Switch cabinet electric field prediction and optimization method based on support vector machine and genetic algorithm

Abstract

The invention relates to a switch cabinet electric field prediction and optimization method based on a support vector machine and a genetic algorithm, and the method comprises the steps: 1, selectingmain factors and levels affecting the distribution of an internal electric field of a switch cabinet, building an orthogonal test table, carrying out the calculation of the internal electric field ofthe switch cabinet, obtaining the maximum electric field intensity of the surface of a contact box, and constructing a training sample; 2, establishing a prediction model of the maximum electric fieldintensity of the surface of the switch cabinet contact box by adopting a support vector machine regression model; 3, selecting an influence factor and a horizontal combination to carry out finite element electric field calculation to obtain the maximum electric field intensity of the surface of the contact box, constructing a verification sample, and optimizing a penalty factor and a kernel function parameter of the prediction model to obtain an optimized prediction model; and 4, optimally designing the structure of the switch cabinet by using a genetic algorithm, wherein the value of the influence factor corresponding to the minimum value of the maximum electric field intensity on the surface of the contact box is the optimized structure parameter. The method can simply, efficiently andaccurately predict the electric field of the switch cabinet and optimize the structure of the switch cabinet.

Description

technical field [0001] The invention belongs to the technical field of electric switchgear, and in particular relates to a method for predicting and optimizing the electric field of a switchgear based on a support vector machine and a genetic algorithm. Background technique [0002] As an important power equipment for receiving and distributing electric energy, high-voltage switchgear is widely used in every link of transmission and distribution networks. Its safe operation is directly related to the safety of the entire power grid and the power supply quality of the power system to users. One of the most important electrical equipment. With the continuous development of high-voltage switchgear in the direction of miniaturization and compactness, the space size and floor area of ​​the switchgear are greatly reduced, and more stringent requirements are put forward for the insulation and structural design of the switchgear. Unreasonable structural design and insulation layout...

AI Technical Summary

Problems solved by technology

[0003] At present, high-voltage switchgear mainly uses finite element analysis software to conduct optimization analysis of the electric field. However, the parameters used in the optimization process are mostly existing empirical parameters, and the optimization process usually involves changing parameters many times and repeated tests, which has a large blindness

Especially for the optimization design under multiple influencing factors, if the primary and secondary conditions of the factors are not clear, not only the optimization design workload is heavy, but also the best optimization results may not be obtained

Images