Research On Bearing Life Prediction And Fault Diagnosis Based On Deep Learnin

Bearing plays an irreplaceable role in the machinery industry,which always keeps running as the core component of the machinery,especially as a major equipment or a key basic component.Accurately predicting the remaining useful life of bearings can improve production efficiency and maximize economic benefits.At the same time,rapid and high-precision bearing fault diagnosis is an important guarantee for monitoring the safe operation of machinery.The prediction of bearing life and the diagnosis of its fault causes are conducive to quickly determine the bearing health condition and develop maintenance strategies.Aiming at the above two problems,this paper studies the life prediction and fault diagnosis of rolling bearing based on deep learning technology.The specific research contents are as follows:(1)Aiming at the difficulty of extracting fault features from non-stationary signals in the time domain,a remaining useful life prediction method based on multi-scale residual convolution neural network is proposed.The vibration acceleration signal collected by the sensor is converted into a time-frequency domain matrix through continuous wavelet transform,and the time-frequency domain features can better display the fault information in the nonstationary signal.Secondly,the proposed multi-scale residual convolution neural network is used to extract features from the time-frequency domain matrix.Its multi-scale jump structure enables the model to extract more local and global features,and construct more accurate health indicators.Then,in order to highlight the degradation trend of mechanical components,the obtained health indicators are smoothed by Exponential Moving Average.Finally,linear regression is exploited to predict the RUL of the bearing.Performance evaluations based on the public dataset PRONOSTIA,demonstrate the effectiveness of our proposed algorithm,which is superior to existing data-driven algorithms in terms of prediction accuracy.(2)Aiming at the problems of traditional deep learning network modules that are too complex and have a large amount of parameters,this paper proposes a lightweight model based on Depthwise separable convolution and Efficient Channel Attention called the DPW＿ATTCNN model.The DPW＿ATTCNN model first adopts DPW to reduce the parameters of the model.Meanwhile,the ECA attention mechanism is utilized to learn crucial information between neural network channels,which improves the accuracy of bearing fault diagnosis.The DPW＿ATTCNN model is improved based on the Adaptive Batch Normalization algorithm,which has excellent domain adaptive capability.DPW＿ATTCNN model achieves excellent performance using a small number of parameters.The experimental results show that the DPW＿ATTCNN model can achieve 99.58% accuracy in bearing fault diagnosis,which is verified on the public dataset Case Western Reserve University(CWRU)dataset.In addition,the anti-interference evaluation experiment shows that the accuracy of DPW＿ATTCNN model for bearing fault diagnosis is still higher than 95% even under strong noise interference.In the domain adaptive performance test,the DPW＿ATTCNN(Ada BN)model achieves an average fault recognition rate of 97.35%,which further verifies the robustness and effectiveness of the proposed DPW＿ATTCNN algorithm.