Transformer fault diagnosis method based on gauss transform and global optimization SVM (support vector machine)

Abstract

The invention discloses a transformer fault diagnosis method based on gauss transform and global optimization SVM (support vector machine) and belongs to the field of fault diagnosis of a transformer.The method comprises the following steps of S10, calculating a three-ratio characteristic quantity according to DGA data of a transformer fault characteristic gas; S20, performing normalization preprocessing on the three-ratio characteristic quantity to obtain a preprocessed sample which is divided into a training sample and a test sample; S30, constructing an SVM fault diagnosis model, and establishing the SVM fault diagnosis model based on GA (Genetic Algorithm) optimization in combination with a cross validation principle and a genetic algorithm; and S40, diagnosing the test sample according to the SVM fault diagnosis model based on GA optimization to obtain a fault diagnosis result. Compared with a transformer fault diagnosis accurate rate performed by use of a conventional standard support vector machine method, an IEC three-ratio method and a neural network algorithm, the accurate rate of a transformer fault diagnosis result obtained by the invention is higher.

Description

technical field [0001] The invention belongs to the field of transformer fault diagnosis, in particular to a transformer fault diagnosis method based on Gaussian transformation and global optimization SVM. Background technique [0002] The power transformer is one of the most important electrical equipment in the power system, and its safe and reliable operation is of great significance to ensure the safety and stability of the power grid. Therefore, it is of great practical significance to study transformer fault diagnosis technology and improve the operation and maintenance level of transformers. Dissolved gas analysis (DGA) in transformer oil is an important method for fault diagnosis of oil-immersed transformers. H in transformer oil 2 , CH 4 , C 2 h 2 , C 2 h 4 、C 2 h 6 The component content of characteristic gases such as CO and CO is closely related to the type of fault. A large number of studies have shown that transformer fault diagnosis cannot only depend o...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a transformer fault diagnosis method based on Gaussian transformation and global optimization SVM, thereby solving the shortcomings of the problem of missed judgment and misjudgment in the existing power transformer insulation latent fault diagnosis

Images