Transformer fault combined diagnosis model building method and diagnosis method

Abstract

The invention provides a novel power transformer fault combined diagnosis model building method and a fault diagnosis method; the diagnosis model building method comprises the following steps: using at least two of the following diagnosis models to primarily diagnose the oil dissolving gas analysis data: a Naive Bayes diagnosis model, a RVM diagnosis model and a matter-element diagnosis model; carrying out weighted average for the primary diagnosis result, using the secondary RVM diagnosis model to make the secondary diagnosis, thus obtaining the combined diagnosis model; using the combined diagnosis model to make fault diagnosis. The method can fully utilize advantages of various diagnosis models, thus effectively improving the diagnosis precision and validity.

Description

technical field [0001] The invention belongs to the field of transformers, and in particular relates to a power transformer fault combination diagnosis method. Background technique [0002] Fault diagnosis of transformer based on dissolved gas analysis (DGA) in oil is simple and feasible, and has been verified in actual operation, maintenance and a large number of research results, but the problem is that fault samples are scarce, which is based on DGA and sample The generalization of the learned transformer fault diagnosis method poses difficulties. According to the research results of various existing intelligent diagnosis methods, each method has different advantages and disadvantages. In view of this, looking for a method that can give full play to the advantages of multiple intelligent diagnostic methods, [0003] Matter-element theory can deal with qualitative and quantitative problems well, and has the advantages of simple modeling and good effect, while cloud model...

AI Technical Summary

Problems solved by technology

[0002] Fault diagnosis of transformer based on dissolved gas analysis (DGA) in oil is simple and feasible, and has been verified in actual operation, maintenance and a large number of research results, but the problem is that fault samples are scarce, which is based on DGA and sample The generalization of the learned transformer fault diagnosis method brings difficulties

[0010] However, these diagnostic methods do not fully consider the advantages and disadvantages of each diagnostic model, and perform poorly in terms of diagnostic accuracy and effectiveness.

Images