2021/02/18 by Murilo Osorio Camargos, Camargos, Murilo Osorio, Iury Bessa +9
Engineering · #Advanced Algorithms and Applications #Advanced Battery Technologies Research #FOS: Electrical engineering #FOS: Mathematics #Fault Detection and Control Systems #Optimization and Control (math.OC) #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2102.09521
openalex publication_date 2021/02/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
This paper addresses the use of data-driven evolving techniques applied to\nfault prognostics. In such problems, accurate predictions of multiple steps\nahead are essential for the Remaining Useful Life (RUL) estimation of a given\nasset. The fault prognostics' solutions must be able to model the typical\nnonlinear behavior of the degradation processes of these assets, and be\nadaptable to each unit's particularities. In this context, the Evolving Fuzzy\nSystems (EFSs) are models capable of representing such behaviors, in addition\nof being able to deal with non-stationary behavior, also present in these\nproblems. Moreover, a methodology to recursively track the model's estimation\nerror is presented as a way to quantify uncertainties that are propagated in\nthe long-term predictions. The well-established NASA's Li-ion batteries data\nset is used to evaluate the models. The experiments indicate that generic EFSs\ncan take advantage of both historical and stream data to estimate the RUL and\nits uncertainty.\n