Application of an information fusion method to the incipient fault diagnosis of the drilling permanent magnet synchronous motor

The signal of incipient fault in the drilling permanent magnet synchronous motor (DPMSM) is not obvious, and it is easy to be submerged by noise. Moreover, the sensitivity of signals to different faults varies, and the fault features of different fault severity are different. Therefore, the diagnostic accuracy is generally low with a single signal for the incipient fault of the DPMSM. A data-driven information fusion method for the incipient fault diagnosis of the DPMSM is presented. Firstly, the empirical wavelet transform (EWT) method is used for signal analysis. Then, the singular value decomposition (SVD) method and the principal component analysis (PCA) method are used to extract the fault feature of the vibration signal and the torque signal, respectively. Finally, the Bayesian network (BN) method is applied to the fault diagnosis with the vibration signal method and torque signal method, and the improved evidence theory method based on the Dempster-Murphy rule is used as an information fusion method to improve diagnostic accuracy. The diagnostic accuracy of the three methods is compared and discussed, the information fusion method has stable and highest diagnostic accuracy for faults with different severity under different load conditions.Note to Practitioners-This article was inspired by the field experience of the maintenance engineers. Our maintenance engineers have found that the diagnosis method based on a single signal is not stable for the DPMSM faults. For different types of faults, the diagnostic accuracy of the vibration signal method is better for mechanical faults, while the diagnosis effect of the torque signal method is better for excitation faults. For different fault severity, the vibration signal method can hardly correctly diagnose the incipient faint faults, while the diagnosis effect of the torque signal method is better for the incipient faults. For faults under different load conditions, the diagnostic accuracy of the two methods decreases with the up in load condition. Based on the above findings, we want to explore the relationship between the diagnostic accuracy of the two methods and the fault type, fault severity, and load condition, and hope to find a better and more stable diagnostic method for engineering applications. Based on this study, the practitioners can select appropriate fault diagnosis methods according to fault type, fault severity, and load condition.