Software / AI

Creating a Digital Twin for Cell to Pack Modelling 2 of 2 Virtual Cell Design: Accelerate design and chemistry exploration without physical prototypes. Optimized Pack Configuration: Tailor battery assembly to specific applications and use cases. Fleet-Wide Intelligence: Real-time monitoring of health and performance to get insight into fleet health and safety. IMPROVING EFFICIENCY, REDUCING COSTS, AND ENHANCING THE RELIABILITY OF BATTERY SYSTEMS

Digital Twin Data Pipeline The Vehicle Path: The IoT Gateway filters and decodes CAN bus metrics (voltage, temp, SOC) for cloud transmission The Cloud Path: The IoT Hub routes data into Hot (real-time), Warm (analytics), or Cold (archival) paths based on urgency Battery Model The battery modeling for the digital twin focuses on high-speed, real-time simulation of the electrical, thermal, and aging behavior of the commercial battery pack. It can be a physics-based, empirical, and data-driven machine learning model Source: 1EUR_LEX, 2MHP

AI Actionable Insights Digital twin application leverages AI/ML primarily for anomaly detection, comparing real-time voltage and current data against expected behavior to identify unusual observations for expert review

Regulatory Compliance and Standards 2025 EU Battery Passport Readiness 1: Digital twin will be the data backbone for battery passport regulatory compliance by 2027 New standard for digital twins of vehicle batteries 2 DIN SAE SPEC 91487202508 defines terms and characteristics for the use of digital twins for electric vehicle batteries. Users benefit from common standards and a uniform basis

Extracted from the PDF; charts and images may read imperfectly.