I am an associate professor in the Department of Electrical and Computer Engineering at the University of Michigan-Dearborn, and I previously held an associate professorship at Kettering University, Michigan. Actively involved in professional communities such as IEEE and ECS, my research focuses on various aspects of battery technology, including design, manufacturing, and modeling for electric vehicles. I have received several awards for my work, including the Distinguished Research Team Award 2025 from UM-Dearborn, the Outstanding Teaching Award from Kettering University in 2020, the Outstanding New Research Award from Kettering University in 2016, and the 2014 Kettering Faculty Research Fellowship for my contributions to battery development for energy storage.
My research leverages machine learning and predictive modeling to improve battery health monitoring, capacity estimation, and fault detection by utilizing historical and real-time data for accurate state-of-health (SOH) and state-of-charge (SOC) predictions. Additionally, by integrating advanced optical sensing technologies within batteries, I collect high-resolution data on temperature, strain, and chemical changes, which are then analyzed to gain deeper insights into battery formation processes and internal interactions.
One of my prominent projects involves a Smart battery management system that uses optical sensing. This project aims to improve the manufacturing of lithium-ion batteries by using special optical sensors to monitor their internal processes in real-time. By embedding these sensors inside the batteries, we can observe how key components form and change, helping us make the batteries safer, more efficient, and longer-lasting. Ultimately, this could lead to faster and more cost-effective battery production, benefiting everything from electric cars to portable electronics.
The most significant scientific contribution I would like to make is to revolutionize battery technology by developing intelligent battery management systems (BMS) that seamlessly integrate advanced sensing technologies, machine learning, and digital twin models. This would enable real-time monitoring, precise prediction of battery performance, and optimization of manufacturing processes. By embedding optical sensors within batteries and employing data-driven models, I aim to enhance battery safety, efficiency, and longevity while reducing production costs. Ultimately, I aspire to create a framework that can be widely adopted across industries, particularly in electric vehicles and energy storage systems, leading to safer, more efficient, and environmentally sustainable energy solutions.
What excites me most about my data science and AI research is the ability to uncover hidden patterns and make intelligent predictions that directly impact the performance, safety, and sustainability of battery systems. The synergy between advanced sensing technologies, machine learning, and digital twin modeling offers unprecedented opportunities to gain real-time insights into battery health and performance.