A recurrent neural network approach for remaining useful life prediction utilizing a novel trend features construction method. (November 2019)

• Record Type: Journal Article
• Authors: Zhao, Sen; Zhang, Yong; Wang, Shang; Zhou, Beitong; Cheng, Cheng
• Is Part Of: Measurement. Volume 146(2019)
• Page Start: 279
• Page End: 288
• Publication Date: 2019-11
• Subjects: Prognostics and health management -- Remaining useful life prediction -- Complete ensemble empirical mode decomposition -- Conditional neural processes -- Recurrent neural network -- Long short-term memory units; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2019.06.004
• Languages: English
• ISSNs: 0263-2241

Abstract

Abstract: Data-driven methods for remaining useful life (RUL) prediction normally learn features from a fixed window size of a priori of degradation, which may lead to less accurate prediction results on different datasets because of the variance of local features. This paper proposes a method for RUL prediction which depends on a trend feature representing the overall time sequence of degradation. Complete ensemble empirical mode decomposition, followed by a reconstruction procedure, is created to build the trend features. The probability distribution of sensors' measurement learned by conditional neural processes is used to evaluate the trend features. With the best trend feature, a data-driven model using long short-term memory is developed to predict the RUL. To prove the effectiveness of the proposed method, experiments on a benchmark C-MAPSS dataset are carried out and compared with other state-of-the-art methods. Comparison results show that the proposed method achieves the smallest root mean square values in prediction of all RUL.