Battery Degradation Prediction for SOC & SOH Estimation of Lithium-Ion Battery in Electric Vehicle
Mr. Mayur S. Sonawane
Department of Electrical Engineering
K.K.Wagh Polytechnic,
Nashik, India
mayursonawane1057@gmail.com
Ms. Sakshi R. Khute
Department of Electrical Engineering
K.K.Wagh Polytechnic,
Nashik, India
khutek335@gmail.com
Mr. Srujal C. Sonawane
Department of Electrical Engineering
K.K.Wagh Polytechnic,
Nashik, India
srujals393@gmail.com
Ms. Sakshi R. Bodke
Department of Electrical Engineering
K.K.Wagh Polytechnic,
Nashik, India
sakshibodke3010@gmail.com
Ms. Harshada P. Wagh
Department of Electrical Engineering
K.K.Wagh Polytechnic,
Nashik, India
harshadawagh5107@gmail.com
Ms. Neha P. Pethkar
Department of Electrical Engineering
K.K.Wagh Polytechnic,
Nashik, India
nehapethakar12@gmail.com
Mr. Dhananjay K. Lakhe
Department of Electrical Engineering
K.K.Wagh Polytechnic,
Nashik, India
dklakhe@kkwagh.edu.in
Abstract- Lithium-ion (Li-ion) batteries are essential in today's electric vehicle (EV) production because they offer high energy storage and are lightweight. However, their chemical nature makes them unstable, which creates challenges for Battery Management Systems (BMS), especially when it comes to accurately measuring how much charge is left (State of Charge, or SOC) and how well the battery is functioning (State of Health, or SOH). As batteries age, caused by things like temperature changes, fast charging, and different levels of discharge, their ability to hold charge and deliver power decreases, making it harder to predict how long they will last. This paper reviews various methods used to estimate SOC and SOH, pointing out their strengths and weaknesses along with the errors they produce. We also suggest a smart monitoring system that uses data analysis and machine learning to predict how batteries will degrade and how much life they have left (Remaining Useful Life, or RUL). By combining real-world driving data with lab tests on battery aging, our model creates detailed degradation profiles. This research improves the safety, dependability, and affordability of electric vehicles, and offers a framework that can be used in both electric car systems and energy storage for renewable sources.
Keywords: Lithium-ion Battery, State of Charge (SOC), State of Health (SOH), Remaining Useful Life (RUL), Battery Management System (BMS), Machine Learning.
