A novel fault diagnosis method for early faults of PMSMs under multiple operating conditions

Abstract

Early fault diagnosis method under multiple operating conditions (OCs) is very important to improve the reliability of the permanent magnet synchronous motors (PMSMs) system. In this paper, a novel early fault diagnosis method for irreversible demagnetization fault and inter-turn short fault under multiple OCs in PMSM is proposed. Multi-layer self-attention mechanism is constructed to capture the long time dependency from the sensor signal, which can fuse the features of individual OCs to diagnose faults under unseen OCs. Furthermore, local feature extraction structure with end-to-end deep learning features and time–frequency domain features is proposed to extract effective features from early faults. The proposed method uses only two-phase current signals as the inputs to diagnose the faults. By comparing 1D convolutional neural network structure with multi-variables and universal machine learning methods, the experimental results show that the proposed method achieves high accuracy for early fault diagnosis of PMSM in unseen OCs.