Partial discharge diagnosis method for power equipment based on data enhancement and neural network

Abstract

The invention proposes a partial discharge diagnosis method for power equipment based on data enhancement and a neural network. Specific to partial discharge data detected when power equipment such astransformers, GISs (Geographic Information Systems) and switch cabinets has defects, the sample size is enriched and a sample database is established by various data enhancement methods, and different neural networks are adopted for training according to the characteristics of different power equipment types and defect types, so that a diagnosis algorithm with higher generalization ability and higher diagnosis pertinence for different faults of different power equipment is obtained, and the partial discharge diagnosis accuracy of the power equipment is improved.

Description

technical field [0001] The invention relates to the field of partial discharge detection of electric power equipment, and more specifically, the present invention relates to a method for diagnosing partial discharge of electric power equipment based on data enhancement and neural network. Background technique [0002] With the rapid development of grid scale and the continuous advancement of grid intelligence, the reliability and safety requirements of power equipment operation are also increasing. The insulation performance of power equipment is a key indicator of constant equipment status, and it is effective for partial discharge , Accurate detection and evaluation are the basis for ensuring the safe and reliable operation of power equipment. [0003] After the power equipment is put into operation, due to design defects, surface contamination and poor contact, etc., partial discharges will occur on the equipment. When the discharge occurs, the fault point will produce ph...

AI Technical Summary

Problems solved by technology

[0005] 1. Since partial discharge is affected by many factors such as the structural design, manufacturing process, operating environment, operation and maintenance of power equipment, the amount of disintegration fault sample data accumulated over the years is small, and it is difficult to cover all types of partial discharge;

Images