Mechanical fault diagnosis of high voltage circuit breaker using multimodal data fusion

• Published in: PeerJ. Computer science Vol. 10; p. e2248
• Main Authors: Li, Tianhui, Xia, Yanwei, Pang, Xianhai, Zhu, Jihong, Fan, Hui, Zhen, Li, Gu, Chaomin, Dong, Chi, Lu, Shijie
• Format: Journal Article
• Language: English
• Published: United States PeerJ. Ltd 26.08.2024; PeerJ Inc
• Subjects: Algorithms and Analysis of Algorithms; Artificial Intelligence; Deep learning; Fault diagnosis; Neural Networks; Seizures (Medicine); Sensors; Deep learning; Fault diagnosis; Artificial intelligence
• ISSN: 2376-5992; 2376-5992
• DOI: 10.7717/peerj-cs.2248

A high voltage circuit breaker (HVCB) plays a crucial role in current smart power system. However, the current research on HVCB mainly focuses on the convenience and efficiency of mechanical structures, ignoring the aspect of their fault diagnosis. It is very important to ensure the circuit breaker conducts in a normal state. According to real statistics when HVCB works, most defects and faults in high voltage circuit breakers is caused by mechanical faults such as contact fault, mechanism seizure, bolt loosening, spring fatigue and so on. In this study, vibration sensors were placed at four different locations in the HVCB system to detect four common mechanical faults using vibration signal. In our approach, a convolutional attention network (CANet) was introduced to extract features and determine which mechanical faults occur within a fixed period of time. The results indicate that the mechanical fault diagnosis accuracy rate is up to 94.2%, surpassing traditional methods that rely solely on vibration signals from a single location.