Residual Convolution Long Short-Term Memory Network for Machines Remaining Useful Life Prediction and Uncertainty Quantification

Abstract

Recently, deep learning is widely used in the field of remaining useful life (RUL) prediction. Among various deep learning technologies, recurrent neural network (RNN) and its variant, e.g., long short-term memory (LSTM) network, are gaining more attention because of their capability of capturing temporal dependence. Although the existing RNN-based approaches have demonstrated their RUL prediction effectiveness, they still suffer from the following two limitations: 1) it is difficult for RNN to extract directly degradation features from original monitoring data, and 2) most of the RNN-based prognostics methods are unable to quantify the uncertainty of prediction results. To address the above limitations, this paper proposes a new method named Residual convolution LSTM (RC-LSTM) network. In RC-LSTM, a new ResNet-based convolution LSTM (Res-ConvLSTM) layer is stacked with convolution LSTM (ConvLSTM) layer to extract degradation representations from monitoring data. Then, predicated on the RUL following a normal distribution, an appropriate output layer is constructed to quantify the uncertainty of the forecast result. Finally, the effectiveness and superiority of RC-LSTM is verified using monitoring data from accelerated degradation tests of rolling element bearings.

Influence of scanning strategies on microstructure, residual stress, and corrosion behavior of 17-4 PH stainless steel fabricated by selective laser melting

“…The finer grains increase in austenite phase because of an increase in the number of grain boundaries per unit volume. 36,37 The misorientation angles for the hexagonal inside-out samples were more than 2°, and the average misorientation angle was 28.9953°, respectively. The wrought alloy showed a misorientation angle greater than 10°.…”

Innovative integration of multi-scale residual networks and MK-MMD for enhanced feature representation in fault diagnosis

“…However, in many cases, it is not feasible to retrain the diagnostic model due to the unavailability of data labels. Therefore, how to achieve unsupervised cross-domain fault diagnosis has become a practical problem [15][16][17]. This is particularly important in the field of rotating machinery.…”

Integrating Survival Analysis with Bayesian Statistics to Forecast the Remaining Useful Life of a Centrifugal Pump Conditional to Multiple Fault Types

“…Deep learning methods have been used in RUL prediction of machines because of their ability to automatically map the relationship between raw data and machine life [3][4][5][6][7][8]. These methods are capable of revealing the underlying correlations between machine phenomenon and its reason.…”