Transformer Fault Diagnosis Method Based on Feature Information Quantization and Weighted knn

Abstract

The invention discloses a transformer fault diagnosis method based on characteristic information quantization and weighted KNN, comprising the following steps: S1, dividing sample data into a training set and a test set; S2, inputting a training set, and preprocessing the sample data; S3, based on Principal component analysis (PCA) and gray correlation analysis (GRA) quantify the fault feature information; S4. Introduce the particle swarm optimization algorithm to optimize the weighted KNN classification algorithm. According to the real fault category, the samples in the standardized fault feature matrix are trained to obtain the power The transformer fault diagnosis model realizes the classification of power transformer faults; S5, input the test set into the power transformer fault diagnosis model, obtains the diagnosis result, and realizes the diagnosis of power transformer faults; the present invention solves the problems of low processing efficiency and model training in the prior art Difficulties and limitations.

Description

technical field [0001] The invention belongs to the technical field of power faults, in particular to a transformer fault diagnosis method based on feature information quantization and weighted KNN. Background technique [0002] As one of the core equipment in the power system, the power transformer takes effective measures to make accurate judgments on the abnormal state or fault inside the transformer, which is of great significance to the whole system. Power transformer fault diagnosis methods are mainly divided into three categories: the first type is based on analytical models, through the establishment of precise mathematical and physical models for transformer fault diagnosis; the second type is the use of incomplete prior knowledge to establish qualitative models, reasoning Transformer fault categories, such as expert systems, fault decision trees and other methods; the third category is based on data-driven power transformer fault intelligent classification methods,...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above-mentioned deficiencies in the prior art, the present invention provides a transformer fault diagnosis method based on characteristic information quantification and weighted KNN with high classification and diagnosis efficiency, high practicability and high accuracy, which solves the problems existing in the prior art Low efficiency, difficult model training and limitations

Images