ANN-BASED BATTERY STATE OF HEALTH ESTIMATION FOR EV ANDGRID APPLICATIONS

Abstract

The increasing integration of renewable energy sources and electric
vehicles (EVs) has introduced significant challenges in maintaining grid stability and ensuring reliable energy storage. Lithium-ion batteries play a crucial role in these systems; however, their performance degrades over time due to electrochemical aging mechanisms [1].
The State of Health (SoH) is a key indicator used to evaluate battery degradation and remaining useful life [2]. This paper proposes an Artificial Neural Network (ANN)- based approach for estimating SoH using measurable parameters such as voltage, current, temperature, and cycle number. The model captures nonlinear relationships between battery variables and degradation behavior.
Experimental results demonstrate that the ANN-based method provides accurate and robust SoH estimation even when historical data is incomplete. The study also highlights the importance of second-life batteries in modern smart grid applications [3].