Permanent magnet synchronous motors (PMSMs) are widely used due to their unique advantages. Their transmission system mainly relies on rolling bearings; therefore, monitoring the motor’s working status and fault diagnosis for the rolling bearings are the key focuses. Traditional resonance demodulation methods analyze the vibration signals of bearings to achieve bearing fault diagnosis, but the limiting condition is that the inherent frequency needs to be known. Based on the resonance demodulation method, deep learning methods, such as the convolutional neural network (CNN) model designed in this article, have improved the practicality and effectiveness of diagnosis. A physical explanation of the deep learning model for bearing fault diagnosis is presented in this article, the relationship between resonance demodulation and the 1D CNN is analyzed, and the model is trained and validated. The experimental results show that the CNN model can identify different types of bearing faults. The analysis results of the trained CNN model and the intermediate results indicate that the CNN model is consistent with the resonance demodulation method. The optimized method is verified, proving that the model can achieve the classification and diagnosis of fault bearing data collected under different environments after the optimized training method is adopted.

This paper presents an effective method for measuring oil debris with high confidence to ensure the wear monitoring of aero-engines, which suffers from severe noise interference, weak signal characteristics, and false detection. First, an improved variational mode decomposition algorithm is proposed, which combines wavelet transform and interval threshold processing to suppress the complex noise interference on the signal. Then, a long-short-term memory neural network with deep scattering spectrum preprocessing is used to identify the signal characteristics under the multi-resolution analysis framework. The optimal hyperparameters are automatically configured using Bayesian optimization to solve the problem of weak, distorted, and hard-to-extract signal characteristics. Finally, a detection algorithm based on multi-window fusion judgment is applied to improve the confidence of the detection process, reduce the false detection and false alarm rate, and calculate the debris size information according to the sensor principle. The experimental results show that the proposed method can extract debris signals from noise with a signal-to-noise ratio improvement of more than 9 dB, achieve a high recognition accuracy of 99.76% with a missed detection rate of 0.24%, and output size information of debris to meet the need for aero-engine oil debris measurement.