Lithium-ion battery diagnostics and prognostics enhanced with Dempster-Shafer decision fusion

Prognostics is the discipline of predicting the remaining useful life of a component or system in order to optimize the maintenance planning or the mission execution. Prognostics-enabled systems likely reduce the overall life-cycle cost and increase the reliability. In the Bayesian estimation framework, the widely used techniques are the traditional Kalman filter, along with its non-linear extensions, and the particle filter. Each technique has different advantages. This paper investigates the fusion of prognostic results from different techniques in order to achieve a more trustworthy remaining useful life (RUL) prediction, as measured by a reduction in uncertainty. Models for extended Kalman filter (EKF) and particle filter (PF) are developed from the feature data. The results from EKF and PF are then fused using an application of Dempster-Shafer theory (DST). Separate models are utilized for EKF and PF in order to introduce multi model prognostics and to optimize the performance of each technique for both diagnosis and RUL prediction. Prognostics is triggered when degradation is detected by diagnosis. DST is then applied to the prognostic results from EKF and PF. The result of DST is a density function whose performance can be compared with that of EKF and PF. DST allows for the fusion of multiple sensors and state estimates. The proposed method is verified with the prognosis of a set of lithium-ion batteries. (c) 2021 Elsevier B.V. All rights reserved.

Automated summary

Prognostics is the discipline of predicting the remaining useful life of a component or system in order to optimize maintenance planning or mission execution. By fusing prognostic results from different techniques, this paper aims to achieve a more trustworthy RUL prediction with reduced uncertainty. The widely used techniques in Bayesian estimation include traditional Kalman filter and particle filter, each with its own advantages.