Power transformer fault diagnosis device and method based on BP nerve network algorithm

Abstract

The invention relates to a power transformer fault diagnosis device and method based on a BP nerve network algorithm; the device comprises a transformer fault diagnosis data import module, a fault type output module and a data analysis module; a rough set processing unit, a normalization processing unit, a BP nerve network processing unit, a device fault data interface module and a data output interface module are arranged in the data analysis module; the method uses the rough set to preprocess a BP nerve network training set, extracts features of collected information and forms a decision sample table, uses the rough set to parse extraction rules, removes redundancy attributes, carries out data normalization treatment, finally uses the BP nerve network to train the sample data after normalization treatment, thus diagnosing the transformer fault main factors, effectively ensuring transformer normal operations, improving service life, reducing working personnel work pressure, and reducing enterprise economic losses.

Description

technical field [0001] The invention belongs to the technical field of power transformer fault diagnosis, in particular to a power transformer fault diagnosis device and method based on BP neural network algorithm. Background technique [0002] The power equipment in the power system is an important equipment to ensure the normal operation of the power system. How to quickly and accurately diagnose the power equipment plays a vital role in the normal operation of the power system. In terms of equipment maintenance in the electric power industry, most of the current fault diagnosis also adopts traditional judgment methods, relying on professionals to manually analyze data, which is very inefficient and cannot effectively obtain evidence, accurate, quantitative and timely feedback information, which affects fault diagnosis. effectively proceed. Therefore, power companies urgently need an effective fault diagnosis method to help them carry out fault early warning efficiently a...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to overcome the deficiencies of the prior art, to provide a power transformer fault diagnosis device and method based on BP neural network algorithm, to solve the problem that the existing traditional fault diagnosis method is inefficient, inaccurate and The defect of not being timely, more effectively solves the problem that the BP neural network algorithm currently used for fault diagnosis of transformer faults is not reliable enough to meet the accuracy requirements of fault diagnosis due to unoptimized analysis results

Images