information and second information, the preset polynomial proxy model is trained, and when the preset loss function meets the set condition, the training is stopped to obtain the insulator model;

[0052] Specifically, the proxy model is also called an approximate model. The principle is to construct a relatively simple function to replace the real function relationship. In this application, a polynomial proxy model is used to approximate the insulator model. There is a certain interaction effect. The preset polynomial proxy model is composed of a first polynomial and a second polynomial. The first polynomial is composed of insulator structural parameters, and the second polynomial is composed of target-related data.

[0053] Specifically, step S30 specifically includes step S31, step S32, step S33, step S34, step S35, step S36, step S37, step S38 and step S39:

[0054] Step S31. Based on a single item composed of a single insulator structural parameter and a preset first coefficient, multiple single items are obtained, each first coefficient in the single item is different, and the index value of the insulator structural parameter in each single item is different;

[0055] Step S32. Based on the interaction terms composed of the plurality of insulator structural parameters and the preset second coefficient, a plurality of interaction terms are obtained, wherein at least one insulator structural parameter is different between any two interaction terms, and the index value of each insulator structural parameter in the interaction term is a set threshold value;

[0056] Step S33. Form a first polynomial based on a preset constant term, a plurality of single terms and a plurality of interaction terms;

[0057] Step S34. Based on the single target-related data and the influence item composed of the preset third coefficient, multiple environmental influence items are obtained, each third coefficient in the environmental influence item is different, and the index value of the target-related data in each environmental influence item is the set threshold;

[0058] Step S35. Based on the action term composed of multiple target-related data and a preset fourth coefficient, an environmental action term is obtained, and the index value of each target-related data in the environmental action term is a set threshold;

[0059] Step S36. Forming a second polynomial based on multiple environmental impact terms and environmental action terms;

[0060] Step S37. constructing a preset polynomial proxy model based on the first polynomial, the second polynomial and the ice thickness of the insulator;

[0061] Step S38. Bring the analyzed first information and second information into a preset polynomial proxy model for calculation, and calculate a preset loss function to obtain a loss function value;

[0062] Step S39. Adjust the values ​​of the coefficients in the preset polynomial proxy model until the loss function value meets the set conditions, and obtain the insulator model, where the coefficients include the first coefficient, the second coefficient, the third coefficient and the fourth coefficient;

[0063] Specifically, in this application, considering that there are five insulator structural parameters, the highest degree of the polynomial is generally set to 4, and the first polynomial expression constructed based on the insulator structural parameters is:

[0064]

[0065] Among them, y 1 is the first polynomial; b 0 is a constant term; b i is the coefficient when only the structural parameters of the i-th insulator are considered; b ij is the coefficient when considering the structural parameters of the i-th and j-th insulators, b ijzs is the coefficient when considering the structural parameters of the i-th, j-th, z-th and s-th insulators; b ii is the coefficient of the quadratic term when only the structural parameters of the i-th insulator are considered; b iiii is the coefficient of the fourth power term when only the i-th insulator structural parameter is considered; n=5.

[0066] The second polynomial is constructed for the environmental target related data that has a significant impact on the ice thickness of the insulator. In this application, only the impact of temperature and humidity on the thickness of the insulator is considered, and the corresponding expression is:

[0067]

[0068] Among them, y 2 is the second polynomial; a is the coefficient when only the i-th target related data is considered; a ji is the coefficient when considering the i-th and j-th target related parameters; m=2.

[0069] The expression of the polynomial surrogate model is:

[0070] Y=y 1 +y 2

[0071] Where Y is the ice thickness of the insulator; 1 is the first polynomial; y 2 is the second polynomial.

[0072] By setting the value range of each coefficient in the polynomial proxy model, the polynomial proxy models under different polynomial coefficient combinations are generated using SolidWorks computer-aided design software; the analyzed first information and second information are respectively brought into multiple polynomial proxy models, and the polynomial coefficient combination is continuously adjusted according to the model prediction results. Finally, the polynomial proxy model corresponding to the optimal polynomial coefficient combination is determined as the insulator model.

[0073] Step S40: input the preset target meteorological observation data into the insulator model and use the optimization algorithm to optimize the ice thickness of the insulator to obtain the optimized initial insulator structural parameters and the corresponding target ice thickness;

[0074] Specifically, when the insulator model is actually used, the target meteorological data needs to be input. At this time, the minimum insulator ice thickness is used as the optimization target, and the size of each parameter in the insulator structural parameters will be continuously adjusted. Finally, the minimum insulator ice thickness is calculated, and the corresponding insulator structural parameters are the optimal target insulator structural parameters under the meteorological environment.

[0075] When adjusting the insulator structural parameters, it is necessary to ensure that the insulator structural parameters meet certain conditions and ensure the mechanical strength requirements of the insulator. In this application, after adjusting the insulator structural parameters, it is necessary to first calculate the creepage distance of the insulator. Only after the creepage distance meets the set conditions can the subsequent calculation of the insulator ice thickness be performed.

[0076] Considering that the creepage distance of the roof insulator is not only related to factors such as voltage, material and pollution level, but also closely related to the structural parameters of the insulator, the curvature radius of the insulator shed, the up and down inclination angle of the shed, the shed spacing and the rod diameter, etc., all have an important influence on the creepage distance. Therefore, considering the five parameters of the insulator structural parameters, the calculation formula of the creepage distance of the roof insulator is:

[0077]

[0078] Where C is the creepage distance of the insulator; k is the empirical coefficient; U r is the insulator voltage; R is the curvature radius of the shed; θ is the up and down inclination angle of the shed; D is the rod diameter; d is the shed spacing.

[0079] The value ranges of some parameters of the insulator structure parameters in the present application are as follows: the shed curvature radius is 0.1 cm to 1.0 cm, the shed spacing is 0.05 cm to 0.2 cm, and the rod diameter is 20 mm to 100 mm.

[0080] Step S50: Based on a preset physical model, the initial insulator structural parameters and the target ice layer thickness are verified to obtain verification results. When the verification results meet preset conditions, the initial insulator structural parameters are used as target insulator structural parameters.

[0081] Specifically, the initial insulator structural parameters calculated by the insulator model are imported into the preset physical model for simulation analysis. The preset physical model includes an electric field distribution model, a heat conduction model and a mechanical stress model, which can respectively calculate the corresponding electric field strength, surface temperature and mechanical stress. These physical parameters are used to further determine whether the insulator structural parameters can meet the actual use requirements.

[0082] In the present application, the electric field distribution model is established using ANSYS Maxwell software, the heat conduction model is established using ANSYS Thermal software, and the mechanical stress model is established using ANSYS Mechanical software.

[0083] In the process of simulating the electric field distribution model, the local electric field enhancement effect is an important physical phenomenon. Especially in the presence of an ice layer, the geometric shape, thickness, surface moisture and temperature of the ice layer may cause the electric field to become abnormally strong in some local areas, resulting in electrical faults such as insulator surface breakdown or flashover. Therefore, in the process of simulating the electric field distribution model, accurate simulation and calculation of the local electric field enhancement effect is crucial to predict the performance of insulators under ice conditions.

[0084] Specifically, step S50 specifically includes step S51, step S52, step S53, step S54 and step S55:

[0085] Step S51. Estimating the tip radius of the ice layer based on the target ice layer thickness;

[0086] Step S52: Calculate the ratio of the tip radius of the ice layer to the target ice layer thickness, and perform an exponential operation on the ratio to obtain a first result, where the value of the exponent is within a preset range;

[0087] Step S53: Calculate the water film thickness on the ice layer based on the target meteorological observation data and the target ice layer thickness;

[0088] Step S54: Calculate the ratio of the water film thickness to the target ice layer thickness, and perform an exponential operation on the ratio to obtain a second result, where the value of the index is within a preset range;

[0089] Step S55. Calculate the product of the first result, the second result and the overall electric field strength to obtain the local electric field strength;

[0090] Specifically, considering that the local electric field strength will increase significantly at the tip or in areas with large curvature, and the degree of increase is related to the ratio of the ice thickness to the tip curvature radius. Under high humidity conditions, water films may form on the surface of the ice layer. These water films have strong conductivity and will affect the distribution of the electric field, thereby causing the enhancement of the local electric field. The conductivity and dielectric constant of the water film are quite different from those of the ice layer itself, so the electric field may show an enhancement effect in the water film area.

[0091] Therefore, the mathematical model combining the geometric effect with the water film effect and comprehensively considering the local electric field enhancement effect is:

[0092]

[0093] Among them, E local is the local electric field strength; r tip is the radius of the ice layer tip; h ice is the target ice layer thickness; h water is the thickness of the water film on the ice layer; E global is the overall electric field strength; o and p are correction coefficients, with values ​​ranging from 0.5 to 1.

[0094] In the simulation process of the electric field distribution model of the roof insulator, it is crucial to accurately describe the conductivity change of the ice layer on the insulator, because the conductivity of the ice layer will change significantly under different environmental conditions. The conductivity of the ice layer depends not only on the temperature, purity and density of the ice, but also on the humidity of the ice layer, the surface water layer, and climatic factors (such as precipitation, wind speed, etc.). Therefore, in this application, a comprehensive model is innovatively established to dynamically simulate the changes in the conductivity of the ice layer and its impact on the electric field.

[0095] Specifically, step S50 specifically includes step S56, step S57, step S58, step S59, step S510 and step S511:

[0096] Step S56. Calculate the product of a preset temperature coefficient and the temperature in the analyzed first information to obtain a first product, wherein the preset temperature coefficient is used to characterize the influence of temperature on the conductivity of the ice layer;

[0097] Step S57. Calculate the product of a preset humidity coefficient and the humidity in the analyzed first information to obtain a second product, wherein the preset humidity coefficient is used to characterize the effect of humidity on the conductivity of the ice layer;

[0098] Step S58. Calculate the product of a preset thickness coefficient and a target ice layer thickness to obtain a third product, wherein the preset thickness coefficient is used to characterize the influence of the ice layer thickness on the conductivity of the ice layer;

[0099] Step S59. Calculate the product of the Boltzmann constant and the temperature in the analyzed first information to obtain a fourth product;

[0100] Step S510. Calculate the ratio of the preset ice activation energy to the fourth product to obtain a target ratio, wherein the preset ice activation energy is used to characterize the energy threshold at which the conductivity of the ice layer changes significantly;

[0101] Step S511. Calculate the conductivity based on the preset ice base conductivity, the first product, the second product, the third product and the target ratio;

[0102] Specifically, the present application mainly considers the effects of temperature, humidity and ice layer thickness on conductivity.

[0103] (1) Temperature: As the temperature rises, the crystal structure of the ice in the ice layer changes, especially the movement of water molecules in the ice intensifies, which leads to an increase in the conductivity of the ice layer.

[0104] (2) Humidity: When the moisture content on the surface of the ice layer increases, that is, when the humidity is high, water molecules will promote ionic conduction, so the conductivity of the ice layer will increase significantly. In addition, under high humidity conditions, a thin water film may form on the ice layer. The conductivity of this water film is much higher than that of the ice itself.

[0105] (3) Ice layer thickness: Generally speaking, a thinner ice layer has a stronger local enhancement effect of the electric field, while a thicker ice layer makes the current more evenly distributed throughout the ice layer.

[0106] In summary, the change in conductivity of the ice layer is affected by temperature, humidity and ice thickness. In the simulation process of the electric field distribution model, the following formula can be used to accurately describe the conductivity:

[0107]

[0108] Among them, σ ice is the conductivity of the ice layer; σ 0 is the basic conductivity of ice; β is the temperature coefficient; T is the temperature; α is the humidity coefficient; is humidity; γ is thickness coefficient; h ice is the target ice layer thickness; E a is the activation energy of ice; k B is the Boltzmann constant; exp is the exponential function.

[0109] After the target insulator structural parameters that meet both the minimum ice layer thickness and the physical model verification are determined by the above model, they can be verified again through experiments. Specifically, corresponding insulator samples are made based on the target insulator structural parameters, and the samples are tested in the laboratory. The tests include testing the electrical properties of the samples' insulation resistance, breakdown voltage, and leakage current, as well as the mechanical properties of tensile strength, bending strength, and impact toughness. The target meteorological observation conditions are simulated in an artificial climate chamber, and the samples are tested for their ice status. The insulator structural parameters can be optimized again based on the test results.

[0110] Embodiment 2:

[0111] like Figure 2 As shown, this embodiment provides an insulator structure optimization device based on a polynomial car, and the device includes:

[0112] An acquisition unit, configured to acquire first information and second information, wherein the first information includes meteorological observation data of an insulator working area, and the second information includes insulator structural parameters and insulator ice thickness;

[0113] An analysis unit, configured to perform a correlation analysis on the insulator ice thickness in the first information and the second information to obtain the analyzed first information, wherein the analyzed first information includes meteorological observation data having a significant impact on the insulator ice thickness;

[0114] A training unit, used for training a preset polynomial proxy model based on the analyzed first information and second information, and stopping the training when the preset loss function meets the set condition to obtain an insulator model;

[0115] An optimization unit is used to input preset target meteorological observation data into the insulator model and optimize the ice thickness of the insulator using an optimization algorithm to obtain optimized initial insulator structural parameters and corresponding target ice thickness;

[0116] The verification unit is used to verify the initial insulator structural parameters and the target ice layer thickness based on a preset physical model to obtain a verification result. When the verification result meets the preset conditions, the initial insulator structural parameters are used as the target insulator structural parameters.

[0117] In a specific embodiment disclosed in the present application, the analysis unit includes:

[0118] A first partitioning unit is used to partition the multiple meteorological related data included in the first information using a predetermined partitioning strategy to obtain multiple partitioning combinations, wherein the partitioning strategy ensures that the combination of meteorological related data in each partitioning combination is unique, and each meteorological related data can appear in multiple partitioning combinations;

[0119] A conversion unit, used for bringing each division combination into a preset feature conversion model for feature conversion to obtain a plurality of first feature vectors;

[0120] An extraction unit, used for bringing the insulator ice coating thickness in each second information into a preset feature extraction model for feature extraction to obtain a plurality of second feature vectors;

[0121] A correlation unit, used to perform correlation analysis based on the first feature vector of each partition combination and the second feature vector corresponding to each second information to obtain a plurality of correlation values;

[0122] A determination unit, used to determine a maximum correlation value from a plurality of correlation values, and use all meteorological related data in the division combination corresponding to the maximum correlation value as target related data;

[0123] The deleting unit is used to delete the meteorological related data except the target related data in the first information to obtain the analyzed first information.

[0124] In a specific embodiment disclosed in the present application, the extraction unit includes:

[0125] A second division unit is used to divide the second information into multiple levels, and compare the importance of data corresponding to each of the two levels to construct a judgment matrix, where there is an inclusion relationship between the multiple levels;

[0126] The judgment unit is used to calculate the weight corresponding to each level in the judgment matrix based on the hierarchical analysis method to determine the importance value of each data;

[0127] A sorting unit, used to sort the data from large to small based on multiple importance values, and use the ice coating thickness of the insulators before the preset sorting position as feature information;

[0128] The normalization unit is used to normalize all feature information to obtain multiple second feature vectors.

[0129] In a specific implementation disclosed in the present application, the training unit includes:

[0130] A first composition unit is used to obtain a plurality of single items based on a single item composed of a single insulator structural parameter and a preset first coefficient, wherein each first coefficient in the single item is different, and an exponential value of the insulator structural parameter in each single item is different;

[0131] The second component unit is used to obtain multiple interaction terms based on the interaction terms composed of multiple insulator structural parameters and preset second coefficients, wherein at least one insulator structural parameter is different in each of the interaction terms, and the index value of each insulator structural parameter in the interaction term is a set threshold value;

[0132] A third composition unit, configured to compose a first polynomial based on a preset constant term, a plurality of single terms, and a plurality of interaction terms;

[0133] A fourth component unit is used to obtain multiple environmental impact items based on the single target-related data and the impact item composed of the preset third coefficient, each third coefficient in the environmental impact item is different, and the index value of the target-related data in each environmental impact item is a set threshold;

[0134] A fifth component unit is used to obtain an environmental action term based on the action term composed of the plurality of target-related data and a preset fourth coefficient, wherein the index value of each target-related data in the environmental action term is a set threshold value;

[0135] A sixth composition unit, used for composing a second polynomial based on a plurality of environmental impact terms and environmental action terms;

[0136] A construction unit, used to construct a preset polynomial proxy model based on the first polynomial, the second polynomial and the ice coating thickness of the insulator;

[0137] A first calculation unit is used to bring the analyzed first information and second information into a preset polynomial proxy model for calculation, and calculate a preset loss function to obtain a loss function value;

[0138] The adjustment unit is used to adjust the values ​​of the coefficients in the preset polynomial proxy model until the loss function value meets the set conditions to obtain the insulator model, and the coefficients include the first coefficient, the second coefficient, the third coefficient and the fourth coefficient.

[0139] In a specific implementation disclosed in the present application, the verification unit includes:

[0140] The second calculation unit is used to calculate the overall electric field strength of the insulator based on the target meteorological observation data, the initial insulator structure parameters and the target ice layer thickness;

[0141] An estimation unit, used for estimating the tip radius of the ice layer based on the target ice layer thickness;

[0142] A third calculation unit is used to calculate the ratio of the ice layer tip radius to the target ice layer thickness, and perform an exponential operation on the ratio to obtain a first result, wherein the value of the exponent is within a preset range;

[0143] A fourth calculation unit, configured to calculate the water film thickness on the ice layer based on the target meteorological observation data and the target ice layer thickness;

[0144] a fifth calculation unit, for calculating a ratio of the water film thickness to the target ice layer thickness, and performing an exponential operation on the ratio to obtain a second result, wherein the value of the exponent is within a preset range;

[0145] The sixth calculation unit is used to calculate the product of the first result, the second result and the overall electric field strength to obtain the local electric field strength.

[0146] In a specific implementation disclosed in the present application, the verification unit includes:

[0147] a seventh calculation unit, configured to calculate a product of a preset temperature coefficient and a temperature in the analyzed first information to obtain a first product, wherein the preset temperature coefficient is used to characterize an effect of temperature on the conductivity of the ice layer;

[0148] an eighth calculation unit, configured to calculate a product of a preset humidity coefficient and the humidity in the analyzed first information to obtain a second product, wherein the preset humidity coefficient is used to characterize the influence of humidity on the conductivity of the ice layer;

[0149] a ninth calculation unit, configured to calculate a product of a preset thickness coefficient and a target ice layer thickness to obtain a third product, wherein the preset thickness coefficient is used to characterize an influence of the ice layer thickness on the conductivity of the ice layer;

[0150] a tenth calculation unit, used for calculating the product of the Boltzmann constant and the temperature in the analyzed first information to obtain a fourth product;

[0151] an eleventh calculation unit, configured to calculate a ratio of a preset activation energy of ice to the fourth product to obtain a target ratio, wherein the preset activation energy of ice is used to characterize an energy threshold at which the conductivity of the ice layer changes significantly;

[0152] The twelfth calculation unit is used to calculate the conductivity based on the preset ice basic conductivity, the first product, the second product, the third product and the target ratio.

[0153] It should be noted that, regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0154] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0155] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A polynomial-based insulator structure optimization method, characterized in that: include: Acquire first information and second information, wherein the first information includes meteorological observation data of an insulator working area, and the second information includes insulator structural parameters and insulator ice thickness; Performing a correlation analysis on the ice thickness of the insulator in the first information and the second information to obtain analyzed first information, wherein the analyzed first information includes meteorological observation data that has a significant impact on the ice thickness of the insulator; Training a preset polynomial proxy model based on the analyzed first information and the second information, and stopping the training when a preset loss function satisfies a set condition to obtain an insulator model; The preset target meteorological observation data is input into the insulator model and the insulator ice thickness is optimized by using the optimization algorithm to obtain the optimized initial insulator structural parameters and the corresponding target ice thickness; The initial insulator structural parameters and the target ice coating thickness are verified based on a preset physical model to obtain a verification result. When the verification result meets a preset condition, the initial insulator structural parameters are used as target insulator structural parameters.

2. The insulator structure optimization method based on polynomial car according to claim 1 is characterized in that , performing correlation analysis based on the insulator ice thickness in the first information and the second information to obtain the analyzed first information, wherein the meteorological observation data includes multiple meteorological related data, including: Using a predetermined partitioning strategy to partition the plurality of meteorological related data included in the first information to obtain a plurality of partition combinations, wherein the partitioning strategy ensures that the combination of meteorological related data in each partition combination is unique, and each meteorological related data can appear in a plurality of partition combinations; Bring each partition combination into a preset feature conversion model for feature conversion to obtain multiple first feature vectors; Bringing each of the insulator ice coating thicknesses in the second information into a preset feature extraction model to perform feature extraction, thereby obtaining a plurality of second feature vectors; Performing correlation analysis based on the first eigenvector of each partition combination and the second eigenvector corresponding to each second information to obtain a plurality of correlation values; Determine a maximum correlation value from the multiple correlation values, and use all meteorological related data in the division combination corresponding to the maximum correlation value as target related data; The meteorological related data except the target related data in the first information is deleted to obtain the analyzed first information.

3. The insulator structure optimization method based on polynomial car according to claim 2 is characterized in that , based on the analyzed first information and the second information, the preset polynomial proxy model is trained, and when the preset loss function meets the set conditions, the training is stopped to obtain the insulator model, the preset polynomial proxy model is composed of a first polynomial and a second polynomial, the first polynomial is composed of insulator structural parameters, and the second polynomial is composed of target-related data, including: Based on a single term composed of a single insulator structural parameter and a preset first coefficient, a plurality of single terms are obtained, wherein each first coefficient in the single term is different, and the index value of the insulator structural parameter in each single term is different; Based on the interaction terms composed of the plurality of insulator structural parameters and the preset second coefficient, a plurality of interaction terms are obtained, wherein at least one insulator structural parameter is different between any two of the interaction terms, and the index value of each insulator structural parameter in the interaction terms is a set threshold value; Forming a first polynomial based on a preset constant term, a plurality of single terms, and a plurality of interaction terms; Based on the single target-related data and the influence item composed of the preset third coefficient, a plurality of environmental influence items are obtained, wherein each third coefficient in the environmental influence item is different, and the index value of the target-related data in each environmental influence item is a set threshold value; Based on the action term composed of the plurality of target-related data and the preset fourth coefficient, an environmental action term is obtained, wherein the index value of each target-related data in the environmental action term is a set threshold value; forming the second polynomial based on a plurality of environmental impact terms and the environmental action term; Constructing the preset polynomial proxy model based on the first polynomial, the second polynomial and the ice coating thickness of the insulator; Bringing the analyzed first information and the second information into the preset polynomial proxy model for calculation, and calculating a preset loss function to obtain a loss function value; The values ​​of the coefficients in the preset polynomial proxy model are adjusted until the loss function value meets the set conditions, thereby obtaining the insulator model, wherein the coefficients include the first coefficient, the second coefficient, the third coefficient and the fourth coefficient.

4. The insulator structure optimization method based on polynomial car according to claim 1 is characterized in that , verifying the initial insulator structural parameters based on a preset physical model, wherein the physical model includes an electric field distribution model, a heat conduction model and a mechanical stress model, wherein the electric field distribution model is composed of at least a local electric field strength and an ice layer conductivity, wherein the local electric field strength includes: Based on the target meteorological observation data, the initial insulator structural parameters and the target ice layer thickness, the overall electric field strength of the insulator is calculated; The radius of the tip of the ice layer is estimated based on the thickness of the target ice layer; Calculating a ratio of the tip radius of the ice layer to the target ice layer thickness, and performing an exponential operation on the ratio to obtain a first result, wherein the value of the exponent is within a preset range; Calculating the water film thickness on the ice layer based on the target meteorological observation data and the target ice layer thickness; Calculating the ratio of the water film thickness to the target ice layer thickness, and performing an exponential operation on the ratio to obtain a second result, wherein the value of the exponent is within a preset range; The product of the first result, the second result and the overall electric field strength is calculated to obtain the local electric field strength.

5. The insulator structure optimization method based on polynomial car according to claim 4 is characterized in that , verifying the initial insulator structural parameters based on a preset physical model, wherein the physical model includes an electric field distribution model, a heat conduction model and a mechanical stress model, wherein the electric field distribution model is at least composed of the conductivity of the ice layer, and the conductivity of the ice layer includes: Calculating the product of a preset temperature coefficient and the temperature in the analyzed first information to obtain a first product, wherein the preset temperature coefficient is used to characterize the influence of temperature on the conductivity of the ice layer; Calculating the product of a preset humidity coefficient and the humidity in the analyzed first information to obtain a second product, wherein the preset humidity coefficient is used to characterize the influence of humidity on the conductivity of the ice layer; Calculating the product of a preset thickness coefficient and the target ice layer thickness to obtain a third product, wherein the preset thickness coefficient is used to characterize the influence of the ice layer thickness on the conductivity of the ice layer; Calculating the product of the Boltzmann constant and the temperature in the analyzed first information to obtain a fourth product; Calculating a ratio of a preset activation energy of ice to the fourth product to obtain a target ratio, wherein the preset activation energy of ice is used to characterize an energy threshold at which the conductivity of the ice layer changes significantly; The conductivity is calculated based on a preset ice basic conductivity, the first product, the second product, the third product and the target ratio.

6. An insulator structure optimization device based on polynomial car, characterized in that: include: an acquisition unit, configured to acquire first information and second information, wherein the first information includes meteorological observation data of an insulator working area, and the second information includes insulator structural parameters and insulator ice thickness; an analysis unit, configured to perform a correlation analysis on the ice thickness of the insulator in the first information and the second information to obtain analyzed first information, wherein the analyzed first information includes meteorological observation data having a significant impact on the ice thickness of the insulator; A training unit, used for training a preset polynomial proxy model based on the analyzed first information and the second information, and stopping the training when a preset loss function satisfies a set condition to obtain an insulator model; An optimization unit is used to input preset target meteorological observation data into the insulator model and optimize the ice thickness of the insulator using an optimization algorithm to obtain optimized initial insulator structural parameters and corresponding target ice thickness; A verification unit is used to verify the initial insulator structural parameters and the target ice coating thickness based on a preset physical model to obtain a verification result, and when the verification result meets a preset condition, the initial insulator structural parameters are used as target insulator structural parameters.

7. The insulator structure optimization device based on polynomial car according to claim 6 is characterized in that: The analysis unit comprises: a first partitioning unit, configured to partition the plurality of meteorological related data included in the first information using a predetermined partitioning strategy to obtain a plurality of partitioning combinations, wherein the partitioning strategy ensures that the combination of meteorological related data in each partitioning combination is unique, and each meteorological related data can appear in the plurality of partitioning combinations; A conversion unit, used for bringing each division combination into a preset feature conversion model for feature conversion to obtain a plurality of first feature vectors; An extraction unit, used for bringing the ice coating thickness of the insulator in each of the second information into a preset feature extraction model for feature extraction to obtain a plurality of second feature vectors; A correlation unit, used to perform correlation analysis based on the first feature vector of each partition combination and the second feature vector corresponding to each second information to obtain a plurality of correlation values; A determination unit, used to determine a maximum correlation value from a plurality of correlation values, and use all meteorological related data in the division combination corresponding to the maximum correlation value as target related data; A deleting unit is used to delete the meteorological related data except the target related data in the first information to obtain the analyzed first information.

8. The insulator structure optimization device based on polynomial car according to claim 7 is characterized in that: The preset polynomial proxy model is composed of a first polynomial and a second polynomial, the first polynomial is composed of insulator structural parameters, the second polynomial is composed of target related data, and the training unit includes: A first composition unit is used to obtain a plurality of single items based on a single item composed of a single insulator structural parameter and a preset first coefficient, wherein each first coefficient in the single item is different, and an exponential value of the insulator structural parameter in each single item is different; A second component unit is used to obtain multiple interaction terms based on the interaction terms composed of multiple insulator structural parameters and preset second coefficients, wherein at least one insulator structural parameter is different in any two of the interaction terms, and an exponential value of each insulator structural parameter in the interaction terms is a set threshold value; A third composition unit, configured to compose a first polynomial based on a preset constant term, a plurality of single terms, and a plurality of interaction terms; A fourth component unit is used to obtain multiple environmental impact items based on the single target-related data and the impact item composed of the preset third coefficient, wherein each third coefficient in the environmental impact item is different, and the index value of the target-related data in each environmental impact item is a set threshold value; A fifth component unit is used to obtain an environmental action term based on the multiple target-related data and the action term composed of the preset fourth coefficient, wherein the index value of each target-related data in the environmental action term is a set threshold value; A sixth composition unit, configured to compose the second polynomial based on a plurality of environmental impact terms and the environmental action term; A construction unit, configured to construct the preset polynomial proxy model based on the first polynomial, the second polynomial and the ice coating thickness of the insulator; A first calculation unit, used for bringing the analyzed first information and the second information into the preset polynomial proxy model for calculation, and calculating a preset loss function to obtain a loss function value; An adjustment unit is used to adjust the values ​​of coefficients in the preset polynomial proxy model until the loss function value meets the set conditions to obtain the insulator model, wherein the coefficients include the first coefficient, the second coefficient, the third coefficient and the fourth coefficient.

9. The insulator structure optimization device based on polynomial car according to claim 6, characterized in that: The physical model includes an electric field distribution model, a heat conduction model and a mechanical stress model, wherein the electric field distribution model is at least composed of local electric field intensity and ice layer conductivity, and the verification unit includes: A second calculation unit is used to calculate the overall electric field strength of the insulator based on the target meteorological observation data, the initial insulator structural parameters and the target ice layer thickness; An estimating unit, configured to estimate the radius of the tip of the ice layer based on the target ice layer thickness; a third calculation unit, configured to calculate a ratio of the ice layer tip radius to the target ice layer thickness, and perform an exponential operation on the ratio to obtain a first result, wherein the value of the exponent is within a preset range; A fourth calculation unit, configured to calculate the water film thickness on the ice layer based on the target meteorological observation data and the target ice layer thickness; a fifth calculation unit, configured to calculate a ratio of the water film thickness to the target ice layer thickness, and perform an exponential operation on the ratio to obtain a second result, wherein the value of the exponent is within a preset range; A sixth calculation unit is used to calculate the product of the first result, the second result and the overall electric field strength to obtain the local electric field strength.

10. The insulator structure optimization device based on polynomial car according to claim 9, characterized in that: The verification unit comprises: a seventh calculation unit, configured to calculate a product of a preset temperature coefficient and a temperature in the analyzed first information to obtain a first product, wherein the preset temperature coefficient is used to characterize an influence of temperature on the conductivity of the ice layer; an eighth calculation unit, configured to calculate a product of a preset humidity coefficient and the humidity in the analyzed first information to obtain a second product, wherein the preset humidity coefficient is used to characterize the influence of humidity on the conductivity of the ice layer; a ninth calculation unit, configured to calculate a product of a preset thickness coefficient and the target ice layer thickness to obtain a third product, wherein the preset thickness coefficient is used to characterize the influence of the ice layer thickness on the conductivity of the ice layer; a tenth calculation unit, configured to calculate the product of the Boltzmann constant and the temperature in the analyzed first information to obtain a fourth product; an eleventh calculation unit, configured to calculate a ratio of a preset activation energy of ice to the fourth product to obtain a target ratio, wherein the preset activation energy of ice is used to characterize an energy threshold at which the conductivity of the ice layer changes significantly; A twelfth calculation unit is used to calculate the conductivity based on a preset ice basic conductivity, the first product, the second product, the third product and the target ratio.

Images