A Hybrid Neuro-Fuzzy Model for Real-Time SOH Estimation of EV Batteries under Dynamic Operating Conditions
G Pandu Ranga Reddy, C Siva, Allanki Vinaykumar, Challa Sai Santhosh
Abstract
Accurate estimation of a battery’s State of Health (SOH) is critical for enhancing safety, extending battery lifespan, and maintaining optimal performance in electric vehicles (EVs) and energy storage systems (ESS). Traditional methods often fail to capture the nonlinear and uncertain nature of battery degradation, motivating the adoption of hybrid intelligent approaches that combine rule-based interpretability with data-driven adaptability. This paper proposes a hybrid SOH estimation framework integrating Fuzzy Logic and Artificial Neural Networks (ANN) to leverage expert knowledge alongside machine learning capabilities. The model utilizes multiple critical battery parameters including internal resistance, capacity fade, temperature, state of charge (SOC), charge/discharge rate (C-rate), and voltage drop under load to reflect real-world operating dynamics. Unlike conventional models, the proposed approach adopts an S-curve degradation profile to more realistically capture battery aging behavior. The Fuzzy Inference System (FIS) provides interpretable baseline estimation, while the ANN refines it through adaptive learning. Their combined output yields robust and accurate SOH estimation across diverse operating conditions. Simulation results validate the model’s effectiveness, demonstrating its potential application in intelligent battery management systems for EVs and smart grid environments.