A joint deep learning model for bearing fault diagnosis in noisy environments

In practical engineering environments, rolling bearing vibration signal is often interfered by strong noise, which negatively affects the diagnostic accuracy of intelligent diagnosis models. To solve the above problem, a fault diagnosis model (MDCAE-CACNN) that fuses a multi-scale dilated convolutional auto-encoder (MDCAE) and a channel attention-based convolutional neural network (CACNN) is proposed. First, the MDCAE model is used to capture the feature information of different time scales in rolling bearing vibration signal by using convolutional kernels with different receptive field sizes. Through unsupervised learning, the noise is removed to obtain high-quality reconstructed signals. Then, the fault features in the reconstructed signal are effectively extracted by CACNN model and the fault type is accurately diagnosed. The experimental results show that the proposed MDCAE-CACNN model exhibits remarkable improvements in fault diagnosis accuracy and effectiveness. Additionally, it showcases high levels of precision, robustness, and generalization ability.