Smart Battery Management System by Integrating Physics-basedModeling and AI-based Methodology

The electrification of the automobile industry is one of the main paths toward global decarbonization and a promising solution to address oil supply shortages and environmental pollution. However, the EV industry still faces critical challenges such as long charging time, low battery lifetime, and safety considerations, which restrict widespread adoption of EVs. In this project, we aim to develop a hybrid modeling framework to tackle these challenges. The hybrid framework will be based on integrating reduced-order multi-physics models and AI-based models to consider all aspects of the complex dynamic of batteries. The battery state estimation model will be able to accurately predict the state of charge, state of health, and state of power of batteries in a wide range of operating conditions. Moreover, the optimal charging pattern will be obtained by implementing the early prediction algorithm and machine learning methodology, to find a tradeoff off charging time and battery lifetime.

Faculty Supervisor:

Zhongwei Chen

Student:

Hamed Fathiannasab

Partner:

Zerone lab inc

Discipline:

Engineering - chemical / biological

Sector:

Administrative and support, waste management and remediation services

University:

University of Waterloo