On-line transformer fault diagnosis method based on SVM and DGA

Abstract

The invention discloses an on-line transformer fault diagnosis method based on support vector machines (SVM) and dissolved gas analysis (DGA), which belongs to the field of transformer fault diagnosis. The method comprises the following steps of: acquiring the concentration of fault feature gases including H2, CH4, C2H2, C2H4 and C2H6 in transformer insulating oil by a gas chromatographic analysis method, normalizing the data through a preprocessing system, sending the data to a classification diagnosis system assembled by an integrative learning method and formed by six SVM classifiers according to a decision process, classifying the measurement data through calculation, judging the running state of the transformer, and at last outputting the diagnosis results. In the method, the support vector machines (SVM) of the artificial intelligence technology are adopted to analyze the gases in the oil, and the relation between gas components and the running state of the transformer can be objectively and essentially reflected, thereby the accuracy of fault diagnosis is effectively improved.

Description

technical field [0001] The invention relates to a transformer fault diagnosis method, in particular to an online transformer fault diagnosis method based on SVM (Support Vector Machine) and DGA (Dissolved Gas Analysis), belonging to the field of transformer fault diagnosis. Background technique [0002] A safe and stable power supply system is an important foundation for the development of the national economy and a necessary condition for the harmonious development of a modern industrial society. As the key equipment of the power supply system, the real-time monitoring of the transformer can effectively ensure the reliability of the power supply system. [0003] At present, the most effective method for internal fault diagnosis of transformers is Dissolved Gas Analysis (DGA) in oil. Most power transformers in the domestic power system use insulating oil to dissipate heat and insulate the internal system, and when the transformer is in different operating states, the compon...

AI Technical Summary

Problems solved by technology

[0005] Although there are currently a large number of studies on transformer fault diagnosis using support vector machines, there are still the following problems in its practical application: 1) No real-time diagnosis system based on support vector machines has been established: most studies have given the idea of ​​fault diagnosis and adopted the existing The data is systematically carried out offline diagnostic tests, but a specific system structure capable of real-time diagnosis is rarely built; 2) Lack of reasonable data preprocessing: the data obtained by sampling dissolved gases in oil must undergo reasonable preprocessing to To effectively describe the operating characteristics of transformers, some studies lack preprocessing of raw data, or the preprocessing method is unreasonable; 3) The diagnosis and decision-making process is unreasonable: support vector machine is essentially a binary classifier, and transformer faults are There are many types, so all faults cannot be distinguished by only one SVM fault classifier. There are some deficiencies in the traditional diagnosis decision-making process, such as blind areas in division and asymmetric training sample sizes, etc., which affect the reliability of diagnosis.

Images