Physics-Based Model Informed Smooth Particle Filter for Remaining Useful Life Prediction of Lithium-Ion Battery

PHM uses lithium-ion batteries' RUL to ensure device dependability and safety. Two concerns plague RUL prediction algorithms. Few techniques consider processes while using empirical deterioration models. Second, a scarcity of particles and ambiguity in degradation model parameters limit PF stability. RUL forecasts wrong. This work predicted RUL using a reduced-ordered physics-based model of LiBs and three RUL-related degradation processes. AM electrode loss, lithium inventory loss are degradation mechanisms (LLI). The suggested system used SPM to forecast deterioration parameters from voltage and capacity data. Predicting capacity loss depending on deterioration. The SPM parameters are used to construct an SPF RUL predictor to overcome PF algorithm issues. Physics-based method properly predicted RUL. Small-framework prediction results. 2000 RUL is 2402. Traditional framework error is 0.8%; relative error is 0.089%. The framework's dependability and resilience were demonstrated using Gaussian white noise and dynamic discharge characteristics.