FURI | Spring 2024, Needs Review

Lithium-ion Battery Degradation Machine Learning Model

Data icon, disabled. Four grey bars arranged like a vertical bar chart.

The objective of this study is to use impedance data to develop a machine-learning model capable of accurately predicting the state of health of lithium-ion batteries. By analyzing the relationship between impedance characteristics and battery health, the model demonstrates a new, noninvasive approach to testing and extending battery life and enhancing reliability. The findings highlight the potential for improved efficiency of battery usage. Future work should focus on continuing to improve the accuracy through increased data collection and possibly applying different machine learning algorithms.

Student researcher

Nithin Jakrebet

Computer science

Hometown: Phoenix, Arizona, United States

Graduation date: Spring 2025