Data-driven prognostic method based on Bayesian approaches for direct remaining useful life prediction

• Published in: Journal of intelligent manufacturing Vol. 27; no. 5; pp. 1037 - 1048
• Main Authors: Mosallam, A., Medjaher, K., Zerhouni, N.
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.10.2016; Springer Nature B.V; Springer Verlag (Germany)
• Subjects: Accumulation; Algorithms; Bayesian analysis; Business and Management; Computer simulation; Construction; Control; Decision making; Degradation; Engineering Sciences; Machine learning; Machines; Manufacturing; Mathematical models; Mechatronics; Methods; Micro and nanotechnologies; Microelectronics; Partial differential equations; Physics; Predictions; Preventive maintenance; Processes; Production; Production management; Repositories; Robotics; Sensors; Studies; Useful life; Discrete Bayes filter; Uncertainty representation; Data-driven PHM; Online estimation; Degradation modeling
• ISSN: 0956-5515; 1572-8145; 1572-8145
• DOI: 10.1007/s10845-014-0933-4

Reliability of prognostics and health management systems relies upon accurate understanding of critical components’ degradation process to predict the remaining useful life (RUL). Traditionally, degradation process is represented in the form of physical or expert models. Such models require extensive experimentation and verification that are not always feasible. Another approach that builds up knowledge about the system degradation over the time from component sensor data is known as data driven. Data driven models, however, require that sufficient historical data have been collected. In this paper, a two phases data driven method for RUL prediction is presented. In the offline phase, the proposed method builds on finding variables that contain information about the degradation behavior using unsupervised variable selection method. Different health indicators (HIs) are constructed from the selected variables, which represent the degradation as a function of time, and saved in the offline database as reference models. In the online phase, the method finds the most similar offline HI, to the online HI, using k-nearest neighbors classifier to use it as a RUL predictor. The method finally estimates the degradation state using discrete Bayesian filter. The method is verified using battery and turbofan engine degradation simulation data acquired from NASA data repository. The results show the effectiveness of the method in predicting the RUL for both applications.