Aircraft engine remaining life prediction method with deep learning

Abstract

The prediction of the remaining life of aircraft engines plays an indispensable role in engine health management, and is of great significance to ensuring flight safety and improving maintenance efficiency. This paper proposes a life prediction model combining convolutional neural network and long short-term memory network in order to solve the problems of difficult model establishment and low calculation accuracy in aircraft engine RUL prediction. Different from the conventionally used single neural network, the proposed ensemble model can combine the advantages of both networks, using convolutional neural network to extract high-level spatial features in the data and long short-term memory network to extract temporal features. Validated on the N-CMAPSS public data set provided by NASA, and compared with a single convolutional neural network and long short-term memory network algorithm, the experimental results show that the accuracy of the prediction results of this method is better than that of a single model, which proves the proposed model. It can fully mine the information contained in the data.