Remaining useful life prediction of rotating machinery based on KPCA-LSTM

The prediction of the remaining useful life (RUL) of rotating machinery is of great significance to the prediction and health management of industrial equipment. This paper addresses the problems of harrowing extraction of degradation information and poor prediction of the RUL of rotating machinery due to redundant data from multiple sensors. This paper proposes a kernel principal component analysis-long short term memory (KPCA-LSTM) based method for predicting the RUL of rotating machines. Firstly, the multi-dimensional degradation data of rotating machinery were analyzed, and the data that can characterize the degradation of rotating machinery were selected. Secondly, KPCA fusion and feature extraction were carried out on the degraded data, and the features of dimensionality reduction fusion were used as the input of the prediction model. Then, the health indicators of rotating machinery were constructed, and a KPCA-LSTM model was established to predict the remaining useful life of rotating machinery by dividing the different health states of rotating machinery by multi-order differentiation. Finally, the proposed method was tested by a mine reducer platform. Experimental results show that compared with LSTM and particle swarm optimization LSTM, the proposed method has better prediction effect than the other two models, and reduces the complexity of model training and the time of prediction. © 2023 Chinese Vibration Engineering Society. All rights reserved.