Electric field optimization method and device for silicon rubber coating thickness of disc-shaped suspension porcelain insulator

Abstract

The invention discloses an electric field optimization method and device for the silicone rubber coating thickness of a disc-shaped suspension type porcelain insulator, and the method comprises the steps: obtaining a model of the disc-shaped suspension type mixed porcelain insulator, combining with a multi-physical field simulation platform, and employing an electric field feedback mechanism to dynamically adjust the thickness distribution of a silicone rubber coating layer. The thickness is balanced through a multi-objective optimization objective function, the electric field and the material cost are stabilized, dynamic electric field intensity constraint conditions are set, and electric field errors are calculated and adjusted. A deep learning driven adjoint sensitivity algorithm is adopted to calculate sensitivity, and the convergence speed is optimized. And performing reverse derivation through a local optimization mechanism, generating local optimization data, finally generating a thickness cloud picture, and displaying silicone rubber thickness distribution and an electric field intensity change region. By implementing the technical scheme, the accuracy of the thickness design of the silicone rubber coating layer is improved while the uniform distribution of the electric field intensity is ensured, the material waste is reduced and the production cost is effectively controlled.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of insulators, in particular to a method and device for optimizing the electric field of the silicon rubber coating thickness of a disc-type suspension porcelain insulator. BACKGROUND

[0002] Disc-type suspension hybrid porcelain insulators are high-voltage insulating elements in power systems, widely used in power transmission and distribution, and play a core role in electrical isolation and protection. With the continuous upgrading of power systems and the higher requirements for equipment reliability, the performance of insulators, especially the performance of their coating materials, directly affects the safety and stability of power systems. Silicon rubber has become a commonly used material for the coating layer of disc-type suspension hybrid porcelain insulators due to its excellent electrical insulation performance, weather resistance, corrosion resistance, and long service life.

[0003] However, the accuracy of the thickness of the silicon rubber coating layer in the current design process is still low, mainly relying on experience or limited simulation trials. This design method cannot accurately control the thickness of the silicon rubber coating layer, resulting in problems such as excessively high or low electric field strength in certain areas. In areas with excessively high electric field strength, local overheating or aging of electrical equipment may occur, affecting the insulation performance; in areas with low electric field strength, the excessively thick silicon rubber coating layer not only causes unnecessary material waste but also increases production costs. Due to the lack of precise electric field distribution analysis in traditional methods, the accuracy of the design of the silicon rubber coating thickness is low.

[0004] Therefore, in addition to ensuring uniform distribution of electric field strength, reducing material waste, and effectively controlling production costs, improving the accuracy of the design of the silicon rubber coating layer thickness has become an important technical requirement in the design of disc-type suspension hybrid porcelain insulators. SUMMARY

[0005] To overcome the shortcomings of the prior art, the present application provides a method and device for optimizing the electric field of the silicon rubber coating thickness of a disc-type suspension porcelain insulator, which improves the accuracy of the design of the silicon rubber coating layer thickness while ensuring uniform distribution of electric field strength, reducing material waste, and effectively controlling production costs.

[0006] In a first aspect of the present application, a method for optimizing the thickness of a silicon rubber coating of a disc-type suspension hybrid porcelain insulator is provided, the method comprising: obtaining a parameterized CAD model of the disc-type suspension hybrid porcelain insulator, and combining a COMSOL multi-physics simulation platform, using a dynamic geometry adjustment mechanism based on electric field feedback, to obtain the thickness distribution of the silicon rubber coating layer; based on minimizing the volume of the silicon rubber, the stability of the electric field intensity distribution, and the material cost, balancing the thickness distribution of the silicon rubber coating layer through a multi-objective optimization objective function to generate objective function optimization data; setting multi-scale dynamic constraint conditions for electric field intensity control, and simultaneously calculating electric field dynamic errors based on local features of electric field intensity changes, and adjusting the thickness distribution of the silicon rubber coating layer in real time based on the electric field dynamic errors and the objective function optimization data to obtain dynamic constraint optimization data; using a deep learning driven concomitant sensitivity algorithm for sensitivity calculation to obtain sensitivity calculation data, and adjusting the optimization convergence speed of the thickness distribution of the silicon rubber coating layer based on the sensitivity calculation data and the dynamic constraint optimization data to obtain sensitivity analysis and optimization data; according to the sensitivity analysis and optimization data, performing local thickness reverse derivation on the thickness distribution of the silicon rubber coating layer through a local optimization mechanism to obtain local optimization data; and based on the objective function optimization data, the dynamic constraint optimization data, the sensitivity analysis and optimization data, and the local optimization data, generating a thickness cloud map of the silicon rubber coating layer, the thickness cloud map being used to display the spatial distribution of the silicon rubber thickness, and simultaneously display the change area of the electric field intensity through color mapping.

[0007] In a second aspect of the present application, a disc-shaped suspension hybrid porcelain insulator silicon rubber coating thickness electric field optimization device is provided, the device comprising an acquisition module and a processing module, wherein the acquisition module is configured to acquire a parameterized CAD model of a disc-shaped suspension hybrid porcelain insulator, and combine a COMSOL multi-physics simulation platform to obtain a thickness distribution of a silicon rubber coating layer by using a dynamic geometry adjustment mechanism based on electric field feedback; the processing module is configured to balance the thickness distribution of the silicon rubber coating layer by a multi-objective optimization objective function based on minimizing the stability of the silicon rubber volume, electric field intensity distribution and material cost, to generate target function optimization data; the processing module is further configured to set a multi-scale dynamic constraint condition for electric field intensity control, calculate an electric field dynamic error based on local features of electric field intensity changes, and adjust the thickness distribution of the silicon rubber coating layer in real time based on the electric field dynamic error and the target function optimization data to obtain dynamic constraint optimization data; the processing module is further configured to perform sensitivity calculation by using a deep learning driven adjoint sensitivity algorithm to obtain sensitivity calculation data, and adjust the optimization convergence speed of the thickness distribution of the silicon rubber coating layer based on the sensitivity calculation data and the dynamic constraint optimization data to obtain sensitivity analysis and optimization data; the processing module is further configured to perform local thickness reverse derivation on the thickness distribution of the silicon rubber coating layer by a local optimization mechanism according to the sensitivity analysis and optimization data to obtain local optimization data; and the processing module is further configured to generate a thickness cloud map of the silicon rubber coating layer based on the target function optimization data, the dynamic constraint optimization data, the sensitivity analysis and optimization data, and the local optimization data, wherein the thickness cloud map is used to display the spatial distribution of the silicon rubber thickness, and simultaneously display the change area of the electric field intensity by color mapping.

[0008] In a third aspect of the present application, an electronic device is provided, comprising a processor, a memory, a user interface and a network interface, the memory is configured to store instructions, the user interface and the network interface are configured to communicate with other devices, and the processor is configured to execute the instructions stored in the memory to enable the electronic device to perform the disc-shaped suspension hybrid porcelain insulator silicon rubber coating thickness electric field optimization method as described above.

[0009] In a fourth aspect of the present application, a computer readable storage medium is provided, which stores instructions that, when executed, perform the disc-shaped suspension hybrid porcelain insulator silicon rubber coating thickness electric field optimization method as described above.

[0010] Compared with the prior art, the present application has the following advantages: (1) The present application combines the parametric CAD model of the disc-shaped suspension mixed porcelain insulator with the COMSOL multi-physics simulation platform, optimizes the design to accurately simulate the electric field intensity distribution, and dynamically adjusts the geometric shape combined with the electric field feedback, so as to ensure that the thickness distribution of the silicone rubber coating layer meets the requirements of electrical performance and realizes the optimal use of materials. The dynamic geometric adjustment mechanism of the electric field feedback ensures that the electric field intensity of each region is effectively controlled, avoiding the problems of excessive electric field and material waste caused by electric field concentration. By considering the minimization of the volume of silicone rubber, the stability of electric field intensity distribution and material cost in the objective function, the accurate optimization of the thickness distribution of the silicone rubber coating layer is realized. Multi-objective optimization can balance each design target, ensure the control of electric field intensity and the minimization of material consumption, and reduce production cost. This makes the design process not only more efficient, but also ensures that the final design meets the electrical performance requirements and has lower cost. Multi-scale dynamic constraint conditions ensure that the thickness can be flexibly adjusted in different electric field intensity changing regions, further optimizing the stability of electric field intensity distribution. This electric field dynamic error calculation based on local electric field intensity change enables automatic adjustment of the design according to the real-time change of electric field distribution in the actual production process, thereby avoiding the risk of excessive or insufficient electric field in the region.

[0011] (2) The present application uses a deep learning driven concomitant sensitivity algorithm, which can accurately calculate the influence of silicone rubber thickness change on electric field intensity distribution, further improving the accuracy and efficiency of the optimization algorithm. The introduction of sensitivity data enables the optimization algorithm to adjust the optimization step according to the sensitivity of each region, ensuring more detailed adjustment in regions with more sensitive electric field intensity, accelerating the convergence speed and improving the overall optimization efficiency. The local optimization mechanism combines sensitivity analysis and objective function data to make detailed thickness adjustments in regions with large changes in electric field intensity, thereby ensuring that the electric field intensity control reaches the best balance in each region. Through local thickness back derivation, the thickness can be accurately increased in the areas that need to be optimized, while avoiding excessive adjustment of other areas to save materials. By generating a thickness cloud map, the thickness distribution of the silicone rubber coating layer and the change area of the electric field intensity can be intuitively displayed. The cloud map not only reflects the thickness of each region, but also displays the change of electric field intensity through color mapping, so that designers can intuitively understand the optimization effect and help further evaluate and adjust the design scheme. This visualization tool plays an important role in subsequent design and manufacturing. Therefore, the above scheme facilitates to ensure the uniform distribution of electric field intensity, reduce material waste, effectively control production cost, and improve the accuracy of the thickness design of the silicone rubber coating layer. BRIEF DESCRIPTION OF DRAWINGS

[0012] Figure 1A flowchart illustrating the electric field optimization method for the silicone rubber coating thickness of a disc-shaped suspension hybrid porcelain insulator provided in an embodiment of the present invention; Figure 2 A schematic diagram of a module for optimizing the electric field thickness of a disc-shaped suspension hybrid porcelain insulator with silicone rubber coating, provided in an embodiment of the present invention. Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0013] Explanation of reference numerals in the attached figures: 21. Acquisition module; 22. Processing module; 31. Processor; 32. Communication bus; 33. User interface; 34. Network interface; 35. Memory. Detailed Implementation

[0014] like Figure 1 As shown, the present invention provides a technical solution: an electric field optimization method for the silicone rubber coating thickness of a disc-shaped suspension porcelain insulator. This method is applied to a server and includes steps S110 to S160, as follows: S110. Obtain the parametric CAD model of the disc suspension hybrid porcelain insulator, and combine it with the COMSOL multiphysics simulation platform to obtain the thickness distribution of the silicone rubber coating layer by adopting a dynamic geometric adjustment mechanism based on electric field feedback.

[0015] Specifically, a server refers to a computer system used to provide network services. In this embodiment of the invention, the server is used to handle data storage, computation, and simulation tasks. The server is responsible for receiving, processing, and storing data from design tools and simulation platforms, and performing complex computational tasks. For example, during the design process, the server can be used to process parametric CAD models of disc suspension hybrid porcelain insulators and large amounts of data generated by the COMSOL simulation platform. For example, in the design department of a power company, the server may receive multiple electrical equipment CAD designs submitted by designers and perform batch calculations, analysis, and optimization of the electric field distribution and material thickness of the design. Disc suspension hybrid porcelain insulators are high-voltage insulation components used in power transmission systems, serving as electrical isolation and support in power lines. They are made of porcelain material on the outside and may have an embedded silicone rubber coating layer inside, providing stronger insulation performance. The disc shape of the disc suspension hybrid porcelain insulator allows it to withstand large mechanical loads and effectively isolate current, preventing current leakage. For example, in high-voltage transmission lines, disc suspension hybrid porcelain insulators are used to isolate cables or conductors from metal towers, ensuring the safety of power transmission.

[0016] A parameterized CAD model is a three-dimensional geometric model that can be flexibly adjusted by modifying parameters. During the design process, a CAD software can be used to create a parameter-based model, and designers can modify key parameters such as dimensions, angles, thicknesses, etc. in the model, and the entire model will be automatically updated. This kind of model allows for quick changes and optimization of the design. For example, when designing a disc-type suspension hybrid porcelain insulator, a parameterized CAD model can be used to define the shape, size, porosity, and other features of the insulator. When the electric field distribution analysis is needed to adjust the size of the insulator according to different electric field requirements, only a few key parameters of the model need to be modified, and the model will be automatically updated. COMSOL is a multi-physics simulation software widely used in engineering, physics, and manufacturing fields, especially suitable for the analysis of multiple physical phenomena coupling. COMSOL allows simultaneous simulation of multiple physical fields such as electric field, thermal field, mechanics, fluid, etc. in the same model. Through comprehensive simulation of complex physical phenomena, designers can accurately predict the performance of products in actual use. For example, using COMSOL to simulate the electric field distribution of a disc-type suspension hybrid porcelain insulator can help designers view the electric field intensity in each region when the current passes through the insulator, and identify potential problems of electric field concentration or excessive high.

[0017] The dynamic geometry adjustment mechanism based on electric field feedback refers to real-time analysis of electric field intensity distribution during electric field simulation, and adjustment of the geometric shape of the model according to the electric field change feedback. This mechanism dynamically adjusts the design according to the distribution of the electric field, optimizes the electric field control and material use, and ensures that the geometric shape of the model can meet the electric field intensity requirements under different electric field conditions. For example, when designing a disc-type suspension hybrid porcelain insulator, the electric field intensity in each region is analyzed using electric field simulation. If the electric field intensity in a certain region is too high, the dynamic geometry adjustment mechanism will automatically thicken the silicone rubber coating layer in that region, ensuring uniform electric field intensity distribution and avoiding electric field concentration.

[0018] The silicone rubber coating layer is a layer of material covering the surface of the insulator, used to provide additional electrical insulation performance, improve weather resistance and anti-aging performance. Silicone rubber has good electrical insulation performance, high temperature resistance, moisture resistance and ultraviolet resistance, and is suitable for the protection of electrical equipment in various harsh environments. For example, the surface of a disc-type suspension hybrid porcelain insulator may be coated with silicone rubber to improve its electric field strength and environmental adaptability, and prevent breakdown or aging due to electric field concentration. Thickness distribution refers to the variation of the thickness of the silicone rubber coating layer in each region on the surface of the insulator. By optimizing the thickness distribution, the waste and cost of materials can be reduced while ensuring the control requirements of the electric field intensity. For example, in the design of the silicone rubber coating layer, thicker silicone rubber layers may be needed in some regions to prevent excessive electric field concentration, while the thickness can be reduced in other regions, thereby saving materials. Optimization of the thickness distribution can help designers minimize material use while ensuring electrical performance.

[0019] Further, first, a parameterized CAD model of the disc-shaped suspension mixed porcelain insulator is obtained. The creation of this model is based on the insulator shape and functional requirements, and is completed by engineers in computer-aided design software, including key parameters such as the size, shape, hole, material, etc. of the insulator. At this time, the CAD model is not just a static description of the geometric shape, but is dynamically adjusted according to the design requirements, and different configurations of the model can be quickly generated by modifying the parameters in the model. Next, the parameterized CAD model is input into the COMSOL multi-physics simulation platform. COMSOL, as a multi-physics simulation software, can perform detailed physical simulation of the CAD model, including electric field, thermal field, mechanics, etc. After inputting the model, COMSOL calculates the electric field intensity distribution of the insulator through its electromagnetic field simulation module, and obtains the electric field intensity and electric field gradient changes in different regions. The electric field gradient reflects the rate of change of the electric field intensity, and can point out the regions where the electric field changes sharply, which often need special attention to avoid the risk of electric field concentration or excessive high.

[0020] Once the electric field simulation is completed and the electric field intensity distribution and electric field gradient change data are obtained, the next step is to adjust through the electric field feedback mechanism. The core idea of the electric field feedback mechanism is to automatically adjust the shape of the geometric model through real-time analysis of the electric field distribution and electric field gradient changes to optimize the electric field distribution and avoid the generation of electric field concentration areas. First, according to the electric field intensity distribution, the system will identify the areas with high electric field intensity. These areas may have the risk of excessive high electric field, so the thickness of the silicone rubber coating layer needs to be increased. At the same time, the areas with large electric field gradient indicate that the electric field intensity changes sharply, which may cause local electric field concentration, so geometric adjustment is needed to optimize the shape of the insulator to make the electric field intensity more uniform. Through these adjustments, the stability of the electric field distribution is ensured. In order to adjust the geometric shape, the system will automatically change the geometric dimensions of the corresponding areas in the CAD model, such as the thickness of the coating layer or the surface shape, so that the optimized geometric model can effectively suppress the areas of excessive high electric field concentration and achieve the expected electric field intensity distribution.

[0021] After real-time adjustment of the geometric model, the new geometry will be fed back into the electric field simulation model for simulation again. Through this process, the electric field distribution generated by the new geometric model will be recalculated to evaluate the effect of the adjustment. Through multiple iterations of adjustment, a set of optimal geometric shapes is finally obtained, ensuring that the electric field intensity in each region meets the design requirements. According to the adjusted geometric shape, the thickness distribution of the silicone rubber coating layer can be obtained. The change in thickness distribution is closely related to the electric field intensity. In areas with high electric field intensity, the thickness of the silicone rubber layer will increase to ensure sufficient electric field isolation effect; while in areas with low electric field intensity, the thickness of the silicone rubber will be reduced accordingly to avoid unnecessary material waste. Finally, the generated thickness distribution map can clearly show the thickness variation of the silicone rubber coating layer on the entire insulator surface, providing an accurate material allocation scheme for the subsequent manufacturing process.

[0022] S120, based on minimizing the volume of silicone rubber, the stability of electric field intensity distribution and material cost, balancing the thickness distribution of the silicone rubber coating layer through the objective function of multi-objective optimization, generating objective function optimization data.

[0023] Specifically, minimizing the volume of silicone rubber is a key target in optimization design, which means reducing the amount of silicone rubber material as much as possible while meeting electrical performance and safety requirements. Silicone rubber is used as an insulating material, so its volume directly affects the cost of materials and the complexity of manufacturing. For example, in the design of disc-type suspension hybrid ceramic insulators, designers hope to reduce the thickness of silicone rubber as much as possible while ensuring electric field intensity and insulation performance. A thick silicone rubber layer will result in material waste and increased production costs, while a thin silicone rubber layer may not effectively isolate the electric field. Therefore, the optimization goal is to find the optimal volume of silicone rubber that meets the electrical performance requirements while minimizing material consumption. The stability of electric field intensity distribution refers to the uniform distribution of electric field intensity throughout the region in electrical equipment, avoiding local electric field overloading or underloading. Uneven distribution of electric field may cause local electric field concentration during device operation, leading to electrical breakdown or insulation failure. For example, in disc-type suspension hybrid ceramic insulators, areas with high electric field intensity may cause partial discharge, which in turn damages the surface of the insulator. While areas with low electric field intensity may result in excessive use of materials, wasting resources. Therefore, maintaining uniform distribution of electric field intensity is an important goal in design. By optimizing the thickness distribution of silicone rubber, the distribution of electric field can be effectively controlled to avoid damage to the device caused by uneven electric field.

[0024] Material cost refers to the cost of the silicone rubber material used in the production process. Material cost includes raw material procurement costs, production processing costs, transportation costs, etc. In the optimization design, the control of material cost is to reduce unnecessary expenses in the production process on the premise of ensuring product quality and performance. For example: the thickness of the silicone rubber coating of the disc suspension mixed porcelain insulator directly affects the amount of material used. If the thickness is too large, it will not only cause material waste, but also increase production costs. Designers need to optimize the thickness distribution of the silicone rubber to ensure the lowest cost without affecting the stability of the electric field intensity and the insulation performance of the equipment.

[0025] Multi-objective optimization is an optimization method that aims to consider multiple objective functions simultaneously and balance between different objectives. In practical applications, these objectives may conflict, so the task of multi-objective optimization is to find a balance point so that multiple objectives can be satisfied to some extent. For example: when designing a disc suspension mixed porcelain insulator, design goals include minimizing the volume of silicone rubber, stabilizing the electric field intensity distribution, and controlling material costs. Through multi-objective optimization, an optimal balance point can be found between these objectives, ensuring stable electric field intensity, reducing material waste, and reducing costs. For example, using a multi-objective optimization algorithm, designers can find a thickness distribution scheme that meets the electric field intensity control while minimizing the amount of silicone rubber used and the cost.

[0026] Objective function is a mathematical expression used to evaluate the quality of the solution in an optimization problem. For multi-objective optimization, the objective function consists of multiple objectives, and different objectives need to be weighted to balance their priorities. For example: when optimizing the thickness of the silicone rubber coating, the objective function includes minimizing the volume of silicone rubber, optimizing the stability of the electric field intensity distribution, and reducing material costs. Each part has a different weight, and designers need to balance these objectives by adjusting the weight coefficients in the objective function to ultimately generate an optimal thickness distribution.

[0027] Further, before starting the optimization design, first, a target function containing three main objectives: minimizing the volume of silicone rubber, the stability of the electric field intensity distribution, and the material cost, is designed through a multi-objective optimization method. There may be some conflicts between these objectives, so they need to be balanced through an optimization algorithm. The objective function is defined as: ; In the formula, represents the comprehensive objective function; represents the volume of silicone rubber; represents the design variable, i.e. the thickness distribution of the silicone rubber coating; represents the fluctuation of the electric field intensity, representing the stability of the electric field intensity distribution; represents the material cost, representing the consumption of silicone rubber material in each region; , , all represent weight coefficients, used to balance the relative importance of each objective.

[0028] In each optimization iteration, the optimization algorithm generates adjustment data based on the definition of the objective function, which is used to guide the thickness distribution adjustment of the silicone rubber coating. The adjustment data includes the amount of silicone rubber that needs to be thickened or thinned in each region to ensure uniform distribution of electric field intensity and minimize material usage and cost. For example, in a region where the electric field intensity is too high, the optimization algorithm will indicate through adjustment data to increase the thickness of the silicone rubber to reduce the electric field intensity; while in the region where the electric field intensity is low, the thickness is reduced to save materials.

[0029] Based on the adjustment data generated in the previous step, the thickness distribution of the silicone rubber coating is adjusted. The goal of the adjustment is to ensure uniform distribution of electric field intensity under the control of electric field intensity, and to minimize the volume of silicone rubber and material cost. Assuming the target electric field intensity is , the optimized thickness distribution will ensure that the electric field intensity of each region satisfies the following formula: ; wherein represents the tolerance error of electric field intensity, representing the maximum allowed deviation of electric field intensity.

[0030] The generation process of adjustment data is based on the relationship between electric field intensity and thickness, and calculates the thickness adjustment amount of silicone rubber in each region. In the adjustment process, through the electric field intensity value of each region and the electric field gradient change between adjacent regions, the thickness of silicone rubber that needs to be increased or decreased is automatically calculated to ensure uniform distribution of electric field intensity. For example, if the electric field intensity of a certain region exceeds the set target value, the adjustment data will guide the region to increase the thickness to reduce the electric field intensity; while in the region where the electric field is low, the thickness will be reduced.

[0031] In multiple optimization iterations, the weight coefficients in the objective function are adjusted in real time according to the changes in electric field intensity and the distribution of silicone rubber material. The weight coefficients in the objective function control the relative importance of each objective in optimization. According to the design requirements and actual situation, the weight coefficients can dynamically change to ensure the balance between the stability of electric field intensity and material consumption. Specifically, the adjustment formula of the weight coefficient is as follows: ; ; wherein , all represent the weight coefficients at the current iteration step ; Multi-scale control coefficient representing the degree of influence of local gradient of electric field intensity on the maximum allowed electric field intensity; Weight coefficient representing the rate of change of electric field intensity, used to adjust the influence of the rate of change of electric field intensity on dynamic error; according to the dynamic changes of these weight coefficients, the optimization process can prioritize electric field stability according to the changes of electric field intensity, and in areas where the material is used more stably, prioritize the optimization of material cost. These weight coefficients are adjusted in real time according to the design feedback in each iteration. For example: in some areas, the electric field intensity changes greatly, the system will increase the weight coefficient of electric field stability, so that the optimization process pays more attention to the stability of the electric field; while in other areas, the material consumption changes greatly, the system will increase the weight coefficient of material cost, to reduce the waste of materials.

[0032] In each iteration process, the target function optimization data finally calculated by multi-objective optimization will provide detailed adjustment schemes for the design. This data includes the thickness of silicone rubber in each area, the corresponding electric field intensity, the amount of material consumption, and the adjustment of weight coefficients in the optimization process. The target function optimization data is the basis for guiding the designer to make the final adjustment of the silicone rubber coating. It not only shows the thickness of silicone rubber in each area, but also includes the corresponding electric field intensity and material consumption, helping the designer to intuitively evaluate the optimization results and make the final adjustment. For example: the optimized data shows the thickness of each area, the corresponding electric field intensity and the amount of material consumption, the designer can further evaluate whether the electric field intensity control requirements are met and whether there is unnecessary waste of materials.

[0033] S130, set multi-scale dynamic constraint conditions for electric field intensity control, calculate electric field dynamic error according to the local characteristics of electric field intensity change, and real-time adjust the thickness distribution of the silicone rubber coating based on the electric field dynamic error and the target function optimization data, to obtain dynamic constraint optimization data.

[0034] Specifically, the multi-scale dynamic constraint of electric field intensity refers to setting different control standards for electric field intensity according to different ranges of electric field intensity changes when designing the silicone rubber coating. These control conditions are "dynamic", meaning they will be adjusted in real time during the design process according to changes in electric field intensity. Multi-scale refers to controlling electric field intensity at different spatial scales. For example, some areas have larger changes in electric field, which may require stricter control of electric field intensity; while other areas have smaller changes in electric field, which can be appropriately relaxed in control standards. For example, when designing a disc-type suspension hybrid porcelain insulator, areas with high electric field intensity, such as the part in contact with the conductor, need to be subjected to strict electric field intensity control conditions to avoid excessive concentration of electric field; while areas with low electric field intensity, such as the part of the insulator far from the conductor, can appropriately reduce the use of materials, thus requiring lower control of electric field.

[0035] The local characteristics of electric field intensity changes refer to the specific ways and degrees of changes in electric field intensity in different regions. The local characteristics of electric field intensity reflect the distribution of electric field, especially in areas with large changes in electric field gradient, which may become risk areas of electric field concentration or overloading. For example, in the design of a disc-type suspension hybrid porcelain insulator, the part close to the conductor has a more dramatic change in electric field intensity and a larger electric field gradient, while the part far from the conductor has a more stable electric field intensity. Analysis of local characteristics can help determine which areas need to increase thickness to alleviate the phenomenon of electric field concentration.

[0036] Electric field dynamic error refers to the difference between the actual electric field distribution and the ideal or expected electric field distribution. With the adjustment and optimization of the thickness of the silicone rubber coating, the electric field distribution may change, and the calculation of electric field dynamic error is an evaluation of these changes, aiming to ensure that the electric field intensity in each area does not exceed the design requirements. For example, when optimizing the thickness of the silicone rubber coating, the electric field intensity distribution calculated by simulation may differ from the target electric field intensity distribution, such as 0.45 kV / mm, and the electric field dynamic error indicates the size of these differences. In areas with large electric field dynamic error, further adjustment of the thickness of the coating is needed.

[0037] Dynamic constraint optimization data refers to the data generated during the optimization process by combining the calculation of electric field dynamic error and the optimization data of the objective function, which is used to further guide the adjustment of the thickness distribution of the silicone rubber coating. It adjusts the constraint conditions in the optimization process in real time according to the changes in electric field intensity, ensuring that the control requirements of electric field intensity are continuously met during the optimization process. For example, assuming that in a certain round of optimization process, the electric field intensity error in a certain area is large, the dynamic constraint optimization data will provide feedback to guide the increase of the thickness of the silicone rubber in that area to reduce the electric field dynamic error. At the same time, the thickness of the silicone rubber in other areas may be reduced, thereby saving materials.

[0038] Further, first, in the optimization design, by analyzing the local characteristics of the electric field intensity variation of each region, a multi-scale electric field intensity control method is adopted. Specifically, the region with larger electric field intensity, such as the region close to the conductor, needs more stringent control conditions, while the region with smaller electric field intensity, such as the part far from the conductor, can appropriately relax the control standard. Through the multi-scale control method, the electric field intensity control constraint conditions of different regions are set to ensure that the variation of the electric field intensity can be adjusted in real time according to the local characteristics of the electric field intensity in different regions. The control condition can be set according to the local gradient of the electric field intensity. The multi-scale electric field intensity control formula is represented as: ; In the formula, represents the maximum electric field intensity; represents the gradient of the electric field intensity; Through this formula, the electric field control condition is adjusted in real time according to the electric field gradient and local characteristics to ensure that the control of the electric field intensity of each region meets the design requirements. For example: when designing a disc-shaped suspension hybrid porcelain insulator, the region close to the conductor needs more stringent electric field control due to the larger variation of the electric field intensity; while the region far from the conductor, the electric field variation is smaller, and the control standard can be appropriately relaxed, thereby saving materials.

[0039] In each round of optimization iteration, based on the specific value of the electric field intensity control and the multi-scale dynamic constraint condition of the electric field intensity control, the electric field dynamic error is calculated. The electric field dynamic error represents the difference between the current electric field intensity distribution and the preset electric field control value, and is corrected in combination with the rate of change of the electric field intensity. The electric field dynamic error calculation formula is as follows: ; In the formula, represents the electric field dynamic error; represents the partial derivative symbol; represents time; This error reflects the deviation and change rate of the electric field intensity, and the region with larger error will need more thickness adjustment, thereby ensuring the stability of the electric field intensity. For example: assuming that the electric field intensity of a certain region exceeds the target electric field intensity, and the change rate is fast, the electric field dynamic error will be larger, which means that more silicon rubber thickness needs to be added to this region to avoid excessive concentration of electric field.

[0040] After each optimization iteration, the electric field dynamic error and the target function optimization data are used to adjust the thickness distribution of the silicon rubber coating layer in real time. Through the analysis of the electric field dynamic error of each region, the thickness of the silicon rubber will be increased in the region with higher electric field intensity or more intense variation, and will be reduced in the region with lower electric field intensity or stable electric field. The real-time adjustment process is as follows: ; In the formula, represents the thickness adjustment amount of the silicone rubber; represents the weight coefficient for balancing the influence between electric field dynamic error and material consumption; the formula shows that the area with larger electric field dynamic error will be given more thickness adjustment, so as to achieve the purpose of optimizing the electric field distribution. For example: assuming that the electric field intensity changes dramatically in a certain area and the error is larger, the system will increase the thickness of the silicone rubber in this area, so as to make the electric field distribution more stable, and at the same time, according to the material consumption, avoid waste of materials.

[0041] After the above adjustment, the dynamic constraint optimization data obtained provides the final thickness distribution of the silicone rubber for each area. These data contain the thickness of the silicone rubber, the corresponding electric field intensity distribution and the amount of material consumption for each area, etc., providing detailed optimization results for the designers. The dynamic constraint optimization data not only ensures the stability of the electric field intensity, but also realizes the optimization of material consumption on the premise of ensuring the electrical performance. For example: the final dynamic constraint optimization data provides the thickness distribution diagram of the silicone rubber coating layer for the designers, and shows the electric field intensity and material consumption of each area. These data can help designers further optimize and adjust the design to ensure the electrical performance and cost-effectiveness of the equipment.

[0042] S140, using a deep learning driven adjoint sensitivity algorithm to perform sensitivity calculation to obtain sensitivity calculation data, and adjusting the optimization convergence speed of the thickness distribution of the silicone rubber coating layer based on the sensitivity calculation data and the dynamic constraint optimization data to obtain sensitivity analysis and optimization data.

[0043] Specifically, the deep learning driven adjoint sensitivity algorithm is an algorithm that uses deep learning technology to assist in calculating the sensitivity in the design optimization process. In the optimization process, sensitivity analysis is used to determine the influence of input variables, such as silicone rubber thickness, design parameters, etc., on the final goal, such as electric field distribution, material consumption, etc. The adjoint sensitivity algorithm is a method for accelerating sensitivity calculation by calculating and optimizing model gradients, which is used for complex multi-physical field simulation and optimization problems. The deep learning driven adjoint sensitivity algorithm uses a neural network model to train complex physical phenomena to capture the relationship between electric field distribution and design parameters. Through the deep learning model, the algorithm can quickly and efficiently calculate the influence of input parameters on the objective function, making the optimization process more intelligent and efficient. Assuming that in the optimization of the thickness of the silicone rubber coating layer of the disc-shaped suspension mixed porcelain insulator, the designer uses a deep learning model to train a neural network that can automatically calculate the influence of the change of the thickness of the silicone rubber on the electric field distribution according to the change of the electric field intensity in different areas. Through the adjoint sensitivity algorithm, the sensitivity of each area can be efficiently calculated to quickly obtain the optimization direction.

[0044] Sensitivity calculation data refers to the result data obtained through sensitivity analysis, which reflects the degree of response of the objective function to changes in input design parameters. Sensitivity data is used to guide designers to understand which areas have a greater impact on the final design, thereby helping to optimize the design. For example, when designing a silicone rubber coating, through sensitivity calculation data, designers can determine which areas have a greater impact on the electric field intensity distribution and which areas have a smaller impact. For example, if the electric field intensity in a certain area changes dramatically, the sensitivity calculation data will show that this area has a greater impact on the electric field distribution, and the designer can focus on this area and adjust the silicone rubber thickness.

[0045] Optimization convergence speed refers to the speed at which the optimization algorithm approaches the optimal solution during the iteration process of finding the optimal solution. The faster the convergence speed of the optimization algorithm, the faster the required optimal design can be found in fewer iterations. In the optimization process of the silicone rubber coating, through the feedback of the sensitivity calculation data and the real-time adjustment of the dynamic constraint optimization data, the optimization convergence speed can be effectively improved, and the final silicone rubber thickness distribution can be more quickly optimized. For example, assuming that the balance between electric field intensity control and material consumption requires multiple rounds of optimization iterations to achieve. By using sensitivity calculation data to guide each iteration, the optimization algorithm can more quickly identify areas that need to be adjusted, thereby speeding up the convergence process and reducing unnecessary calculations and adjustments.

[0046] Sensitivity analysis and optimization data are the final optimization results formed by combining sensitivity calculation data and constantly updated data during the optimization process. These data not only include the final thickness distribution of the silicone rubber coating, but also reflect the relationship between the electric field intensity, material consumption, and other design parameters. Sensitivity analysis and optimization data provide the basis for the final design for designers, helping them to verify and further optimize the design. For example, when optimizing the silicone rubber coating, sensitivity analysis and optimization data may include the silicone rubber thickness of each area, electric field intensity, weight adjustment during the optimization process, etc. These data can help designers understand the effects of adjusting the thickness of different areas and how to more effectively balance the electric field intensity and material consumption.

[0047] Furthermore, firstly, a deep learning-driven adjoint sensitivity algorithm is used to calculate the impact of changes in the silicone rubber coating thickness on the electric field intensity distribution. The deep learning model can be trained to model the complex relationship between silicone rubber thickness and electric field intensity, obtaining sensitivity data on the electric field intensity distribution caused by changes in silicone rubber thickness. This sensitivity data helps analyze the contribution of silicone rubber thickness changes to electric field intensity control. Specifically, by training a neural network and inputting silicone rubber thickness and electric field intensity data for different regions, the model learns the relationship between these parameters and outputs the sensitivity of silicone rubber thickness changes to the electric field intensity. The sensitivity data reflects how small changes in thickness in each region affect the overall electric field intensity distribution. For example, in a disc-type suspension hybrid ceramic insulator, changes in the thickness of the silicone rubber coating may affect the electric field intensity in different regions. Through the deep learning model, the impact of thickness changes in each region on the electric field intensity can be accurately calculated, thus obtaining sensitivity data to support subsequent optimization.

[0048] After obtaining the sensitivity calculation data, the optimization step size needs to be adjusted during the optimization process based on the contribution of each region to the electric field strength control. The optimization step size determines the adjustment magnitude of parameters, such as the silicone rubber thickness, in each iteration. Sensitivity data can reflect which regions have a greater impact on the electric field strength change, thus requiring more refined optimization adjustments, while regions with a smaller impact on the electric field can have their step size increased appropriately to improve convergence speed. The formula for adjusting the optimization step size is as follows: ; In the formula, Indicates the first The sensitivity of each region to electric field intensity control reflects the influence of changes in silicone rubber thickness on the electric field intensity distribution; This indicates the number of regions involved in the optimization, i.e., the total number of regions that need to be considered; This represents the weighting coefficient used to balance the relationship between sensitivity and optimization step size. Using this formula, in regions of high sensitivity, the optimization step size is reduced to ensure finer adjustments; while in regions of low sensitivity, the optimization step size can be increased to improve convergence speed. For example, during the design process, if the electric field intensity in a certain region is very sensitive to changes in thickness, the thickness adjustment in that region will use a smaller step size to avoid over-adjustment; while in regions where the electric field changes less, increasing the step size can accelerate the convergence of the optimization process.

[0049] In the optimization process, the sensitivity calculation data is combined with the dynamic constraint optimization data for iterative optimization. The dynamic constraint optimization data reflects the electric field intensity control requirements of each region and provides constraint conditions for the optimization process. By combining sensitivity data and dynamic constraint data, the optimization algorithm can gradually adjust the thickness distribution of silicon rubber in each region to meet both the electric field intensity control requirements and the optimization of material usage. After each iteration of optimization, the thickness distribution of the silicon rubber coating layer is adjusted according to the feedback of sensitivity data and dynamic constraint optimization data. Through continuous iteration, the final thickness distribution that meets the design requirements is obtained, while optimizing the electric field distribution and material consumption. The feedback formula of sensitivity analysis and optimization data is as follows: ; In the formula, represents the adjusted silicon rubber thickness; represents the silicon rubber thickness before adjustment.

[0050] Through these iterative optimization processes, the final thickness distribution of the silicon rubber coating layer will reach a balance point, meeting both the electric field intensity control requirements and the optimization of material usage. For example: During the optimization process, with each iteration, the designer can adjust the thickness of the silicon rubber according to the feedback data to ensure that the electric field intensity of each region is controlled within the design requirements, while avoiding excessive material usage. Ultimately, the design converges to an optimal silicon rubber coating thickness distribution scheme.

[0051] S150, according to the sensitivity analysis and optimization data, a local optimization mechanism is used to perform local thickness reverse derivation on the thickness distribution of the silicon rubber coating layer, obtaining local optimization data.

[0052] Specifically, the local optimization mechanism refers to making more detailed adjustments to certain specific regions or local designs within the framework of overall optimization. Through local optimization, designers can make fine adjustments to the thickness, shape or other design parameters of local regions according to actual needs, to solve problems such as local electric field concentration and material waste, without unnecessarily affecting the overall design. For example: In the design of the silicon rubber coating layer, the area close to the conductor may need thicker silicon rubber to ensure that the electric field intensity does not exceed the safety value; while the area far from the conductor can reduce the thickness. The local optimization mechanism allows fine adjustments in these areas without affecting the design of other areas, ensuring optimal overall performance and material consumption.

[0053] Local thickness reverse derivation refers to the process of reverse derivation of the thickness of the silicone rubber coating layer that needs to be adjusted by analyzing the change of electric field intensity, sensitivity data and optimization data in each local area. This reverse derivation can help designers accurately calculate the thickness change of each area to ensure the best balance between electric field intensity and material consumption. For example, if the electric field intensity in a certain area is high, the reverse derivation can calculate the amount of silicone rubber thickness that should be increased in that area to avoid electric field concentration. The reverse derivation process is based on data such as electric field intensity distribution and material consumption to derive the adjustment scheme. This method can accurately provide the adjustment amount for each area, avoiding overdesign or underdesign.

[0054] Local optimization data refers to the adjustment data generated during the local optimization process about the thickness distribution of the silicone rubber coating layer. These data reflect the specific adjustment amount of the silicone rubber thickness in each area after optimization. Local optimization data provides designers with information on how to make detailed adjustments in each area based on electric field intensity distribution, sensitivity analysis and objective function optimization results. For example, after a certain optimization step, local optimization data may indicate that the area near the wire needs to increase the thickness of the silicone rubber by 3 mm, while the area away from the wire can reduce the thickness by 2 mm. Designers can further optimize the thickness distribution of each area based on these data to ensure uniform electric field distribution and avoid material waste.

[0055] Further, first, according to the sensitivity analysis and optimization data and the objective function optimization data, the areas with significant changes in electric field intensity are identified. The electric field intensity in these areas may change significantly, so they need to be fine-tuned through the local optimization mechanism. The local optimization mechanism determines how to adjust the thickness of the silicone rubber in each area to achieve uniform distribution of electric field intensity by analyzing the contribution of each area to the control of electric field intensity. Through reverse derivation, the sensitivity calculation data is used to make fine adjustments to the areas with significant changes in electric field intensity in each optimization iteration to obtain the required thickness change of the silicone rubber in each area. The local optimization reverse derivation formula is: ; In the formula, represents the sensitivity function, which represents the relationship between the change of silicone rubber thickness and the change of electric field intensity; represents the sensitivity to the control of electric field intensity; through this formula, the amount of silicone rubber thickness that needs to be increased or decreased in each area can be calculated to ensure effective control of electric field intensity. For example, if the electric field intensity in a certain area exceeds the target value, the system will calculate the amount of silicone rubber thickness that needs to be increased in that area through reverse derivation to alleviate the phenomenon of electric field concentration.

[0056] After obtaining the thickness adjustment amount for each region, the optimization algorithm will adjust the thickness of the silicone rubber coating layer based on these adjustment amounts. According to the target function optimization data, the thickness of the silicone rubber in each region will be fine-tuned to ensure that the electric field intensity is controlled within the predetermined range, while avoiding material waste. Through this optimization process, the thickness of the silicone rubber coating layer will be effectively adjusted, the electric field intensity will be controlled within the predetermined range, and the material usage will be optimized. For example: if the electric field intensity in a certain region is higher, the thickness of the silicone rubber in that region will be increased through the adjustment formula, thereby reducing the risk of excessive electric field intensity. Conversely, in regions with lower electric fields, the thickness will be reduced, thereby reducing unnecessary material waste.

[0057] After each local optimization, the optimization algorithm will adjust the thickness distribution of the entire silicone rubber coating layer based on the feedback of the local optimization data. At this time, the optimization data not only includes the thickness change amount of the local region, but also considers factors such as global electric field intensity distribution and material consumption. The purpose of global optimization is to optimize the material usage as a whole while ensuring that each region meets the electric field intensity control requirements. The global optimization adjustment formula is: ; In the formula, represents the thickness distribution of the silicone rubber after global optimization; represents the thickness change amount of the local region; represents the design variable of the th local region; Through this formula, global optimization will correct the overall thickness distribution based on the results of local optimization, ensuring the stability of global electric field intensity control and optimizing material consumption. For example: Assuming that through local optimization, the thickness of the silicone rubber in some regions increases, and in other regions decreases, the system will adjust the thickness distribution of the entire insulator based on the feedback of the local optimization data, ensuring that the overall electric field intensity distribution is uniform and the material consumption is minimized.

[0058] Finally, after multiple rounds of optimization iterations, the thickness distribution of the silicone rubber coating layer will gradually approach the optimal solution. The stability of the electric field intensity distribution and the minimization of material consumption will be further optimized after each optimization iteration, thereby ensuring that the final design not only meets the electrical performance requirements, but also maximizes the reduction of material waste. The global optimization and stability guarantee formula is as follows: ; In the formula, represents all optimization regions; Through this target function, the optimization algorithm can find the best balance between electric field intensity control and material usage, ensuring stable electric field distribution and minimizing material consumption. For example: During the multiple rounds of optimization process, by continuously adjusting the thickness of the silicone rubber, the final design can ensure that the electric field intensity is within the target range, the material consumption is minimized, and the problem of electric field concentration or excessive electric field is avoided.

[0059] S160, based on the target function optimization data, the dynamic constraint optimization data, the sensitivity analysis and optimization data, and the local optimization data, generate a thickness cloud map of the silicone rubber coating layer, the thickness cloud map is used to show the spatial distribution of the silicone rubber thickness, and the change area of the electric field intensity is displayed synchronously through color mapping.

[0060] Specifically, the thickness cloud map of the silicone rubber coating layer is a graph generated by data visualization of the silicone rubber coating layer thickness distribution. It uses color or other visualization methods to represent the change of silicone rubber thickness in different areas, so that the designer can intuitively see the thickness distribution of each area. The thickness cloud map is used to show the thickness adjustment amount of each area in the entire design, helping the decision-making in the optimization process. For example: by generating a thickness cloud map, the designer can clearly see which areas have thicker silicone rubber layers and which areas have thinner layers. For example, areas close to the area with large changes in electric field intensity may need to display thicker silicone rubber, while areas with stable electric field intensity may display thinner thickness.

[0061] Color mapping refers to representing different values of data through changes in color. In the thickness cloud map of the silicone rubber coating layer, color mapping is used to display the change area of the electric field intensity, helping the designer quickly identify areas with high or low electric field intensity. Through different colors, the designer can intuitively see the changes in electric field intensity and which areas need to be adjusted. For example: in the thickness cloud map, areas with high electric field intensity may use red or dark colors, and areas with low electric field intensity may use green or light colors. Through this color mapping, the designer can quickly determine which areas have unstable or exceed the control range of electric field intensity, and thus decide which areas need to increase the thickness of the silicone rubber.

[0062] The change area of the electric field intensity refers to the area in the design where the electric field intensity changes significantly. These areas may be places where the electric field is concentrated or unevenly distributed, and therefore require special attention and adjustment. In the design of the silicone rubber coating layer, these areas often need to increase the material thickness to prevent the electric field intensity from exceeding the safety range. For example: in the design process of the silicone rubber coating layer, the area close to the wire has a large change in electric field intensity, so the designer will mark these areas as areas with large changes in electric field intensity through color mapping, guiding the increase in thickness to balance the electric field distribution.

[0063] Further, first, the objective function optimization data, dynamic constraint optimization data, sensitivity analysis and optimization data, and local optimization data are integrated. Each type of data contains optimization information at different levels, for example, the objective function data reflects the overall optimization goal, the dynamic constraint data provides constraints for electric field strength control, the sensitivity analysis data shows the impact of changes in silicone rubber thickness on electric field strength, and the local optimization data provides specific thickness adjustment amounts for each region. By integrating these data, thickness distribution calculation data for the silicone rubber coating layer is generated, which includes the required silicone rubber thickness, material consumption, electric field strength, and optimization steps for each region. The thickness distribution data will provide the basis for generating the thickness cloud map and provide the basis for subsequent optimization. The data integration formula is as follows: ; In the formula, represents the comprehensive thickness distribution calculation data; represents the thickness adjustment amount provided by the objective function optimization data; represents the thickness adjustment amount provided by the dynamic constraint optimization data; represents the thickness adjustment amount provided by the sensitivity analysis and optimization data; represents the thickness adjustment amount provided by the local optimization data; , , , respectively represent , , , corresponding weight coefficients, respectively used to balance the priority of the "objective function optimization data", "dynamic constraint optimization data", "sensitivity analysis and optimization data", and "local optimization data" during integration, and adjust the influence of each type of data on the total thickness distribution data; through this formula, each data source is considered to generate the final thickness distribution calculation data for each region. For example: in the optimization process of the silicone rubber coating layer, some regions may need to increase the thickness due to high electric field strength, while some regions can reduce the thickness due to low electric field strength. By integrating different data sources, the specific thickness requirement for each region can be obtained.

[0064] Using the thickness distribution calculation data, a thickness cloud map of the silicone rubber coating layer is generated through a graphical algorithm. This process includes visualizing the calculated thickness data using a graphical tool. The thickness cloud map displays the thickness of the silicone rubber in each region through color mapping, and simultaneously displays the changes in electric field strength. The graphical generation formula is as follows: ; In the formula, represents the color value used to generate the thickness cloud map; represents a mapping function that maps the silicone rubber thickness and electric field intensity to color values; the graphical algorithm maps the thickness and electric field intensity into a color space, with areas of higher electric field intensity possibly using red or dark colors, and areas of lower electric field intensity using green or light colors, thus visually displaying the changes in electric field intensity and silicone rubber thickness. For example: during the design process, areas close to the current path, which have higher electric field intensity, will be displayed as dark red in the cloud map, indicating that a thicker layer of silicone rubber is needed; while areas far from the current path, which have lower electric field intensity, will be displayed as green or light color in the cloud map, indicating that the thickness of the silicone rubber can be appropriately reduced.

[0065] According to the generated thickness cloud map, the designer can visually view the distribution of electric field intensity and the changes in silicone rubber thickness, and make necessary adjustments. Through feedback on the thickness cloud map, the designer can adjust the thickness distribution of the silicone rubber coating layer to control the electric field intensity within a predetermined range and ensure the optimization of material use. According to the feedback of the thickness cloud map, the designer can increase the thickness in areas that do not meet the electric field intensity requirements or have excessively high electric field intensity, and reduce the thickness in areas with lower electric field intensity, thus optimizing the design scheme. For example: according to the thickness cloud map, the designer finds that the electric field intensity in some areas is too high, and the system will prompt that the thickness of the silicone rubber in this area needs to be increased; while in areas with lower electric field intensity, the system will suggest reducing the thickness, thus ensuring that the entire design meets the electric field intensity requirements and avoids material waste.

[0066] The present application also provides an electric field optimization device for the thickness of a disc-shaped suspension mixed porcelain insulator silicone rubber coating, which is described with reference to Figure 2 , Figure 2A module schematic diagram of the electric field optimization device for the silicon rubber coating thickness of the disc suspension hybrid porcelain insulator provided by the embodiment of the present application is provided, the device is a server, the server comprises an acquisition module 21 and a processing module 22, wherein the acquisition module 21 is configured to acquire a parameterized CAD model of the disc suspension hybrid porcelain insulator, and in combination with a COMSOL multi-physical field simulation platform, a dynamic geometry adjustment mechanism based on electric field feedback is adopted to obtain the thickness distribution of the silicon rubber coating layer; the processing module 22 is configured to balance the thickness distribution of the silicon rubber coating layer by a multi-objective optimization objective function based on the minimization of the silicon rubber volume, the stability of the electric field intensity distribution and the material cost, and generate target function optimization data; the processing module 22 is further configured to set a multi-scale dynamic constraint condition for the electric field intensity control, calculate an electric field dynamic error based on the local characteristics of the electric field intensity change, and adjust the thickness distribution of the silicon rubber coating layer in real time based on the electric field dynamic error and the target function optimization data to obtain dynamic constraint optimization data; the processing module 22 is further configured to perform sensitivity calculation by using a deep learning driven adjoint sensitivity algorithm to obtain sensitivity calculation data, and adjust the optimization convergence speed of the thickness distribution of the silicon rubber coating layer based on the sensitivity calculation data and the dynamic constraint optimization data to obtain sensitivity analysis and optimization data; the processing module 22 is further configured to perform local thickness reverse derivation on the thickness distribution of the silicon rubber coating layer by a local optimization mechanism according to the sensitivity analysis and optimization data to obtain local optimization data; and the processing module 22 is further configured to generate a thickness cloud map of the silicon rubber coating layer based on the target function optimization data, the dynamic constraint optimization data, the sensitivity analysis and optimization data and the local optimization data, and the thickness cloud map is used to display the spatial distribution of the silicon rubber thickness and synchronously display the change area of the electric field intensity by color mapping.

[0067] It should be noted that the device provided in the above embodiment is only used as an example to illustrate the division of the above functional modules in realizing its functions, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above described functions. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be described here.

[0068] The present application also provides an electronic device, referring to Figure 3 , Figure 3 A structural schematic diagram of an electronic device provided by the embodiment of the present application. The electronic device can include at least one processor 31, at least one network interface 34, a user interface 33, a memory 35, and at least one communication bus 32.

[0069] The communication bus 32 is used to realize the connection and communication between the components.

[0070] The user interface 33 can include a display, a camera, and optionally a standard wired interface and a wireless interface.

[0071] The network interface 34 can optionally include a standard wired interface and a wireless interface (e.g., a Wi-Fi interface).

[0072] The processor 31 can include one or more processing cores. The processor 31 connects various parts of the server through various interfaces and lines, and performs various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 35, and calling data stored in the memory 35. Optionally, the processor 31 can be implemented in at least one of a hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 31 can be integrated with a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU is mainly used to process an operating system, a user interface, and an application program. The GPU is used to render and draw content to be displayed on the display. The modem is used to process wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 31, but can be implemented by a separate chip.

[0073] The memory 35 can include a random access memory (RAM) and a read-only memory (ROM). Optionally, the memory 35 includes a non-transitory computer-readable storage medium. The memory 35 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 35 can include a program storage area and a data storage area. The program storage area can store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-mentioned various method embodiments, etc. The data storage area can store data involved in the above-mentioned various method embodiments, etc. The memory 35 can optionally be at least one storage device located away from the above-mentioned processor 31. For example, Figure 3As shown, the memory 35 as a computer storage medium can include an operating system, a network communication module, a user interface module, and an application program of the method for optimizing the thickness of the silicon rubber coating of the disc-type suspension hybrid porcelain insulator.

[0074] In Figure 3 In the electronic device shown, the user interface 33 is mainly used to provide an interface for the user to input, and obtain data input by the user; and the processor 31 can be used to invoke the application program of the method for optimizing the thickness of the silicon rubber coating of the disc-type suspension hybrid porcelain insulator stored in the memory 35, and when executed by one or more processors, make the electronic device execute the method of one or more of the above embodiments.

[0075] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all described as a series of action combinations, but those skilled in the art should know that the present application is not limited to the order of the actions described, because according to the present application, certain steps can be performed in other order or at the same time. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0076] The present application also provides a computer readable storage medium, which stores instructions. When executed by one or more processors, make the electronic device execute the method of one or more of the above embodiments.

[0077] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0078] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic. The division of the units is only a logical function division. There can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some services interfaces, devices or units, and can be electrical or other forms.

[0079] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0080] In addition, each function unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software function unit.

[0081] If the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable memory. Based on this understanding, the technical solutions of the present application or the part of the prior art that essentially contributes or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a memory and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned memory includes: a U disk, a mobile hard disk, a magnetic disk or an optical disk and various program code storage media.

[0082] The above is only exemplary embodiments of the present disclosure, and cannot limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Other embodiments of the present disclosure will be readily apparent to those skilled in the art upon considering the specification and practicing the true principles of the present disclosure. The present application is intended to cover any variations, uses or adaptive changes of the present disclosure that follow the general principles of the present disclosure and include common knowledge or conventional technical means in the technical field not disclosed by the present disclosure. The specification and examples are only considered as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for optimizing the electric field of silicone rubber coating thickness in disc-type suspension porcelain insulators, characterized in that, Includes the following steps: A parametric CAD model of a disc-type suspension hybrid porcelain insulator was obtained, and the thickness distribution of the silicone rubber coating layer was obtained by combining it with the COMSOL multiphysics simulation platform and adopting a dynamic geometric adjustment mechanism based on electric field feedback. Based on minimizing the volume of silicone rubber, the stability of electric field intensity distribution, and material cost, the thickness distribution of the silicone rubber coating layer is balanced through a multi-objective optimization objective function to generate objective function optimization data; Multi-scale dynamic constraints for electric field intensity control are set, and the electric field dynamic error is calculated based on the local characteristics of electric field intensity changes. The thickness distribution of the silicone rubber coating layer is adjusted in real time based on the electric field dynamic error and the objective function optimization data to obtain dynamic constraint optimization data. A deep learning-driven adjoint sensitivity algorithm is used to calculate sensitivity data. Based on the sensitivity data and the dynamic constraint optimization data, the convergence speed of the thickness distribution of the silicone rubber coating layer is adjusted to obtain sensitivity analysis and optimization data. Based on the sensitivity analysis and optimization data, local optimization data is obtained by reverse derivation of the thickness distribution of the silicone rubber coating layer through a local optimization mechanism. Based on the objective function optimization data, the dynamic constraint optimization data, the sensitivity analysis and optimization data, and the local optimization data, a thickness cloud map of the silicone rubber coating layer is generated. The thickness cloud map is used to display the spatial distribution of the silicone rubber thickness and to synchronously display the area of ​​electric field intensity variation through color mapping.

2. The method for optimizing the electric field of the silicone rubber coating thickness of the disc-shaped suspension porcelain insulator according to claim 1, characterized in that: The parametric CAD model of the disc-type suspension hybrid porcelain insulator was obtained, and using the COMSOL multiphysics simulation platform, a dynamic geometric adjustment mechanism based on electric field feedback was employed to obtain the specific process of the thickness distribution of the silicone rubber coating layer: Obtain the parametric CAD model of the disc-shaped suspension hybrid porcelain insulator, and input the parametric CAD model into the COMSOL multiphysics simulation platform to perform electric field simulation, thereby obtaining the electric field intensity distribution and electric field gradient change; Through the electric field feedback mechanism, based on the electric field intensity distribution and the electric field gradient change, the geometry of the disc suspension hybrid porcelain insulator is automatically adjusted to generate a geometric model optimized for the electric field intensity distribution. The thickness distribution of the silicone rubber coating layer is obtained by adjusting the geometric model in real time.

3. The method for optimizing the electric field of the silicone rubber coating thickness of the disc-shaped suspension porcelain insulator according to claim 2, characterized in that: Based on minimizing the volume of silicone rubber, the stability of the electric field intensity distribution, and material cost, the specific process of generating objective function optimization data by balancing the thickness distribution of the silicone rubber coating layer through multi-objective optimization is as follows: Based on the objective function of the multi-objective optimization, in each optimization iteration, adjustment data is generated according to minimizing the volume of silicone rubber, the stability of the electric field intensity distribution, and the material cost. The adjustment data is used to guide the adjustment of the thickness distribution of the silicone rubber coating layer. Under electric field strength control conditions, the thickness distribution of the silicone rubber coating layer is adjusted according to the adjustment data to make the electric field strength uniformly distributed in each region and to minimize the volume and material cost of the silicone rubber. Through multi-objective optimization calculations, the weight coefficients in the objective function are adjusted in real time based on the changes in electric field strength and the distribution of silicone rubber material to ensure the balance between electric field strength and material consumption during the optimization process, thereby obtaining the optimized data of the objective function.

4. The method for optimizing the electric field of the silicone rubber coating thickness of the disc-shaped suspension porcelain insulator according to claim 3, characterized in that: The specific process of setting multi-scale dynamic constraints for electric field intensity control, calculating the electric field dynamic error based on the local characteristics of electric field intensity changes, and adjusting the thickness distribution of the silicone rubber coating layer in real time based on the electric field dynamic error and the objective function optimization data to obtain dynamic constraint optimization data is as follows: Based on the local characteristics of the electric field intensity change, multi-scale electric field intensity control is used to set electric field intensity constraints for different regions, and the specific value of the electric field intensity control is dynamically adjusted according to the local characteristics of the electric field change. Based on the specific value of the electric field strength control and the multi-scale dynamic constraint conditions of the electric field strength control, the electric field dynamic error is calculated, wherein the electric field dynamic error is calculated based on the difference between the electric field strength and the preset control value and the deviation of the rate of change; Based on the electric field dynamic error and the objective function optimization data, the thickness of the silicone rubber in each region is optimized by adjusting the thickness distribution of the silicone rubber coating layer in real time, thereby obtaining the dynamic constraint optimization data.

5. The method for optimizing the electric field of the silicone rubber coating thickness of the disc-shaped suspension porcelain insulator according to claim 4, characterized in that: Sensitivity calculation is performed using a deep learning-driven adjoint sensitivity algorithm to obtain sensitivity calculation data. Based on the sensitivity calculation data and the dynamic constraint optimization data, the convergence speed of the thickness distribution of the silicone rubber coating layer is adjusted to obtain the sensitivity analysis and optimization data. The specific process is as follows: Based on a deep learning-driven adjoint sensitivity algorithm, the sensitivity calculation data of the effect of the change in the thickness of the silicone rubber coating layer on the electric field intensity distribution is calculated, and the contribution of each region to the control of the electric field intensity is analyzed through the sensitivity calculation data. The optimization step size is adjusted based on the sensitivity calculation data, and the convergence speed of the optimization process is adjusted based on the optimization step size and the contribution of each region to the electric field strength control. By combining the sensitivity calculation data and the dynamic constraint optimization data, the thickness distribution of the silicone rubber coating layer is adjusted through iterative optimization to obtain the sensitivity analysis and optimization data.

6. The method for optimizing the electric field of the silicone rubber coating thickness of the disc-shaped suspension porcelain insulator according to claim 5, characterized in that: Based on the sensitivity analysis and optimization data, the specific process of obtaining the local optimization data by performing a local thickness inverse derivation of the thickness distribution of the silicone rubber coating layer through a local optimization mechanism is as follows: Based on the sensitivity analysis and optimization data and the objective function optimization data, the local optimization mechanism is used to finely adjust the regions where the electric field intensity changes significantly, and the required change in silicone rubber thickness for each region is determined by reverse derivation. By optimizing the thickness of the silicone rubber coating layer in each region based on the required variation in silicone rubber thickness, the electric field strength is controlled within a predetermined range, thus obtaining the local optimization data. Based on the feedback from the local optimization data, the global silicone rubber coating thickness distribution is adjusted after each optimization iteration to ensure the stability of the electric field strength distribution and minimize material usage.

7. The method for optimizing the electric field of the silicone rubber coating thickness of the disc-shaped suspension porcelain insulator according to claim 6, characterized in that: Based on the objective function optimization data, the dynamic constraint optimization data, the sensitivity analysis and optimization data, and the local optimization data, a thickness cloud map of the silicone rubber coating layer is generated. This thickness cloud map is used to display the spatial distribution of the silicone rubber thickness. The specific process of synchronously displaying the changing regions of the electric field intensity through color mapping is as follows: Based on the objective function optimization data, the dynamic constraint optimization data, the sensitivity analysis and optimization data, and the local optimization data, the thickness distribution calculation data of the silicone rubber coating layer is generated through data integration. Using the thickness distribution calculation data, a graphical algorithm is used to generate a thickness cloud map of the silicone rubber coating layer, wherein color mapping is used to reflect the changes in silicone rubber thickness and electric field intensity in each region; Based on the thickness cloud map, the electric field strength control is optimized by adjusting the thickness distribution to generate silicone rubber coating design data that meets the electric field strength requirements and material optimization.

8. An electric field optimization device for the silicone rubber coating thickness of a disc-shaped suspension porcelain insulator, characterized in that, The device is used to execute the electric field optimization method for the silicone rubber coating thickness of disc-type suspension porcelain insulators as described in any one of claims 1 to 7. The device includes an acquisition module and a processing module, wherein... The acquisition module is used to acquire the parametric CAD model of the disc suspension hybrid porcelain insulator, and in conjunction with the COMSOL multiphysics simulation platform, adopts a dynamic geometric adjustment mechanism based on electric field feedback to obtain the thickness distribution of the silicone rubber coating layer. The processing module is used to balance the thickness distribution of the silicone rubber coating layer through a multi-objective optimization objective function based on minimizing the volume of silicone rubber, the stability of the electric field intensity distribution, and the material cost, and to generate objective function optimization data. The processing module is also used to set multi-scale dynamic constraints for electric field intensity control, calculate the electric field dynamic error based on the local characteristics of electric field intensity changes, and adjust the thickness distribution of the silicone rubber coating layer in real time based on the electric field dynamic error and the objective function optimization data to obtain dynamic constraint optimization data. The processing module is also used to perform sensitivity calculation using a deep learning-driven adjoint sensitivity algorithm to obtain sensitivity calculation data, and to adjust the optimized convergence speed of the thickness distribution of the silicone rubber coating layer based on the sensitivity calculation data and the dynamic constraint optimization data to obtain sensitivity analysis and optimization data. The processing module is also used to perform local thickness reverse derivation on the thickness distribution of the silicone rubber coating layer through a local optimization mechanism based on the sensitivity analysis and optimization data to obtain local optimization data. The processing module is also used to generate a thickness cloud map of the silicone rubber coating layer based on the objective function optimization data, the dynamic constraint optimization data, the sensitivity analysis and optimization data, and the local optimization data. The thickness cloud map is used to display the spatial distribution of the silicone rubber thickness and to synchronously display the area of ​​electric field intensity change through color mapping.

9. An electronic device, characterized in that, The electronic device includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions. The user interface and the network interface are both used to communicate with other devices. The processor is used to execute the instructions stored in the memory so that the electronic device performs the electric field optimization method for the silicone rubber coating thickness of the disc suspension porcelain insulator as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed, perform the electric field optimization method for the silicone rubber coating thickness of the disc suspension porcelain insulator as described in any one of claims 1 to 7.

Images