Turbofan Engine's RUL Prediction Based on the CSI-EMD and Double-Channel Multilayer Feature Fusion Network

In this article, a hybrid network framework based on the empirical-mode decomposition improved by cubic spline interpolation (CSI-EMD) and double-channel multilayer feature fusion network (DCM-FFN) has been proposed to improve the accuracy of remaining useful life (RUL) prediction. The CSI-EMD is an empirical-mode decomposition (EMD) method that we have improved, which decomposes the multisensor time series into a bunch of intrinsic-mode functions, and then the DCM-FFN predicts the concrete states and summarizes the final RUL prediction value. Our proposed CSI-EMD method successfully alleviates the endpoint effect problem in the traditional EMD methods. In order to improve the ability of neural network to extract degraded signals, a method combining multiscale convolutional neural networks and echo state network is adopted in the framework. The proposed approach is evaluated by aircraft turbine engine data from NASA (FD001-FD004). Compared with the existing state-of-the-art methods, the root-mean-square error and score of the proposed method decreased by 15.33% and 54.86%, respectively. Therefore, results and comparisons show that the prediction performance of the proposed method has been improved greatly.