Improved power transformer fault diagnosis method

Abstract

The invention belongs to the field of power transformer fault diagnosis, and particularly relates to an improved power transformer fault diagnosis method. The general thought of a fault prediction model is that a CBR (Case-Based Reasoning) and RBR (Rule-Based Reasoning) serial reasoning way is used, the number of feature values of a transform is limited due to the particularity of a case, an overhauling strategy can be quickly obtained if retrieval matching can be carried out, reasoning time is saved, the historical experience case is effectively utilized, and the fault diagnosis efficiency ofthe system is improved. When no proper cases can be matched with the cases in a factbase, a rule reasoning way is adopted, a rule conclusion which is generated by reasoning and proves to be accuratecan be taken as the overhauling strategy result of the case, and a new case is formed. By use of the method, the problems in the prior art that elaborative diagnosis can not be carried out, diagnosisfault time cost is high, faults can not be quickly positioned and the like are mainly solved.

Description

technical field [0001] The invention relates to the field of fault diagnosis of power system transformers, in particular to an improved power transformer fault diagnosis method. Background technique [0002] With the rapid development of the economy, the power grid system is gradually developing towards large capacity, ultra-high voltage, long-distance, and intelligence. Power transformers play a vital role in the power system. Therefore, improving the efficiency of transformer fault diagnosis can not only strengthen the power grid Stability and reliability of operation, but also save energy consumption and improve work efficiency. At present, the commonly used power transformer fault diagnosis method in this field is to conduct DGA (Dissolved Gas Analysis), that is, the analysis of dissolved gas in oil, by taking oil samples online or offline. Then, neural network, support vector machine, GEP (Gene Expression Programming) gene expression programming algorithm, etc. are use...

AI Technical Summary

Problems solved by technology

[0003] The research objective of the present invention is: through comparative analysis of the case to be diagnosed (target case) and the historical case (source case), select the case with high similarity as the diagnosis conclusion of the target case, which can effectively avoid complicated mathematical models, and is scientific Reasonable diagnosis of power system transformer faults can solve the problems of high time cost and inability to quickly locate transformer faults in the existing technology, realize fine-grained diagnosis of potential transformer faults, and ensure accuracy and integrity

Images