Creating AI-Based ROMs for Battery Fast Charging Applications

While electrochemical models provide detailed insights into battery performance and aging, they are computationally intensive. These full-order high-fidelity models, while effective for detailed component design, are too slow and therefore impractical for control design, hardware-in-the-loop (HIL) testing, embedded deployment, and system-level analyses. Does this mean you have to start from scratch to create faster approximations of your high-fidelity model? This is where reduced-order modeling (ROM) comes to the rescue. ROM is a set of computational techniques that helps you reuse your high-fidelity models to create faster-running, lower-fidelity approximations.

In this session, you will learn how to import a high-fidelity electrochemical model from PyBaMM (a battery simulation package in Python^®) into Simulink^® using Python Importer and create an AI-based ROM for that component. Using the trained ROM, you’ll see how to integrate it into Simulink for fast charging control, HIL testing, or deployment to embedded systems for virtual sensor applications.

Highlights

• Importing a high-fidelity battery electrochemical model created in PyBaMM into Simulink using Python Importer
• Creating AI-based reduced order models using the Reduced Order Modeler App, including design of experiments, data generation, and AI model training
• Integrating trained ROMs into Simulink for control design and system-level simulation
• Generating optimized C code for HIL testing and deployment to embedded systems