High-performance remaining useful life prediction for aeroengine based on combining health states and trajectory similarity

Aeroengine is a kind of highly complex and precise thermal machinery with various data features. Therefore, the selections of appropriate key features and effective utilization of data are the challenges and focal points in the prediction of remaining useful life (RUL) for the aeroengine. This paper proposes a high-precision method for predicting the RUL of aeroengines based on health states and trajectory similarity. Firstly, with a comprehensive understanding of the domain knowledge, the K-means clustering method is employed to categorize different health states of aeroengines and construct the aeroengine life database accordingly. This effectively reduces the false prediction caused by overlapping curves in the life model library. Secondly, by introducing a segmented similarity measurement method, the trajectory similarity of the Health Index (HI) curve between test data and life library can be better matched. Furthermore, incorporating a multiple weighted combination of L bestmatched HI curves further improves the prediction accuracy. Finally, the validity of this method is verified by the simulation data set of turbofan aeroengines provided by National Aeronautics and Space Administration (NASA). Compared with other two similar algorithms, the accuracy increases by 4% and 6% respectively, in which the penalty Score of the proposed method decreases 20.82% and 69.17% respectively, and the lowest root mean square error (RMSE) is obtained.