Remaining Useful Life Prediction of Aero-Engine Based on PCA-LSTM

Abstract

Remaining useful life (RUL) Prediction is one of the key technologies to realize engine health management. Aiming at the problems of high dimension of aeroengine sensor monitoring data and complex modeling of performance degradation, a prediction method of aeroengine remaining useful life based on PCA-LSTM is proposed. Firstly, Principal component analysis (PCA) is used to reduce the dimension of sensor data, and the correlation between engine multidimensional sensor data is extracted to improve the prediction performance. Then, the extracted time sequence data is predicted by Long and Short-Term Memory neural network (LSTM), and the remaining useful life prediction model is established. Finally, the NASA's C-MAPSS aero-engine data set is selected for verification, and the results show that the remaining useful life prediction method based on PCA-LSTM has high accuracy.