Insulation fault diagnosis method and system for high-voltage equipment

Abstract

The invention discloses an insulation fault diagnosis method for high-voltage equipment. The method comprises the steps of (1) acquiring a polluted training sample for representing partial discharge signals of a plurality of insulation fault types of the high-voltage equipment, extracting phase resolution pulse sequence data based on the polluted training sample, and normalizing the phase resolution pulse sequence data; (2) training a constructed deep sparse denoising autoencoder through the normalized phase resolution pulse sequence data; and (3) inputting the polluted partial discharge signals of the to-be-identified high-voltage equipment into the trained deep sparse denoising autoencoder, and obtaining the defect type of the high-voltage equipment based on output of an output classification layer of the deep sparse denoising autoencoder. In addition, the invention further discloses an insulation fault diagnosis system for the high-voltage equipment. The system comprises a data preprocessing module and a fault identification module.

Description

technical field [0001] The present invention relates to a fault diagnosis method and system, in particular to a fault diagnosis method and system for high-voltage equipment. Background technique [0002] Partial discharge (PD) is one of the important reasons for the failure of high-voltage equipment. Long-term accumulation of PD will cause a series of physical and chemical reactions in high-voltage equipment, aggravate insulation damage, and cause equipment failure. PD status detection is an important means to ensure the reliable operation of high-voltage equipment, and PD fault identification is the core link of PD detection. In recent years, the neural network diagnosis technology expresses the learned fault diagnosis knowledge with the neural network connection weights through the learning of fault samples, and has the ability of fuzzy matching of faults, similarity induction and associative memory. Among them, the most commonly used neural network diagnosis technology i...

AI Technical Summary

Problems solved by technology

[0003] That is to say, the existing neural network diagnosis technology has a good recognition ability when the data with no interference or small interference signal is used as a sample. However, because the electromagnetic environment of the substation site is very complex, PD detection is susceptible to various electromagnetic interferences. Impact

Under the influence of multiple factors, the characteristics of electromagnetic interference are dynamically changing, which increases the difficulty of electromagnetic interference identification and suppression, greatly reduces the identification accuracy of the existing technology, and causes false positives and false negatives.

Images