Comparison of different models of future operating condition in Particle-Filter-based Prognostic Algorithms⁎This work has been supported by FONDECYT Chile Grant Nr. 1170044, ANID REDES 170031, and the Advanced Center for Electrical and Electronic Engineering, AC3E, Basal Project FB0008, ANID. The work of Heraldo Rozas was supported by ANID-PFCHA/Magister Nacional/2018-22180232. The work of Francisco Jaramillo was supported by ANID-PCHA/ Doctorado Nacional/2014-21140201. Issue 2 (2020)

• Record Type: Journal Article
• Authors: Rozas, Heraldo; Tamssaouet, Ferhat; Jaramillo, Francisco; Nguyen, Khanh T.P.; Medjaher, Kamal; Orchard, Marcos
• Is Part Of: IFAC-PapersOnLine. Volume 53:Issue 2(2020)
• Page Start: 10336
• Page End: 10341
• Publication Date: 2020
• Subjects: Failure prognostic -- Mission profile -- Markov Chain -- LSTM network -- Li-Ion battery; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2020.12.2770
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: In literature, a major part of the prognostic studies considers the mission profile as a static parameter when evaluating the system Remaining Useful Life (RUL). However, in practice, the way in which a system operates significantly impacts the future evolution of its degradation. Therefore, this paper aims at evaluating the impact associated with the utilization of three different methods to characterize future operating conditions within the implementation of probability-based prognostic algorithms, namely Long-short term memory (LSTM), Markov Chain and Constant (or time-invariant) usage. These three methods are compared together in terms of both prognostic accuracy and essential update times when investigating the Time-of-Discharge (ToD) of an electric bicycle Lithium-Ion (Li-Ion) battery.