Transformer insulation state diagnosis method based on improved support vector machine

Abstract

The invention provides a transformer insulation state diagnosis method based on an improved support vector machine, wherein the method is mainly based on an SVM theory and improves a traditional SVM algorithm at the same time. According to the method, a transformer winding structure, namely an XY model, is simulated through a time domain dielectric response, namely a return voltage method, and the return voltage method is adopted to measure the characteristic quantities of an existing transformer oil-paper insulation system: a return voltage peak value, peak value time and a return voltage initial slope. A large amount of experimental characteristic quantities are measured, samples conforming to training are extracted for preprocessing, environmental factors are combined, SVM theory modeling is adopted, the polymerization degree of an unknown oil-immersed paperboard is predicted according to the existing polymerization degree of an oil-immersed paperboard, and then the purpose of diagnosing the insulation state of the unknown transformer is achieved.

Description

technical field [0001] The invention designs a transformer insulation state diagnosis method based on an improved support vector machine, and belongs to the technical field of electric equipment insulation state evaluation. Background technique [0002] In today's era, electric energy is an important reliance for people's basic life and work, and the scale of the power grid is getting larger and larger. Therefore, ensuring the safe and stable operation of power equipment is the basis for power grid security. The failure of the transformer oil-paper insulation system due to aging may cause power outages and cause huge economic losses to the society. [0003] In the early days, our country generally waited until some kind of fault occurred in the transformer before processing and repairing it. In this way, it is difficult to predict the fault, judge the location of the fault and the extent of the impact of the fault, and it will also bring many unsafe factors and hidden dange...

AI Technical Summary

Problems solved by technology

However, due to the randomness, ambiguity and uncertainty of the cause of transformer faults, it is limited to diagnose the fault state of transformers only based on the gas content in transformer oil

Since a single source of dissolved gas analysis information cannot fully reflect the fault state of the transformer

Images