Dilated Convolutional Recurrent Deep Network with Transfer Learning for Remaining Useful Life Prediction

Abstract

Remaining Useful Life (RUL) prediction of industrial systems/components helps to reduce the risk of system failure as well as facilitates efficient and flexible maintenance strategies. However, due to cost and/or time limitations, it is a major challenge to collect sufficient lifetime data, especially the fault/failure data, from an industrial system for training an efficient model to predict the RUL. In addition, many of these systems work under dynamically changing operating conditions, which would require model retraining for adapting and generalizing to new conditions. In order to address these issues, we propose an architecture comprising a Dilated Convolutional Neural Network, which utilises non-causal dilations, combined with a Long Short-Term Memory Network: DCNN-LSTM model for RUL prediction. This model was validated on the publicly available NASA turbofan dataset and its performance was benchmarked against previously proposed models, showing the improvement by our proposed model. Next, DCNN-LSTM model was used in a transfer learning setting where both the issues of model retraining and limited availability of experimental data were addressed. The results showed a significant reduction in training time compared to the time required for retraining models from scratch, while achieving similar performance. Moreover, the proposed method also achieved at par performance by utilizing a much smaller amount of data.