In the process of structural health monitoring, effective fault diagnosis of the rotary machinery is crucial to ensure safe and reliable operations. The majority of rotary machinery, however, typically operates under varying operational conditions and is prohibited from operating in the fault state. The fluctuation in these conditions results in a corresponding variation in the distribution of samples, and the difficulty of collecting fault data leads to an imbalance in the number of health and fault samples. Transfer learning provides a promising tool for handling the cross-domain diagnosis problems. However, the potential of transfer learning techniques in motor current analysis as a cost-effective alternative has not yet received sufficient attention." In this article, a novel deep domain adaptation approach called Fault Feature Proxy Transfer (FFPT) is implemented to facilitate knowledge transfer across different operating condition domains in the presence of imbalanced class distribution. The proposed end-to-end scheme automatically learns the fault features from the raw current signals and transfers the fault feature explicitly both considering marginal and conditional distribution discrepancies. In FFPT, a set of proxies is employed to facilitate the transfer of features by establishing an intermediate domain. We introduce the pseudo-labeling-based metric learning to alleviate the problem of class imbalance between health and damage samples. A high accuracy for single and combined faults, a great robustness against class imbalance, and a significant gain in performing knowledge transfer prove the competitive performance of the proposed domain adaptation approach.

Joint Approximate Diagonalization of Eigen-matrices (JADE) cannot deal with non-stationary data. Therefore, in this paper, a method called Non-stationary Kernel JADE (NKJADE) is proposed, which can extract non-stationary features and fuse multi-sensor features precisely and rapidly. In this method, the non-stationarity of the data is considered and the data from multi-sensor are used to fuse the features efficiently. The method is compared with EEMD-SVD-LTSA and EEMD-JADE using the bearing fault data of CWRU, and the validity of the method is verified. Considering that the vibration signals of high-speed trains are typically non-stationary, it is necessary to utilize a rapid feature fusion method to identify the evolutionary trends of hunting motions quickly before the phenomenon is fully manifested. In this paper, the proposed method is applied to identify the evolutionary trend of hunting motions quickly and accurately. Results verify that the accuracy of this method is much higher than that of the EEMD-JADE and EEMD-SVD-LTSA methods. This method can also be used to fuse multi-sensor features of non-stationary data rapidly.

Traction motor’s rolling element bearings are one of the most critical components for the structural health monitoring of high-speed train vehicles. Most structural health monitoring techniques for railway rolling element bearings are using vibration signal. However, the vibration characteristic of cage defect is difficult to be transmitted to external monitoring point owing to the location of cage in bearing. Hence, the cage defect of Railway Traction Motor Bearing (RTMB) is usually difficult to be recognized with motor housing vibration acceleration signal. Considering Induction Motor (IM) itself a sensor, the mechanical imbalance of bearing cage defect can reflect in stator current through the motor gap magnetic field rather than a solid transmission path. A novel strategy with stator current for monitoring the traction motor bearing cage health status in High-Speed Train (HST) is proposed in this paper. This method requires no additional sensor in the practical application. To prove the strategy is feasible and more effective than vibration-based method for the cage fault diagnosis of RTMB, a comprehensive experiment investigation with a real railway traction motor of a HST is completed. Artificial cage defects are processed on bearings at both ends of the induction motor, respectively. Three high-speed (≥250 km/h) conditions are observed. The data analysis results show that vibration-based method is almost invalid at high-speed condition and the proposed current-based method is feasible and effective for the fault diagnosis of high-speed railway traction motor bearing cage.