Remaining Useful Life Prediction of Turbofan Engines Using CNN-LSTM-SAM Approach

Abstract

Accurate remaining useful life prediction of turbofan engines can effectively avoid serious air-disaster due to engine failure by mining its components degradation characteristics. However, the complexity of engine components degradation characteristics keeps increasing when the airplane flies in complex environments and multi-operating points (MOP) mode. In this work, a deep learning fusion algorithm based on self-attention mechanism (SAM) is proposed. This algorithm uses one-dimensional convolutional neural network (CNN) to extract the spatial features and long-short-term memory networks (LSTM) to fuse the measurement data of 21 components and extract the temporal feature from the measured data. Furthermore, with extracted features and SAM, the proposed algorithm provides weight redistribution and solves the information loss problem in LSTM. Experimental results validated the proposed model and it is found that the proposed prediction model can predict RUL of turbofan engines accurately and stably under MOP mode and the proposed model outperforms other latest existing approaches.