CNN-LSTM-Based Model for Predicting the Remaining Useful Life of Rolling Bearings

To achieve accurate prediction of the remaining useful life of rolling bearings, a prediction method combining convolutional neural network (CNN) and long and short-term memory network (LSTM) is proposed. Firstly, the feature parameters in the time domain frequency domain are extracted, and the degradation trend is determined to be characterized using segmentation function, then the feature parameters are normalized as the input of CNN, and the information is extracted using CNN, and then these deep-level features are input to LSTM These deep-level features are then fed into the LSTM for prediction using the predict function to achieve the goal of rolling bearing life prediction. To verify the rationality of the proposed method, the PHM2012 dataset was used and its whole life cycle vibration data was substituted into the proposed method. The experimental results show that the proposed method has a good fitting effect, and the prediction results are close to the real-life value.