An Open-Circuit Fault Diagnosis Method for Three-Level Neutral Point Clamped Inverters Based on Multi-Scale Shuffled Convolutional Neural Network.

This study constructs a power switching device open-circuit fault diagnosis model for a three-level neutral point clamped inverter based on the multi-scale shuffled convolutional neural network (MSSCNN) and extracts and classifies the fault information contained in the output current of inverters. The model employs depthwise separable convolution and channel shuffle techniques to improve diagnostic accuracy and reduce model complexity. The experimental results show that the new model has lower model complexity, better noise resistance and higher average diagnostic accuracy compared with fault diagnosis models based on CNN, ResNet, ShuffleNet V2 and Mobilenet V3 networks.

Analytical Modeling and Analysis of Permanent-Magnet Motor with Demagnetization Fault.

Factors such as insufficient heat dissipation and excessively high temperature can easily lead to demagnetization of the PMs in permanent-magnet (PM) motors. As a result, the magnetic field distribution of the motor will not be uniform, producing fault harmonics and lowering the operational performance of the motor. An essential stage in the diagnosis of faults and the monitoring of motor condition is the establishment of an accurate model of motors with demagnetization faults. In this paper, demagnetization faults are modeled by changing the Fourier coefficients in the Fourier expansion of the magnetization of PMs. This model can be used to determine the motor performance under various types of demagnetization, including radial air gap flux density, back electromotive force (EMF), and torque. On this basis, the corresponding relationship between the demagnetization degree and the fault signature is established, to provide a theoretical foundation for the subsequent demagnetization fault diagnosis. The finite element analysis (FEA) verifies the effectiveness and superiority of the proposed analytical model. The modeling method proposed in this paper can be applied to PM motors with PMs having different magnetization directions and shapes because it is based on the demagnetization region of PMs.

Application of Teager-Kaiser Energy Operator in the Early Fault Diagnosis of Rolling Bearings.

Rolling bearings are key components that support the rotation of motor shafts, operating with a quite high failure rate among all the motor components. Early bearing fault diagnosis has great significance to the operation security of motors. The main contribution of this paper is to illustrate Gaussian white noise in bearing vibration signals seriously masks the weak fault characteristics in the diagnosis based on the Teager-Kaiser energy operator envelope, and to propose improved TKEO taking both accuracy and calculation speed into account. Improved TKEO can attenuate noise in consideration of computational efficiency while preserving information about the possible fault. The proposed method can be characterized as follows: a series of band-pass filters were set up to extract several component signals from the original vibration signals; then a denoised target signal including fault information was reconstructed by weighted summation of these component signals; finally, the Fourier spectrum of TKEO energy of the resulting target signal was used for bearing fault diagnosis. The improved TKEO was applied to a vibration signal dataset of run-to-failure rolling bearings and compared with two advanced diagnosis methods. The experimental results verify the effectiveness and superiority of the proposed method in early bearing fault detection.