Evaluation and Prediction Method of Rolling Bearing Performance Degradation Based on Attention‐LSTM

Abstract

It is significant for the evaluation and prediction of the performance degradation of rolling bearings. However, the degradation stage division of the rolling bearing performance is not obvious in traditional methods, and the prediction accuracy is low. Therefore, an Attention-LSTM method is proposed to improve the evaluation and prediction of the performance degradation of rolling bearings. First, to reduce the uncertainty of the manual intervention, performance degradation characteristic indexes of rolling bearings are evaluated and screened by the correlation, the monotonicity, and the robustness. Second, the original characteristic indicator curve is divided into the Health Indicator (HI) curve and the residual curve by means of fixed-window averaging to quantitatively and intuitively reflect the deterioration degree of the rolling bearing performance. Finally, the Attention mechanism is combined with the LSTM model, and a scoring function is established to enhance the prediction accuracy. The scoring function is used to adjust the intermediate output state weight of the LSTM model and improve the prediction accuracy. The appropriate network structure and the parameter configuration are determined, and the prediction model of rolling bearing degradation performance is established. Compared with other models, the method proposed by this paper makes full use of the historical data and is more sensitive to the key information in the long time series, and the eRMSE index and the eMAE index of the two sets of experimental data are minimum, and the prediction accuracy of rolling bearing degradation performance is higher. The model has the strong robustness and the generalization ability, which has the important engineering practical value for the prediction of the equipment health state.

Research on the online evaluation of the straightness error of hydrostatic guideways based on deep learning

“…An attention mechanism 27 takes advantage of the shift of people's attention to reasonably change the focus on information obtained from the outside world, which is a mechanism focusing on local…”

“…A loss function [27] is used to calculate the deviation between the theoretical value and the actual value of the network model. The input to the loss function is the training sample, bias and weight of the data set, and the output is the theoretical sample error loss value.…”

RUL prediction method for rolling bearing using convolutional denoising autoencoder and bidirectional LSTM

“…Wang et al [20] proposed a method that decomposes fused features on multiple scales and removes high-frequency components to reduce volatility, then combines stacked self-encoders with Bi-LSTM models to achieve high-quality feature extraction and satisfied precision. Wang et al [21] proposed a prediction model of LSTM under an attention mechanism, which makes full use of past information under long sequences to improve the prediction ability. Jiang and Xiang [22] proposed a prediction model for ensemble LSTM with deep extraction of bearing degradation features, which adopted the maximum information component criterion to integrate multiple LSTM to improve the prediction stability of the model.…”

Deep learning method for remaining useful life prediction of the rolling bearing of high-speed train

“…The first is to predict whether the bearing will fail in a certain period of time in the future and the probability of failure. The second is the prediction of bearing RUL [8][9][10]. With the mature application of deep learning methods and the emergence of optimization algorithms, more complex deep cyclic networks continue to show their advantages and make important achievements in time series prediction.Based on the particle swarm optimization algorithm, the back propagation neural network (BPNN) has been optimized, and has obtained better robustness and prediction accuracy [11].…”