Method for diagnosing mechanical fault of high-voltage circuit breaker

Abstract

The invention relates to a method for diagnosing a mechanical fault of a high-voltage circuit breaker, which is characterized by comprising the steps of acquiring vibration signals of the high-voltagecircuit breaker, performing time-domain segmentation processing on the vibration signals of the high-voltage circuit breaker, extracting Tsallis entropy features for the segmented signals, and diagnosing the state of the high-voltage circuit breaker by using a hierarchical hybrid classifier formed by an OCSVM (One-class Support Vector Machine) and an ELM (Extreme Learning Machine). Compared withmultiple traditional classifiers, the method can avoid a circumstance that a failure sample is mistakenly recognized as a normal state due to adoption of the hierarchical hybrid classifier, and the mechanical state recognition effect is improved. In addition, the multilevel hybrid classifier can accurately recognize the failure state of an untrained sample and discover emerging faults in electrical equipment. The method has the advantages of ability of being scientific and reasonable, high applicability, high accuracy, excellent effect and the like.

Description

technical field [0001] The invention relates to a method for diagnosing a mechanical fault of a high-voltage circuit breaker, which is applied to the online diagnosis of the mechanical fault state of the high-voltage circuit breaker and the identification of unknown fault types. Background technique [0002] On-line diagnosis of high voltage circuit breaker (High voltage circuit breaker, HVCB) mechanical failure is an important prerequisite for the safe operation of the circuit breaker. Finding hidden safety hazards in the operation of the circuit breaker and timely repairing and maintaining the fault point are important for maintaining the safety and stability of the power system. significance. With the advent of the Internet era, people have higher and higher requirements for electrical equipment monitoring and maintenance technology. Traditional detection technology cannot meet the requirements in many aspects, and there will be insufficient maintenance or blind maintenan...

AI Technical Summary

Problems solved by technology

However, due to the large variety of mechanical faults of high-voltage circuit breakers, the small number of actions, and the high cost of obtaining fault samples, it is difficult to obtain training samples that include all fault types.

Images