A spatiotemporal feature learning-based RUL estimation method for predictive maintenance

Abstract

Studies that apply deep learning (DL) methods to maintenance support systems have achieved many successes because degradation patterns and remaining useful life (RUL) of critical equipment can be described and predicted by DL techniques. However, mining spatial and temporal dependencies from multivariate sensor signals and fusing spatiotemporal features sufficiently are challenging tasks. In this proposal, a novel signal-level DL framework containing three layers called STRUL is proposed for end-to-end RUL estimation. The first data segmentation layer is designed based on the sliding window manner which makes STRUL work directly on raw signals. Then, in the information extraction layer, two feature extractors based on the convolutional neural network are used synchronously to learn spatial and temporal features from each time series. The last information aggregation layer is designed to fuse features so that the holistic spatiotemporal features can be learned and further contribute to RUL prediction. The proposed STRUL model achieves better comprehensive performance on RUL estimation tasks than existing models, which has been verified by two case studies.