基于动态残差收缩网络的滚动轴承故障诊断OA

In recent years,rotating machinery and equipment has been widely used in the field of modern industrial production.As one of the key parts of rotating machinery,the rolling bearing is easy to wear and lead to mechanical failure due to the long time working in changeable and noisy harsh environment.To solve this problem,an intelligent fault diagnosis method based on dynamic residual shrink-age network(DyRSN)is proposed.The dynamic features,according to different input vibration data,can be adaptively captured by this method,thereby breaking through the limitation of the traditional static feature extraction method on the fixed network structure and pa-rameters.Secondly,the noise can be adaptively eliminated by utilizing the automatic soft thresholding module,so as to address the issue of noise interference in the actual application scene and improve the anti-noise capability of the model.Finally,the real vibration data of motor bearing bench is obtained by the vibration signal acquisition system of motor bearing based on wireless network to verify the effec-tiveness of the proposed method.The experimental results validate the good robustness of the proposed method and the feasibility of ac-curate rolling bearing diagnostics.