AI-Based Digital Twin - Anomaly Detection and Diagnostics for HV Battery Behavior and Performance

Thomas Alexander Kristan (AVL List/Graz University of Technology)･Milan Živadinović･Christian Rupert Rehrl (AVL List)･Roman Kern (Graz University of Technology)･Alwin Tuschkan (AVL List)

In the rapidly evolving automotive industry, HV batteries play a pivotal role, demanding a focused effort on safety and failure prevention. Conventional methods for health monitoring fall short due to their supervised nature, relying on historical fault data. This paper proposes an innovative approach involving the implementation of an AI-based digital twin leveraging a graph neural network for unsupervised anomaly detection in fleet data. Furthermore, our approach incorporates domain knowledge to proactively prevent HV battery failure. The results demonstrate state-of-the-art performance for enhancing the reliability and safety of EV power systems.

Charge Planning Tool for Heavy-Duty Electric Vehicle Fleets

Alenka Beckers･Róbinson Medina･Steven Wilkins (TNO/Powertrains)

Driven by zero-emission targets, fleet owners in the Heavy-Duty transport sector are transitioning towards Electric Vehicles (EVs). However, existing Fleet Management Software (FMS), designed for conventional vehicles, needs to incorporate the planning of charging moments of EVs. We propose a Charge Planning Tool (CPT) that can be integrated with existing FMS. The CPT optimizes a charging schedule for a non-homogeneous EV fleet with multiple charging opportunities, less chargers than vehicles, while considering compatibility between chargers and vehicles, and grid related constraints. Additionally, the charging schedule minimizes battery degradation, peak power demand, and electricity costs of the entire fleet.

Next Generation Battery Packs Ready for the Battery Passport

Erik Hoedemaekers･Sjoerd Rongen･Steven Wilkins (TNO)

This paper presents a novel methodology for a model-based battery prototype design process, incorporating design innovations and Battery Passport requirements derived from the new EU Battery Regulation. The design process includes the use of a modular simulation tool to justify choices by means of simulation analysis. A case study is presented, linking the design of a battery pack with the implementation of a battery passport and the therefore required BMS algorithms. A battery passport implementation based on International Data Spaces will be presented and discussed in this paper, and results from a demonstration are included.