Application of Intelligent Diagnosis System in Fault Prediction and Maintenance of Vacuum Circuit Breaker

Traditional fault prediction methods often rely on manual experience and rules, which has some shortcomings. The intelligent diagnosis system combines advanced data analysis technologies, such as machine learning, artificial intelligence and signal processing, and can find hidden fault patterns from a large amount of data and improve the accurate prediction ability of faults. Firstly, the vibration signals during operation are obtained at two different positions of the high voltage vacuum circuit breaker by electromagnetic repulsion mechanism. Then, the improved S-transform is used for time-frequency analysis of the vibration signal, and the feature quantity is extracted based on normalized energy entropy, and the dimension of the feature vector is reduced by principal component analysis. Finally, the eigenvalues are input to SVM training model for fault classification and compared with wavelet packet decomposition. In addition, compared with other methods, the proposed method also shows superiority in accuracy. In summary, the fault diagnosis method based on improved S-transform and support vector machine has high accuracy and superiority in fault prediction and maintenance of HV vacuum circuit breaker.