Remaining Useful Life Prediction Based on Normalizing Flow Embedded Sequence-to-Sequence Learning

• Published in: IEEE transactions on reliability Vol. 70; no. 4; pp. 1342 - 1354
• Main Authors: Yang, Haosen, Ding, Keqin, Qiu, Robert C., Mi, Tiebin
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.12.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation models; Clustering; Coders; Computational modeling; Deep learning; Feature extraction; Life prediction; Machine learning; Neural networks; Normalizing flow; Prognostics and health management; prognostics and health management (PHM); Reliability analysis; remaining useful life (RUL); sequence-to-sequence (seq2seq); Teaching methods; Useful life; Vibration measurement; Vibrations
• ISSN: 0018-9529; 1558-1721
• DOI: 10.1109/TR.2020.3010970

Remaining useful life (RUL) prediction is of fundamental importance in reliability analysis and health diagnosis of complex industrial systems. Aiming at improving the prediction accuracy, this article proposes a normalizing flow embedded sequence-to-sequence (seq2seq) learning method to predict the RUL of an asset or a system. This method introduces a block of normalizing flow into the middle area of the familiar encoder-decoder structure of the seq2seq model. This normalizing flow enjoys the remarkable representation ability for the nonlinearity between input sequential data and outputs and enables the original seq2seq model to be more suitable for vibration signals of engines. The encoder and the decoder, which fall before and after the normalizing flow, are both built by gated recurrent units. Besides, a one-hot coding of clustering is concatenated with measurement data to indicate the frequently shifting vibration state, and a sensor selection method is designed to drop some weakly related and ineffective variables. Our method is tested and further analyzed by 2008 IEEE PHM challenge data (PHM08), of which many practical preprocessing methods are conducted. Numerous tests verify that our method outperforms other related deep learning methods for RUL estimation.