Transformer substation fault diagnosis method and diagnosis device based on improved case-based reasoning

Abstract

The invention relates to a transformer substation fault diagnosis method and diagnosis device based on improved case-based reasoning, and the method gives consideration to the correlation between thecondition attributes of all rules in a case library and the correlation between the condition attributes of other rules, and combines with a similarity measurement method of a weighted Euclidean distance. The method can continuously update the case library, improves the adaptability and accuracy of reasoning through the correlation between signals, has the self-learning capability of the system, and effectively improves the work efficiency of operation and maintenance personnel.

Description

technical field [0001] The invention relates to the field of power system fault diagnosis, in particular to a substation fault diagnosis method and a diagnosis device based on improved case reasoning. Background technique [0002] Smart substations often generate a large number of alarm signals when a fault occurs. It is difficult for substation staff to accurately identify the type and location of the fault from these signals in a short period of time. Therefore, how to quickly and accurately analyze these fault information Fault diagnosis and taking corresponding effective measures to deal with the fault has become a work of great practical significance and economic value. In the prior art, the methods of intelligent fault diagnosis mainly include methods such as artificial neural network (ANN), expert system (ES), Petri network (PN) and case reasoning (CBR), wherein, artificial neural network (ANN) diagnosis method needs There are a large number of samples, and the exper...

AI Technical Summary

Problems solved by technology

However, in the actual smart substation, the quantity of signal data is insufficient and the quality is not high. In complex fault diagnosis modes such as incomplete signals, there is no solution with high accuracy and high applicability.

At present, most of the fault diagnosis systems based on case-based reasoning (CBR) are used. Although they can solve fault diagnosis in the case of incomplete data, the accuracy of similarity retrieval is low and the self-learning ability of cases is weak.

Images