Transformer fault diagnosis method based on similarity analysis strategy

Abstract

The invention discloses a transformer fault diagnosis method based on a similarity analysis strategy, and the method can achieve the accurate diagnosis of a transformer fault type on the premise thata limited number of dissolved gas concentration data serve as a reference. Specifically, the method comprises the following steps: carrying out multi-aspect ratio characteristic construction on dissolved gas concentration data; using a discriminant partial least squares algorithm for carrying out feature conversion on the concentration ratio data, and finally, implementing similarity analysis based on neighbors, so that the fault type of the transformer is diagnosed. The method basically does not involve complex transformation or mathematical calculation, and is simple to operate and very easyto implement. In addition, in the implementation process of the method, certain model parameters do not need to be determined subjectively, so that the problem of parameter selection is greatly solved.

Description

technical field [0001] The invention relates to a transformer fault diagnosis method, in particular to a transformer fault diagnosis method based on a similarity degree analysis strategy. Background technique [0002] With the increasing demand for power, transformers have become essential power equipment in power transmission systems. As a key link in power supply and distribution, the performance of the transformer will directly affect the operation of the entire power system. Any type of transformer fault will lead to power waste or even more serious economic losses, so the fault diagnosis of transformer equipment is of great research significance to avoid potential power or other economic losses. Since the transformers used in the power supply and distribution system are generally oil-immersed transformers, the common way to implement transformer fault diagnosis is to analyze the dissolved gases (hydrogen, methane, ethane, ethylene, and acetylene) in the transformer oil...

AI Technical Summary

Problems solved by technology

However, there is a significant technical problem in transformer fault diagnosis driven by dissolved gas concentration data: the data of dissolved gas concentration under each f

Images