A novel mechanical fault diagnosis for high-voltage circuit breakers with zero-shot learning

Abstract

In recent years, data-driven methods have been widely used in the field of high-voltage circuit breakers (HVCBs) fault diagnosis. However, due to the complex mechanical structure of HVCBs and the special operating environment, it is difficult to obtain a large amount of fault samples and exhaust all fault types. The lack of fault samples and fault types typically results in significant degradation of diagnostic performance. To address this problem, we design a novel method named R-MLL for zero-shot HVCB fault diagnosis. R-MLL tries to identify unseen fault types only by training seen fault types. First, to focus on all the details of the HVCB mechanical vibration signal, the wavelet transform is used to multi-scale refine the fault data. Second, a new network (RDSCNN) is designed to extract multidimensional features based on convolutional neural network incorporating residual block and depthwise separable convolution. Third, a multi-label attribute learning network is designed, enabling the fusion of fault features and attributes and allowing attribute labels to assist fault diagnosis tasks. Extensive experiments show that R-MLL gets average accuracy of 86.2% for compound fault diagnosis without the need of using target fault samples for building the diagnostic model. Comparisons with a number of state-of-the-art techniques show the superiority of the proposed method for zero-shot HVCB diagnosis.