Combining physics-based and machine learning methods to accelerate innovation in sustainable transportation and beyond: a control perspective

TL;DR

This paper reviews three battery modeling approaches—first principle, machine learning, and hybrid—highlighting their strengths, challenges, and applications in optimizing lithium-ion batteries for sustainable energy.

Contribution

It provides a comprehensive comparison of modeling methodologies for batteries, integrating control perspectives to accelerate sustainable transportation innovations.

Findings

Three modeling approaches are analyzed with case studies.

Hybrid models combine strengths of physics-based and machine learning methods.

Insights into challenges and future directions for battery modeling.

Abstract

Lithium-ion batteries are playing a key role in the sustainable energy transition. To fully exploit the potential of this technology, a variety of modeling, estimation, and prediction problems need to be addressed to enhance its design and optimize its utilization. Batteries are complex electrochemical systems whose behavior drastically changes as a function of aging, temperature, C-rate, and state of charge, posing unique modeling and control research questions. In this tutorial paper, we provide insights into three battery modeling methodologies, namely first principle, machine learning, and hybrid modeling. Each approach has its own strengths and weaknesses, and by means of three case studies we describe main characteristics and challenges of each of the three methods.