In most industrial applications, it is difficult to obtain complete demagnetization fault signals of all conditions with labels for permanent magnet synchronous motor (PMSM), and motors are not allowed to be disassembled, so non-contact diagnostic methods are essential. A non-contact fault diagnosis method using magnetic leakage signal based on wavelet scattering convolution network (WSCN) and semi-supervised deep rule-based (SSDRB) classifier is proposed. Through magnetic equivalent circuit model analysis, the magnetic leakage signal on motor surface is selected as fault signal. To avoid complex signal processing, the symmetrized dot pattern method is introduced to convert fault signals into two-dimensional images. Then, WSCN is applied to extract features from images, and SSDRB classifier is adopted to diagnose demagnetization fault. Finally, faulty motor prototypes are manufactured for experiment. By comparing with other methods, the superiority and effectiveness of the proposed method using a small number of labeled samples under different conditions are verified.

Most of the mechanical fault diagnosis methods of induction motors (IMs) are based on vibration signals. However, vibration sensors are expensive and require direct contact with IMs. This article proposes a data-driven mechanical fault diagnosis method for IMs using stator current signals, which is more convenient and low cost, since no additional sensors are required. Aiming at the weak representation of mechanical faults in current signals, an intelligent noise elimination method based on noise reconstruction model is proposed to improve the signal-to-noise ratio. Through the automatic feature extraction and classification of the residual current envelope spectrum, high diagnosis accuracy can be obtained even if some differences have existed among samples. The effectiveness of the proposed method is verified by high accuracy diagnosis results on two experimental platforms. The results show that the average diagnostic accuracy of the proposed algorithm for one bearing fault and two eccentricity faults can reach 96%. Even if the fault type and the fault degree are distinguished at the same time, an accuracy of 90% can be achieved for six kinds of bearing faults.

During the long-term operation of motors, their working conditions are changing due to the industrial demands or declining health status, and traditional diagnosis methods perform poorly in that case. This article proposes a fault diagnosis method based on graph cardinality preserved attention network (GCPAT), which can work under varying working conditions, and can be generalized to the transient state. Diagnosis results are obtained by analyzing signal-converting graphs, which are composed of nodes and edges. First, the vibration signals are converted into symmetrical snowflake images by symmetrized dot pattern (SDP) method. Second, SLIC is developed to make homogeneous super-pixels in SDP images as nodes, and form graphs according to color, texture, and distance features. Finally, the GCPAT is utilized to distinguish motor status. Compared with other state-of-art methods, the results show the out-performance of GCPAT under varying working conditions both in steady and transient state.

Data-driven intelligent diagnosis methods require sufficient labeled data during training, which are usually limited in practice. A semisupervised conditional random field-based graph attention network (CRF-GAT) algorithm is proposed in this article for fault diagnosis and condition monitoring. The proposed method combines the advantages of CRF and GAT, and therefore, it achieves semisupervised fault diagnosis by modeling the label dependency and learning object representations. The scheme is optimized with the variational expectation–maximization (EM) algorithm. Specially, the clustering with adaptive neighbor (CAN) method is introduced for constructing the graph. The proposed method is applied in induction motor (IM) and permanent magnet synchronous motor (PMSM), which achieves the identification of the motor status, fault severity, and working condition. The results show that the CRF-GAT can realize an accuracy of above 97% with even below 10% of labeled samples for training, which demonstrates that it is an effective method in semisupervised fault diagnosis.

Intelligent fault diagnosis algorithms require large amounts of data to train models, and the fusion of heterogeneous information from multiple sensors increases the computational complexity exponentially. To address these problems, a few-shot cross-domain motor fault diagnosis method based on multi-sensor information fusion and meta-learning is proposed. Firstly, a multi-sensor heterogeneous information fusion framework, named low-pass pyramidal ratio-color symmetric dot pattern (RP-CSDP), is proposed. It enables to achieve the information fusion of three-axis vibration sensor and three-phase current sensor without increasing the computational burden of the intelligent diagnosis algorithm. Secondly, RP-CSDP fuses and reconstructs the data from both types of sensors into color images. Based on this, a meta-learning database is constructed. The Relation Network (RN) is improved, and various cross-working conditions and few-shot experiments are set up. Finally, the proposed method is promoted to diagnose motor faults that are not present in the training phase. The results show that the proposed method can be quickly adapted to new tasks without repeating training network when faced with new working conditions and faulty types with limited training samples.