Air breakdown voltage prediction method based on path feature set and support vector regression

Abstract

The present invention relates to high voltage and insulation technology, in particular to an air breakdown voltage prediction method based on path feature set and support vector regression, constructing a training sample set and establishing its finite element simulation model, performing electrostatic field calculation and extracting the shortest path feature set, After standardized processing, it is used as the input parameter, and the breakdown voltage is used as the output parameter; the prediction model is established by using the support vector regression machine (SVR), the model is trained through the training sample set, and the optimization algorithm is used to optimize the parameters of the SVR to obtain the optimal Prediction model: establish a finite element simulation model of the air gap to be predicted, perform electrostatic field calculation and feature extraction, standardize the shortest path feature set, and input it to the optimal prediction model, the output of the model is the impact of the air gap to be predicted Breakthrough voltage predictions. The prediction method has simple operation process, reliable prediction accuracy, high calculation efficiency, can greatly reduce the experimental workload, and has good generalization.

Description

technical field [0001] The invention belongs to the technical field of high voltage and insulation, in particular to an air breakdown voltage prediction method based on path feature set and support vector regression. Background technique [0002] Air is the most widely used insulating medium in power systems, and the breakdown voltage of the air gap is an important basis for the insulation design of high-voltage electrical equipment. At present, the insulation design of power transmission and transformation projects and various high-voltage electrical equipment mainly depends on the air gap discharge characteristics obtained from discharge tests. The cost of test research is high and the cycle is long, and the empirical formulas obtained are often limited in applicability and difficult to be popularized and applied. In all kinds of complex engineering gap structures. Obtaining the breakdown voltage of the air gap by simulation calculation instead of high-voltage test has be...

AI Technical Summary

Problems solved by technology

The above-mentioned disclosed technology extracts the electric field feature quantity from the four spatial regions of "the whole area, the discharge channel, the electrode surface, and the discharge path". For complex engineering gaps, these spatial regions are often difficult to define due to the extremely irregular electrode structure

Images