Abstract
Recently, condition monitoring methods using the sound of the machine have attracted attention. Since approaching high voltage equipment increases the risk of electrocuting, non-contact data acquisition is desirable. Most of the research targets of acoustic monitoring are rotating machines and it is not clear whether it is effective for machines that switch between two states, such as contactors and circuit breakers. In this work, several investigations have been carried out on the acoustic condition monitoring of contactor. The Mel-frequency cepstrum coefficients (MFCCs) were obtained from the sound data of the contactors under normal and simulated fault conditions. Support Vector Machine (SVM) was trained with MFCCs and found that it could detect and diagnose contactor faults with high accuracy.
Highlights
BackgroundContactors, switches and circuit breakers are used in Japan’s high-speed railways and in power distribution networks around the world, and the failure of these equipment can be significant
The results showed that 13 Mel-frequency cepstrum coefficients (MFCCs) was optimal for failure detection
Since the operating sound of contactors varies with time, the time-varying data obtained by MFCC was used as training data for the Support Vector Machine (SVM)
Summary
Contactors, switches and circuit breakers are used in Japan’s high-speed railways and in power distribution networks around the world, and the failure of these equipment can be significant. Huang et al.[18] proposed a method to extract the EMD energy entropy from the vibration data of a 72.5 kV SF6 gas circuit breaker and to classify the feature data using a multi-layered SVM. In this verification, the following failures were considered: ‘‘loosing the base screw,’’ ‘‘invalid overtravel of the buffer spring,’’ and ‘‘time-delay vibration event caused by the inadequate lubrication for the operating mechanism.’’ Twenty-five data for each failure, and 25 normal data were collected. Huang et al.[19] proposed a fault diagnosis method using variational mode decomposition (VMD) and a multi-layered SVM for circuit breaker vibration data. These results showed that the proposed method is practical for several types of circuit breakers
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
