Method for recognizing partial discharge pattern of gas insulation combined electrical apparatus

Abstract

The invention provides a method for recognizing a partial discharge pattern of a gas insulation combined electrical apparatus, which comprises the steps of building different types of partial discharge defect models, performing a simulated discharge experiment on each model, and acquiring waveform data by adopting an ultrahigh-frequency detection method; extracting a multi-dimensional feature vector representing waveform features by adopting an EEMD algorithm and an SVD algorithm; training acquired samples by adopting a support vector machine optimized through a particle swarm algorithm; and classifying measured partial discharge by using the trained support vector machine. According to the invention, pattern recognition is performed on partial discharge of the gas insulation combined electrical apparatus by adopting the support vector machine optimized by the particle swarm algorithm as a classifier, the support vector machine can acquire high classification accuracy under the condition that the number of training samples is small, two key parameters in the algorithm need to be set in advance, the two parameters can be effectively optimized by adopting the particle swarm algorithm, and the classification performance of the support vector machine is improved.

Description

technical field [0001] The invention relates to the field of high-voltage insulation fault diagnosis, in particular to a method for recognizing partial discharge patterns of gas-insulated combined electrical appliances. Background technique [0002] During the design, manufacture, transportation and installation of gas-insulated combined electrical appliances, latent insulation defects will inevitably be left inside. These defects will not cause serious damage to the equipment in the early stage of equipment operation, but with the long-term pressurized operation of the equipment, its harmfulness will gradually become prominent. Partial discharge is an early sign of insulation performance degradation of combined electrical equipment due to internal defects. Effective monitoring and classification of partial discharge is of great significance to ensure the safe operation of equipment, evaluate the insulation status of equipment, and guide reasonable maintenance of equipment. ...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a partial discharge pattern recognition method for gas-insulated combined electrical appliances, aiming at the drawbacks of the existing partial discharge pattern recognition methods, which have poor resistance to environmental noise, and to provide a theory for accurately evaluating the insulation status of equipment and formulating corresponding maintenance strategies and method based on

Images