Parameter optimization method, device and equipment for electrical crepe paper and readable storage medium

Abstract

The invention discloses a parameter optimization method, device and equipment for electrical crepe paper and a readable storage medium, and the method comprises the steps: determining a plurality of performance target parameters and a plurality of processing optimization parameters of the electrical crepe paper, and determining all processing optimization parameters influencing each performance target parameter and a numerical value adjustment range of each processing optimization parameter; constructing a regression model corresponding to each performance target parameter based on each performance target parameter and each processing optimization parameter corresponding to the performance target parameter; and solving the regression model corresponding to each performance target parameter to maximize the parameter value of each performance target parameter in combination with the numerical value adjustment range of each processing optimization parameter, and determining the optimal parameter value of each processing optimization parameter. Therefore, the scientificity and the accuracy of determining the processing parameters of the electrical crepe paper can be comprehensively improved through parameter analysis, model construction and optimization solution, and the product performance and the processing quality are effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of processing, more particularly, to a method, device and equipment for parameter optimization of electrical corrugated paper and a readable storage medium. BACKGROUND

[0002] In the field of dry bushing manufacturing, electrical corrugated paper as the core insulating material, its performance plays a decisive role in the insulation performance of dry bushing. In order to ensure that the dry bushing has reliable insulation performance, the electrical corrugated paper must meet strict requirements in terms of dielectric strength, mechanical properties, impregnation performance and other electrical properties.

[0003] At present, when determining the processing parameters of electrical corrugated paper, the technical guidance provided by the manufacturer, the long-term experience accumulated by the processing personnel, and repeated tests are mainly relied on. However, this parameter selection method mainly relying on manual work has significant limitations. On the one hand, when manually selecting parameters, only a single electrical property can be considered, and it is difficult to fully consider the correlation and balance between multiple electrical properties. On the other hand, due to the lack of systematization and accuracy in the manual selection process, it is difficult to obtain an optimal combination of processing parameters that can simultaneously optimize multiple electrical properties, thereby affecting the full play of the performance of electrical corrugated paper and limiting the further improvement of the insulation performance of dry bushing. Therefore, how to find a more scientific and efficient method to determine the processing parameters of electrical corrugated paper has become an important problem to be solved in the field. SUMMARY

[0004] Therefore, the present application provides a method, device and equipment for parameter optimization of electrical corrugated paper and a readable storage medium, which solves the problem that the processing parameters of electrical corrugated paper cannot be determined in the prior art.

[0005] In order to achieve the above-mentioned purpose, the present application provides the following scheme:

[0006] A method for parameter optimization of electrical corrugated paper, comprising:

[0007] determining a plurality of performance target parameters and a plurality of processing optimization parameters of the electrical corrugated paper, and determining all processing optimization parameters affecting each performance target parameter and the numerical adjustment range of each processing optimization parameter, wherein each performance target parameter is any of the following: dielectric strength, breakdown voltage, volume resistivity, reciprocal of water extract conductivity, reciprocal of moisture content, impregnation performance and tensile strength;

[0008] based on each performance target parameter and its corresponding processing optimization parameters, constructing a regression model corresponding to each performance target parameter;

[0009] The regression model corresponding to each performance target parameter is solved based on the parameter value of each performance target parameter and the numerical adjustment range of each processing optimization parameter, and the optimal parameter value of each processing optimization parameter is determined.

[0010] Optionally, the regression model corresponding to each performance target parameter is constructed based on each performance target parameter and the corresponding processing optimization parameter, and the regression model corresponding to each performance target parameter is solved based on the parameter value of each performance target parameter and the numerical adjustment range of each processing optimization parameter.

[0011] The parameter values of a plurality of electrical crease test papers are obtained.

[0012] The regression coefficients of each processing optimization parameter corresponding to each performance target parameter are calculated based on the parameter values of each electrical crease test paper.

[0013] The regression model corresponding to each performance target parameter is constructed based on the regression coefficients of each processing optimization parameter corresponding to each performance target parameter.

[0014] Optionally, the regression coefficients of each processing optimization parameter corresponding to each performance target parameter are calculated based on the parameter values of each electrical crease test paper, and the regression model corresponding to each performance target parameter is constructed based on each performance target parameter and the corresponding processing optimization parameter.

[0015] The regression coefficients of each processing optimization parameter corresponding to each performance target parameter are calculated based on the parameter values of each electrical crease test paper by using the least square method.

[0016] Optionally, the regression model corresponding to each performance target parameter is solved based on the parameter value of each performance target parameter and the numerical adjustment range of each processing optimization parameter, and the optimal parameter value of each processing optimization parameter is determined, and the regression model corresponding to each performance target parameter is solved based on the parameter value of each performance target parameter and the numerical adjustment range of each processing optimization parameter.

[0017] The parameter combination feasible solution is generated based on the numerical adjustment range of each processing optimization parameter.

[0018] The fitness value and the crowding value of each parameter combination feasible solution are calculated based on the regression model of each performance target parameter.

[0019] The parameter combination feasible solution is iteratively updated based on the fitness value and the crowding value of each parameter combination feasible solution, and the step of calculating the fitness value and the crowding value of each parameter combination feasible solution based on the regression model of each performance target parameter is returned until a preset iteration number threshold is reached.

[0020] The optimal parameter combination feasible solution is selected from the latest parameter combination feasible solution, and the optimal parameter value of each processing optimization parameter is obtained.

[0021] Optionally, the fitness value and the crowding value of each parameter combination feasible solution are calculated based on the regression model of each performance target parameter.

[0022] combining each parameter combination feasible solution into each regression model, to obtain a function value corresponding to each performance target parameter;

[0023] Based on the function values of the same parameter combination feasible solution, the fitness value and the crowding degree value of the corresponding parameter combination feasible solution are determined.

[0024] Optionally, the fitness value and the crowding degree value of the corresponding parameter combination feasible solution are determined based on the function values of the same parameter combination feasible solution, comprising:

[0025] Each weight value is determined for representing the importance of the corresponding performance target parameter to the electrical crepe paper.

[0026] Based on the weight value and the function value of each performance target parameter of the same parameter combination feasible solution, the fitness value of the corresponding parameter combination feasible solution is calculated.

[0027] According to the function value of the same performance target parameter, the parameter combination feasible solutions are sorted, and the maximum function value and the minimum function value are selected from the function values of different parameter combination feasible solutions corresponding to the same performance target parameter.

[0028] Based on the maximum function value and the minimum function value of the same performance target parameter, the individual crowding degree of different parameter combination feasible solutions under the corresponding performance target parameter is calculated.

[0029] Based on the individual crowding degree and the weight value of different performance target parameters of the same parameter combination feasible solution, the crowding degree value of the corresponding parameter combination feasible solution is calculated.

[0030] Optionally, the numerical adjustment range of each processing optimization parameter is determined, comprising:

[0031] Using a crawler tool, relevant information of each processing optimization parameter is obtained from the public electrical crepe paper processing standards and electrical crepe paper processing files.

[0032] Based on the relevant information of each processing optimization parameter, the numerical adjustment range of the corresponding processing optimization parameter is determined.

[0033] A parameter optimization device for electrical crepe paper, comprising:

[0034] The determination module is used to determine a plurality of performance target parameters and a plurality of processing optimization parameters of the electrical crepe paper, and to determine all processing optimization parameters affecting each performance target parameter and the numerical adjustment range of each processing optimization parameter, and each performance target parameter is any of the following: dielectric strength, breakdown voltage, volume resistivity, inverse number of water extract conductivity, inverse number of moisture content, impregnation performance and tensile strength.

[0035] The constructing module is configured to construct a regression model corresponding to each performance target parameter based on each performance target parameter and the corresponding individual processing optimization parameter;

[0036] The solving module is configured to solve the regression model corresponding to each performance target parameter to determine the optimal parameter value of each processing optimization parameter by maximizing the parameter value of each performance target parameter and combining the numerical adjustment range of each processing optimization parameter.

[0037] A parameter optimization device for electrical crepe paper, comprising a memory and a processor;

[0038] The memory is configured to store a program.

[0039] The processor is configured to execute the program to implement each step of the parameter optimization method for electrical crepe paper.

[0040] A readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements each step of the parameter optimization method for electrical crepe paper.

[0041] From the above technical solution, the parameter optimization method of the electrical crepe paper provided by the present application can determine multiple performance target parameters and multiple processing optimization parameters of the electrical crepe paper, and determine all processing optimization parameters affecting each performance target parameter and the numerical adjustment range of each processing optimization parameter. Each performance target parameter is any of the following: dielectric strength, breakdown voltage, volume resistivity, water extract conductivity, moisture content, impregnation performance, and tensile strength. Based on this, the present application determines multiple performance target parameters to ensure that the final generated parameter combination meets the strict requirements of multiple electrical characteristics. Comprehensive consideration of multiple processing optimization parameters and their adjustment ranges provides a comprehensive and accurate basis for subsequent optimization, which helps to improve the overall performance of the product. The present application can also construct a regression model corresponding to each performance target parameter based on each performance target parameter and the corresponding processing optimization parameters. Based on this, the relationship between the performance target parameters and the processing optimization parameters is quantified through the regression model. Through the mathematical model, it accurately describes how different processing optimization parameters affect each performance target parameter, making the originally complex relationship clear and analyzable. The present application also maximizes the parameter values of each performance target parameter, combines the numerical adjustment range of each processing optimization parameter, and solves the regression model corresponding to each performance target parameter to determine the optimal parameter value of each processing optimization parameter. Based on this, through this optimization solving process, the best balance point can be found among multiple performance target parameters, and the adjustment range of the processing optimization parameter is fully utilized to obtain the optimal parameter combination. This not only improves the performance of the electrical crepe paper in each performance target parameter, but also optimizes the overall performance, effectively solving the problem that manual selection of parameters cannot obtain the optimal processing parameter combination, thereby improving the processing quality of the electrical crepe paper, ensuring the insulation performance of the dry bushing, and improving the competitiveness of the product in the market. It can be seen that the present application can improve the scientificity and accuracy of the determination of the processing parameters of the electrical crepe paper through parameter analysis, model construction and optimization solving, effectively improve the product performance and processing quality, and has an important technical promoting role in the field of dry bushing manufacturing. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiment or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only embodiments of the present application, and those skilled in the art can obtain other drawings based on the provided drawings without creative labor.

[0043] Figure 1 A parameter optimization method flow chart of the electrical crepe paper disclosed in the embodiments of the present application;

[0044] Figure 2This is a structural block diagram of a parameter optimization device for electrical crepe paper disclosed in an embodiment of this application;

[0045] Figure 3 This is a hardware structure block diagram of a parameter optimization device for electrical crepe paper disclosed in an embodiment of this application. Detailed Implementation

[0046] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0047] This application provides a parameter optimization method for electrical crepe paper. This parameter optimization method can be applied to various electrical crepe paper processing systems or electrical crepe paper management systems, as well as to various computer terminals or smart terminals. The executing entity can be the processor or server of the computer terminal or smart terminal.

[0048] Next, combine Figure 1 The parameter optimization method for the electrical crepe paper of this application is described in detail, including the following steps:

[0049] Step S1: Determine multiple performance target parameters and multiple processing optimization parameters for electrical crepe paper, and determine all processing optimization parameters that affect each performance target parameter and the numerical adjustment range of each processing optimization parameter.

[0050] Specifically, the target performance parameters can be any of the following: dielectric strength, breakdown voltage, volume resistivity, the negative of the conductivity of the water extract, the negative of the moisture content, impregnation performance, and tensile strength.

[0051] High crystallinity typically means a more ordered molecular arrangement, resulting in stronger intermolecular forces, which helps improve the mechanical strength and electrical insulation properties of materials. Therefore, higher crystallinity often corresponds to higher dielectric strength and breakdown voltage, as well as better volume resistivity.

[0052] Surface polarity determines whether a material is hydrophilic or hydrophobic. Samples with higher surface polarity absorb water more readily, resulting in higher conductivity and water content in their water extracts. Conversely, samples with lower surface polarity exhibit better hydrophobicity.

[0053] Porosity directly affects the permeability and air permeability of a material. Higher porosity allows fillers such as epoxy resins to penetrate better, thus improving impregnation performance. At the same time, higher porosity also increases the material's air permeability.

[0054] Highly aligned fibers can significantly enhance mechanical strength in one direction, but can reduce strength in other directions. Fiber orientation can also affect the overall density of the material, with uniform fiber alignment often leading to higher density and better mechanical strength.

[0055] Each processing optimization parameter is an optimization variable that can be implemented under the current process condition, and each numerical adjustment range is an optimization range that can be implemented under the current process condition.

[0056] Each processing optimization parameter can be any of the following: fiber orientation dispersion, surface roughness, crystallinity, surface polarity, porosity, scraper angle, scraper pressure, and wrinkle aid type.

[0057] It can be understood that as the process condition changes, the type and numerical adjustment range of each processing optimization parameter will also change.

[0058] Since different performance target parameters can be affected by the same processing optimization parameter, different performance target parameters can have one or more processing optimization parameters in common.

[0059] Step S2, based on each performance target parameter and its corresponding processing optimization parameters, a regression model corresponding to each performance target parameter is constructed.

[0060] Specifically, the relationship between each performance target parameter and its corresponding processing optimization parameters can be determined;

[0061] Based on the relationship between each performance target parameter and its corresponding processing optimization parameters, the type of regression model corresponding to each performance target parameter can be determined;

[0062] Using a regression analysis method, combined with the type of regression model, a regression model for each performance target parameter can be constructed.

[0063] The regression model type can be a linear regression model or a polynomial regression model.

[0064] Step S3, to maximize the parameter value of each performance target parameter, combined with the numerical adjustment range of each processing optimization parameter, the regression model corresponding to each performance target parameter is solved to determine the optimal parameter value of each processing optimization parameter.

[0065] Specifically, to maximize the parameter value of each performance target parameter, a linear weighting method, a hierarchical sequence method, a particle swarm optimization algorithm, or an ant colony algorithm can be used, combined with the numerical adjustment range, to solve the regression model corresponding to each performance target parameter to obtain an optimal parameter combination feasible solution, thereby determining the optimal parameter value of each processing optimization parameter.

[0066] From the above technical solutions, the parameter optimization method of the electrical crepe paper provided by the present application can determine multiple performance target parameters and multiple processing optimization parameters of the electrical crepe paper, and determine all processing optimization parameters affecting each performance target parameter and the numerical adjustment range of each processing optimization parameter. Each performance target parameter is any of the following: dielectric strength, breakdown voltage, volume resistivity, water extract conductivity, moisture content, impregnation performance, and tensile strength. Based on this, the present application determines multiple performance target parameters to ensure that the final generated parameter combination meets the strict requirements of multiple electrical properties. Comprehensive consideration of multiple processing optimization parameters and their adjustment ranges provides a comprehensive and accurate basis for subsequent optimization, which helps to improve the overall performance of the product. The present application can also construct a regression model corresponding to each performance target parameter based on each performance target parameter and the corresponding processing optimization parameters. Based on this, the regression model quantifies the relationship between the performance target parameters and the processing optimization parameters. Through the mathematical model, it accurately describes how different processing optimization parameters affect each performance target parameter, making the originally complex relationship clear and analyzable. The present application also maximizes the parameter values of each performance target parameter, combines the numerical adjustment range of each processing optimization parameter, and solves the regression model corresponding to each performance target parameter to determine the optimal parameter value of each processing optimization parameter. Based on this, through this optimization solving process, the best balance point between multiple performance target parameters can be found, and the adjustment range of the processing optimization parameter is fully utilized to obtain the optimal parameter combination. This not only improves the performance of the electrical crepe paper in each performance target parameter, but also optimizes the overall performance, effectively solving the problem that manual selection of parameters cannot obtain the optimal processing parameter combination, thereby improving the processing quality of the electrical crepe paper, ensuring the insulation performance of the dry bushing, and improving the competitiveness of the product in the market. It can be seen that the present application can improve the scientificity and accuracy of the determination of the processing parameters of the electrical crepe paper through parameter analysis, model construction and optimization solving, effectively improve the product performance and processing quality, and has an important technical promoting role in the field of dry bushing manufacturing.

[0067] In some embodiments of the present application, the process of determining the numerical adjustment range of each processing optimization parameter in step S1 is described in detail as follows:

[0068] S10, using a crawler tool, obtaining relevant information of each processing optimization parameter from public electrical crepe paper processing standards and electrical crepe paper processing files.

[0069] Specifically, a tool configured with a crawler algorithm can be used to obtain relevant information of each processing optimization parameter from public electrical crepe paper processing papers, electrical crepe paper industry standard websites, electrical crepe paper research reports, electrical crepe paper processing standards, and electrical crepe paper production guide manuals.

[0070] S11, based on the relevant information of each processing optimization parameter, determine the numerical adjustment range of the corresponding processing optimization parameter.

[0071] Specifically, the relevant information of each processing optimization parameter can be cleaned and integrated to determine the numerical adjustment range of the corresponding processing optimization parameter.

[0072] From the above technical solutions, it can be seen that the embodiment provides an optional way to determine the numerical adjustment range of the processing optimization parameter. Through the above-mentioned way, the dynamic updating of the numerical adjustment range can be further completed through the crawler technology, and the reliability of the numerical adjustment range is improved.

[0073] In some embodiments of the present application, the process of step S2, based on each performance target parameter and its corresponding various processing optimization parameters, constructing a regression model corresponding to each performance target parameter, is described in detail as follows:

[0074] S20, obtain the parameter values of a plurality of electrical crepe experimental papers.

[0075] Specifically, the parameter values of various performance target parameters and various processing optimization parameters corresponding to different electrical crepe experimental values produced can be obtained, as shown in Tables 1 and 2 below.

[0076] Table 1

[0077]

[0078] Table 2

[0079]

[0080] In the table, A, B, and C are types of creping aids.

[0081] S21, combine the parameter values of each electrical crepe experimental paper to calculate the regression coefficients of each performance target parameter corresponding to each processing optimization parameter.

[0082] Specifically, a higher crystallinity generally improves dielectric strength and breakdown voltage. Materials with higher surface polarity are more likely to absorb moisture, affecting electrical performance. Porosity affects impregnation performance and air permeability. Doctor blade angle and pressure affect thickness, softness, and surface roughness. Creping aids improve paper softness and ductility.

[0083] The regression coefficients of each processing optimization parameter corresponding to each performance target parameter can be calculated by using a multiple linear regression method or a multinomial logistic regression method according to the parameter values of each electrical crepe test paper.

[0084] The regression coefficients of different performance target parameters to the same processing optimization parameter are different because the same processing optimization parameter affects different performance target parameters.

[0085] S23, based on the regression coefficient of each processing optimization parameter corresponding to each performance target parameter, a regression model corresponding to the performance target parameter is constructed.

[0086] Specifically, the regression coefficients of each performance target parameter can be integrated to generate a regression model of each performance target parameter.

[0087] As can be seen from the above technical solution, the embodiment provides an optional way of constructing a regression model corresponding to each performance target parameter based on each performance target parameter and its corresponding processing optimization parameters. Through the above method, the relationship between the performance target parameter and different processing optimization parameters can be quantified by calculating the regression coefficient according to the parameter values of the actual electrical crepe test paper, and then the regression model is constructed. This process strengthens the relationship between the regression model and the actual construction process, and improves the reliability of the regression model.

[0088] In some embodiments of the present application, the process of calculating the regression coefficient of each processing optimization parameter corresponding to each performance target parameter by combining the parameter values of each electrical crepe test paper in step S21 is described in detail as follows:

[0089] S210, the regression coefficients of each processing optimization parameter corresponding to each performance target parameter are calculated by using the least square method in combination with the parameter values of each electrical crepe test paper.

[0090] Specifically, the least square method can be used to operate the parameter values of each electrical crepe test value to calculate the regression coefficients of each processing optimization parameter corresponding to different performance target parameters, and obtain the regression model of each performance target parameter.

[0091] Further, each regression model of the present application can be as follows:

[0092]

[0093]

[0094]

[0095]

[0096]

[0097]

[0098]

[0099] wherein D is dielectric strength; B is breakdown voltage; R v is volume resistivity; C w is water extract conductivity; M is moisture content; I is impregnation performance; T is tensile strength; C is crystallinity; P is surface polarity; is porosity; P r is doctor blade pressure; is doctor blade angle; A is creping aid type.

[0100] The regression coefficient corresponding to the creping aid type is used to represent the use amount corresponding to the creping aid type.

[0101] It can be seen from the above technical solution that the embodiment provides an optional way of calculating the regression coefficient of each processing optimization parameter corresponding to each performance target parameter by combining the parameter values of each electrical crepe paper experiment paper, and the least square method can be further used to calculate the regression coefficient, and the reliability of the regression coefficient is further improved.

[0102] In some embodiments of the present application, the process of step S3, i.e., solving the regression model corresponding to each performance target parameter by maximizing the parameter value of each performance target parameter and combining the numerical adjustment range of each processing optimization parameter, is described in detail, and the steps are as follows:

[0103] S30, generating a parameter combination feasible solution based on the numerical adjustment range of each processing optimization parameter.

[0104] Specifically, the optimal parameter value of each processing optimization parameter can be obtained by combining the Pareto optimization and the NSGA-II algorithm.

[0105] The NSGA-II algorithm is used. By simulating the natural selection process, the Pareto optimal solution can be effectively found in the multi-dimensional space.

[0106] According to the numerical adjustment range of each processing optimization parameter, a plurality of parameter combination feasible solutions are randomly generated.

[0107] S31, calculating the fitness value and the crowding value of each parameter combination feasible solution by combining the regression model of each performance target parameter.

[0108] Specifically, the fitness value and the crowding value of each parameter combination feasible solution can be calculated by using the regression model of each performance target parameter, and the evaluation of each parameter combination feasible solution can be completed.

[0109] S32, based on the fitness value and the crowding value of each parameter combination feasible solution, the iteration update of each parameter combination feasible solution is performed, and step S31 is returned until the preset iteration number threshold is reached.

[0110] Specifically, based on the fitness value and the crowding value of each parameter combination feasible solution, the non-dominated sorting and the crossover mutation of each parameter combination feasible solution can be performed, the iteration of the parameter combination feasible solution is completed, and the step of calculating the fitness value and the crowding value of each parameter combination feasible solution by combining the regression model of each performance target parameter is returned until the iteration number reaches the preset iteration number threshold.

[0111] S33, the optimal parameter combination feasible solution is selected from the latest each parameter combination feasible solution, and the optimal parameter value of each processing optimization parameter is obtained.

[0112] Specifically, the parameter combination feasible solution with the highest fitness value can be selected from the latest each parameter combination feasible solution as the optimal parameter combination feasible solution, and the optimal parameter value of each processing optimization parameter is obtained.

[0113] In some embodiments, the optimal parameter value corresponding to each processing optimization parameter includes a doctor blade angle of 45°, a doctor blade pressure of 1.0 MPa, and the use of an auxiliary agent B in the Crepetrol 9000 series.

[0114] After using the optimal parameter combination feasible solution described above, the parameter value of each performance target parameter can include a dielectric strength of 6.80 kV / mm, a breakdown voltage of 2.00 kV, a volume resistivity of 4.50 x 10 7 Ω·m, a moisture content of 5.00%, a water extract conductivity of 2.20 mS / m, an immersion performance of 250.0 g / m², and a tensile strength of 5.00 kN / m.

[0115] From the above technical solution can be seen, the embodiment provides an optional way of solving the regression model corresponding to each performance target parameter by maximizing the parameter value of each performance target parameter, and combining the numerical adjustment range of each processing optimization parameter, which can ensure that the optimal parameter value meets the current process conditions and ensures the practicability and reliability of the application. Based on multi-objective optimization, the dielectric strength is improved to 7.84 kV / mm (industry average 5.2 kV / mm), the longitudinal tensile strength is improved to 6.1 kN / m (national standard requirement ≥5 kN / m), and the impregnation performance is improved to 389.09 g / m² (45% higher than traditional products). In order to realize the synergistic optimization of base paper structure, creping process and crepe paper characteristics, the Pareto optimization method is adopted, the interaction between the microstructure of base paper, the process parameters of creping and the macro performance of the final product is considered, and the creping process is optimized to meet the demand of macro performance. When the orientation angle is 105-115°, the crystallinity is 70-75%, and the porosity is 0.045-0.05 cm³ / g, the dielectric strength is greater than 7 kV / mm and the tensile strength is greater than 6 kN / m, which has process guiding value. Develop adaptive creping process: real-time monitoring of wrinkle morphology (depth 50-80 μm, width 200-300 μm) by SEM, which can improve the uniformity of crepe by 60%.

[0116] In some embodiments of the application, the process of step S31, combining the regression model of each performance target parameter, calculating the fitness value and crowding value of each parameter combination feasible solution is described in detail, and the steps are as follows:

[0117] S310, each parameter combination feasible solution is substituted into each regression model to obtain the function value corresponding to each performance target parameter.

[0118] Specifically, each parameter value of each parameter combination feasible solution can be substituted into each regression model to calculate the function value of each performance target parameter under the corresponding parameter combination feasible solution.

[0119] S311, based on the function values of the same parameter combination feasible solution, the fitness value and crowding value of the corresponding parameter combination feasible solution are determined.

[0120] Specifically, the fitness value and crowding value of the corresponding parameter combination feasible solution can be calculated by combining the function values of the same parameter combination feasible solution under different performance target parameters.

[0121] From the above technical solution can be seen, the embodiment provides an optional way of calculating the fitness value and crowding value of each parameter combination feasible solution, which combines the iteration process of parameter combination feasible solution with each regression model.

[0122] In some embodiments of the present application, the process of determining the fitness value and the crowding value of the feasible solution of the corresponding parameter combination based on the function value of the feasible solution of the same parameter combination in step S311 is described in detail as follows:

[0123] S3110, determining each weight value for representing the importance of the corresponding performance target parameter to the electrical crepe paper.

[0124] Specifically, the weight value of each performance target parameter can be determined based on the influence of each performance target parameter on the insulation performance of the dry bushing.

[0125] S3111, calculating the fitness value of the feasible solution of the corresponding parameter combination based on the weight value and the function value of each performance target parameter of the feasible solution of the same parameter combination.

[0126] Specifically, the product of each weight value and the corresponding function value of the same parameter combination can be calculated, and the sum of the products of the same parameter combination is taken as the fitness value of the corresponding parameter combination.

[0127] S3112, sorting the feasible solutions of each parameter combination according to the function value of the same performance target parameter, and selecting the maximum function value and the minimum function value from the function values of the different parameter combinations corresponding to the same performance target parameter.

[0128] Specifically, the feasible solutions of each parameter combination can be sorted according to the function value of the same performance target parameter from small to large to obtain the sorting result of the corresponding performance target parameter.

[0129] The maximum function value and the minimum function value can be selected from each sorting result, and the difference between the maximum function value and the minimum function value of the same sorting result is taken as the performance difference of the corresponding performance target parameter.

[0130] S3113, calculating the individual crowding of the different parameter combinations under the corresponding performance target parameter based on the maximum function value and the minimum function value of the same performance target parameter.

[0131] Specifically, the ratio of the adjacent function difference and the performance sorting difference of each parameter combination in each sorting result is calculated to obtain the individual crowding of the corresponding parameter combination under the corresponding performance target parameter, wherein the adjacent function difference can be the function value difference of two adjacent parameter combinations in the sorting result of the corresponding parameter combination under the corresponding performance target parameter.

[0132] S3114, calculating the crowding value of the corresponding parameter combination based on the individual crowding and the weight value of the different performance target parameters of the same parameter combination.

[0133] Specifically, the product of the crowding degree of each individual in the same parameter combination feasible solution and the corresponding weight value is calculated, and the sum of the products of the same parameter combination feasible solution is taken as the crowding degree value of the corresponding parameter combination feasible solution.

[0134] From the above technical solutions, the embodiment provides an optional way of determining the fitness value and the crowding degree value of the corresponding parameter combination feasible solution based on the function values of each parameter combination feasible solution. Through the above method, the application can determine the crowding degree value and the fitness value by comprehensively considering different performance target parameters and their importance, thereby improving the reliability of fitness calculation and crowding degree calculation.

[0135] Through experiments, compared with the traditional method, the fiber orientation dispersion of the electrical crepe paper obtained by using the parameter values of the various processing optimization parameters of the application is improved from 5.2° to 14.2°; the crystallinity is improved from 68.88% to 73.43%; the dielectric strength is enhanced from 6.51 kV / mm to 7.84 kV / mm; the tensile strength (longitudinal) is increased from 4.9 kN / m to 6.1 kN / m; the impregnation performance is improved from 375.75 g / m² to 389.09 g / m²; the water extract conductivity is reduced from 3.6 mS / m to 2.0 mS / m, and the overall performance is better.

[0136] Next, the electrical crepe paper parameter optimization device provided by the application will be described in detail. Figure 2 The electrical crepe paper parameter optimization device provided by the application will be described in detail below, and the electrical crepe paper parameter optimization device provided below can be compared with the electrical crepe paper parameter optimization method provided above.

[0137] Referring to Figure 2 It can be found that the electrical crepe paper parameter optimization device can include:

[0138] The determination module 10 is configured to determine a plurality of performance target parameters and a plurality of processing optimization parameters of the electrical crepe paper, and determine all processing optimization parameters affecting each performance target parameter and the numerical adjustment range of each processing optimization parameter, wherein each performance target parameter is any one of the following: dielectric strength, breakdown voltage, volume resistivity, inverse of water extract conductivity, inverse of moisture content, impregnation performance, and tensile strength.

[0139] The construction module 20 is configured to construct a regression model corresponding to each performance target parameter based on each performance target parameter and the corresponding processing optimization parameters.

[0140] The solving module 30 is configured to solve the regression model corresponding to each performance target parameter by maximizing the parameter value of each performance target parameter and combining the numerical adjustment range of each processing optimization parameter, to determine the optimal parameter value of each processing optimization parameter.

[0141] Further, the determining module 10 can comprise:

[0142] a first determining unit configured to use a crawler tool to obtain relevant information of each process optimization parameter from the published electrical crepe paper processing standards and electrical crepe paper processing files;

[0143] a second determining unit configured to determine a numerical adjustment range of the corresponding process optimization parameter based on the relevant information of each process optimization parameter.

[0144] Further, the constructing module 20 can comprise:

[0145] a parameter value obtaining unit configured to obtain parameter values of a plurality of electrical crepe experiment papers;

[0146] a regression coefficient calculating unit configured to calculate regression coefficients of each process optimization parameter corresponding to each performance target parameter in combination with the parameter values of the electrical crepe experiment papers;

[0147] a regression model constructing unit configured to construct a regression model of the corresponding performance target parameter based on the regression coefficients of each process optimization parameter corresponding to each performance target parameter.

[0148] Further, the regression coefficient calculating unit can comprise:

[0149] a first regression coefficient calculating sub-unit configured to calculate the regression coefficients of each process optimization parameter corresponding to each performance target parameter in combination with the parameter values of the electrical crepe experiment papers by using a least square method.

[0150] Further, the solving module 30 can comprise:

[0151] a parameter combination feasible solution generating unit configured to generate parameter combination feasible solutions based on the numerical adjustment range of each process optimization parameter;

[0152] a crowding degree value calculating unit configured to calculate fitness values and crowding degree values of each parameter combination feasible solution in combination with the regression models of each performance target parameter;

[0153] a parameter combination feasible solution iterating unit configured to iteratively update each parameter combination feasible solution based on the fitness values and crowding degree values of each parameter combination feasible solution, return to call the crowding degree value calculating unit until a preset iteration number threshold is reached;

[0154] an optimal parameter value determining unit configured to select an optimal parameter combination feasible solution from the latest each parameter combination feasible solution to obtain optimal parameter values of each process optimization parameter.

[0155] Further, the crowding degree value calculating unit can comprise:

[0156] The function value calculation subunit is configured to substitute each parameter combination feasible solution into each regression model to obtain a function value corresponding to each performance target parameter;

[0157] The fitness value calculation subunit is configured to determine a fitness value and a crowding degree value of the corresponding parameter combination feasible solution based on the function values of the same parameter combination feasible solution.

[0158] Further, the fitness value calculation subunit can include:

[0159] The first fitness value calculation component is configured to determine each weight value for representing the importance of the corresponding performance target parameter to the electrical crepe paper;

[0160] The second fitness value calculation component is configured to calculate the fitness value of the corresponding parameter combination feasible solution based on the weight value and the function value of each performance target parameter of the same parameter combination feasible solution;

[0161] The third fitness value calculation component is configured to sort the parameter combination feasible solutions according to the function value of the same performance target parameter, and select the maximum function value and the minimum function value from the function values of the different parameter combination feasible solutions corresponding to the same performance target parameter;

[0162] The fourth fitness value calculation component is configured to calculate the individual crowding degree of the different parameter combination feasible solutions under the corresponding performance target parameter based on the maximum function value and the minimum function value of the same performance target parameter;

[0163] The fifth fitness value calculation component is configured to calculate the crowding degree value of the corresponding parameter combination feasible solution based on the individual crowding degree and the weight value of the different performance target parameters of the same parameter combination feasible solution.

[0164] The parameter optimization device for electrical crepe paper provided by the embodiments of the present application can be applied to a parameter optimization device for electrical crepe paper, such as a PC terminal, a cloud platform, a server, a server cluster, etc. Figure 3 The hardware structure block diagram of the parameter optimization device for electrical crepe paper is shown in FIG. 1. Figure 3 The hardware structure of the parameter optimization device for electrical crepe paper can include at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4.

[0165] In the embodiments of the present application, the number of the processor 1, the communication interface 2, the memory 3 and the communication bus 4 is at least one, and the processor 1, the communication interface 2 and the memory 3 complete the communication among each other through the communication bus 4.

[0166] The processor 1 can be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present application, etc.

[0167] The memory 3 can include a high-speed RAM memory, and can also include a non-volatile memory, such as at least one disk memory, etc.

[0168] The memory stores a program, and the processor can invoke the program stored in the memory, and the program is used for:

[0169] determining a plurality of performance target parameters and a plurality of process optimization parameters of the electrical crepe paper, and determining all process optimization parameters affecting each performance target parameter and a numerical adjustment range of each process optimization parameter, each performance target parameter being any one or more of the following: dielectric strength, breakdown voltage, volume resistivity, reciprocal of water extract conductivity, reciprocal of moisture content, impregnation performance, and tensile strength;

[0170] based on each performance target parameter and its corresponding process optimization parameter, constructing a regression model corresponding to each performance target parameter;

[0171] maximizing the parameter value of each performance target parameter, and combining the numerical adjustment range of each process optimization parameter, to solve the regression model corresponding to each performance target parameter, and determine the optimal parameter value of each process optimization parameter.

[0172] Optionally, the detailed functions and extended functions of the program can refer to the description above.

[0173] The embodiments of the present application also provide a readable storage medium, which can store a program suitable for processor execution, and the program is used for:

[0174] determining a plurality of performance target parameters and a plurality of process optimization parameters of the electrical crepe paper, and determining all process optimization parameters affecting each performance target parameter and a numerical adjustment range of each process optimization parameter, each performance target parameter being any one or more of the following: dielectric strength, breakdown voltage, volume resistivity, reciprocal of water extract conductivity, reciprocal of moisture content, impregnation performance, and tensile strength;

[0175] based on each performance target parameter and its corresponding process optimization parameter, constructing a regression model corresponding to each performance target parameter;

[0176] The regression model corresponding to each performance target parameter is solved by maximizing the parameter value of each performance target parameter in combination with the numerical adjustment range of each processing optimization parameter, to determine the optimal parameter value of each processing optimization parameter.

[0177] Optionally, the refinement function and the expansion function of the program can refer to the description above.

[0178] Finally, it should be noted that in this document, the terms such as first and second are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between such entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or apparatus including a series of elements includes not only those elements, but also other elements not explicitly listed, or inherent to such process, method, article or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus including the element.

[0179] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The same or similar parts between the various embodiments can be mutually referred to.

[0180] The above description of the disclosed embodiments enables a person skilled in the art to implement or use the present application. Various modifications to the embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. The various embodiments of the present application can be combined with each other. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for parameter optimization of electrical crepe paper, characterized in that, The method comprises the following steps: determining a plurality of performance target parameters and a plurality of process optimization parameters of electrical crepe paper, and determining all process optimization parameters affecting each performance target parameter and the numerical adjustment range of each process optimization parameter, wherein each performance target parameter is any of the following: dielectric strength, breakdown voltage, volume resistivity, inverse of water extract conductivity, inverse of moisture content, impregnation performance and tensile strength; based on each performance target parameter and its corresponding process optimization parameter, a regression model corresponding to each performance target parameter is constructed; by maximizing the parameter value of each performance target parameter and combining the numerical adjustment range of each process optimization parameter, the regression model corresponding to each performance target parameter is solved to determine the optimal parameter value of each process optimization parameter.

2. The parameter optimization method of electrotechnical crepe paper according to claim 1, characterized in that, The regression model corresponding to each performance target parameter is constructed based on each performance target parameter and its corresponding process optimization parameter, which comprises: obtaining the parameter value of a plurality of electrical crepe experimental papers; combining the parameter value of each electrical crepe experimental paper, the regression coefficient of each process optimization parameter corresponding to each performance target parameter is calculated; based on the regression coefficient of each process optimization parameter corresponding to each performance target parameter, a regression model corresponding to the performance target parameter is constructed.

3. The parameter optimization method of electrotechnical crepe paper according to claim 2, characterized in that, The regression coefficient of each process optimization parameter corresponding to each performance target parameter is calculated by combining the parameter value of each electrical crepe experimental paper, which comprises: using the least square method, the regression coefficient of each process optimization parameter corresponding to each performance target parameter is calculated by combining the parameter value of each electrical crepe experimental paper.

4. The electrical craφleback paper parameter optimization method of claim 1 wherein, The regression model corresponding to each performance target parameter is solved by maximizing the parameter value of each performance target parameter and combining the numerical adjustment range of each process optimization parameter to determine the optimal parameter value of each process optimization parameter, which comprises: based on the numerical adjustment range of each process optimization parameter, a parameter combination feasible solution is generated; combining the regression model of each performance target parameter, the fitness value and crowding degree value of each parameter combination feasible solution are calculated; based on the fitness value and crowding degree value of each parameter combination feasible solution, each parameter combination feasible solution is iteratively updated, and the step of combining the regression model of each performance target parameter to calculate the fitness value and crowding degree value of each parameter combination feasible solution is returned until a preset iteration number threshold is reached; the optimal parameter combination feasible solution is selected from the latest parameter combination feasible solution to obtain the optimal parameter value of each process optimization parameter.

5. The parameter optimization method of electrotechnical crepe paper according to claim 4, characterized in that, The fitness value and crowding degree value of each parameter combination feasible solution are calculated by combining the regression model of each performance target parameter, which comprises: each parameter combination feasible solution is substituted into each regression model to obtain the function value corresponding to each performance target parameter; based on the function values of the same parameter combination feasible solution, the fitness value and crowding degree value of the corresponding parameter combination feasible solution are determined.

6. The parameter optimization method of electrotechnical crepe paper according to claim 5, characterized in that, The fitness value and crowding degree value of the corresponding parameter combination feasible solution are determined based on the function values of the same parameter combination feasible solution, which comprises: determining each weight value for representing the importance of the corresponding performance target parameter to electrical crepe paper; The fitness value of the feasible solution of the corresponding parameter combination is calculated based on the weight value and the function value of each performance target parameter of the same parameter combination feasible solution; The different parameter combination feasible solutions are sorted according to the function value of the same performance target parameter, and the maximum function value and the minimum function value are selected from the function values of the different parameter combination feasible solutions corresponding to the same performance target parameter; The individual crowding degree of the different parameter combination feasible solutions under the corresponding performance target parameter is calculated based on the maximum function value and the minimum function value of the same performance target parameter. The crowding degree value of the corresponding parameter combination feasible solution is calculated based on the individual crowding degree and the weight value of the different performance target parameters of the same parameter combination feasible solution.

7. The method of parameter optimization of electrotechnical crepe paper according to any of claims 1 - 6, characterized in that, The numerical adjustment range of each processing optimization parameter is determined, including: Using a crawler tool, relevant information of each processing optimization parameter is obtained from the public electrical crepe paper processing standards and electrical crepe paper processing files; Based on the relevant information of each processing optimization parameter, the numerical adjustment range of the corresponding processing optimization parameter is determined.

8. An apparatus for optimizing parameters of electrical crepe paper, characterized by, Including: A determination module is configured to determine a plurality of performance target parameters and a plurality of processing optimization parameters of electrical crepe paper, and determine all processing optimization parameters affecting each performance target parameter and the numerical adjustment range of each processing optimization parameter, and each performance target parameter is any one of the following: dielectric strength, breakdown voltage, volume resistivity, reciprocal of water extract conductivity, reciprocal of moisture content, impregnation performance and tensile strength; A construction module is configured to construct a regression model corresponding to each performance target parameter based on each performance target parameter and its corresponding processing optimization parameters; A solving module is configured to solve the regression model corresponding to each performance target parameter by maximizing the parameter value of each performance target parameter in combination with the numerical adjustment range of each processing optimization parameter, to determine the optimal parameter value of each processing optimization parameter.

9. An electrical crepe paper parameter optimization apparatus, characterized by, It includes a memory and a processor; The memory is used to store programs; The processor is used to execute the programs to realize the steps of the parameter optimization method of the electrical crepe paper according to any one of claims 1-7.

10. A readable storage medium, having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the parameter optimization method of the electrical crepe paper according to any one of claims 1-7.

Images