In the controlled world of simulation and lab testing, battery algorithms often perform flawlessly. Yet, when deployed in real vehicles, theory quickly meets the unpredictable realities of temperature variation, load dynamics, and user behavior. This talk explores how battery management algorithms must adapt to use-case environment to deliver reliable performance and longevity. Through real-world examples, we will highlight how theoretical models are modified, fused with field data, and validated to ensure accurate and stable performance across applications. This session bridges the gap between elegant equations and messy reality, proving that when theory meets the road, innovation accelerates and batteries become truly intelligent companions to technology.

In this session, you will learn more about:

• How real-world factors like temperature, load, and user behavior influence battery algorithm performance
• How theoretical models are adapted and tuned for real-world deployment
• How field data is integrated to refine, validate, and enhance battery reliability and longevity
• Practical examples of bridging the gap between simulation precision and on-road performance

• What’s one “theoretical assumption” in battery modeling that fails most dramatically in real-world use?
• Do you rely more on physics-based or data-driven models in your workflow, and why?
• How often should SOC/SOH estimators be recalibrated during the product life cycle?
• What would an ideal collaboration between academia and industry look like to accelerate algorithm development?
• What are the biggest challenges in aligning telematics data with cell-level battery measurements?