| KEYWORD |
A Digital Twin for EV Battery Monitoring
keywords BATTERY, BATTERY MANAGEMENT SYSTEM, CLOUD COMPUTING, DEEP LEARNING, DIGITAL TWIN, EDGE COMPUTING, NEURAL NETWORKS, NEURAL NETWORKS, EMBEDDED SYSTEMS, C++ PROGRAMMING
Reference persons MASSIMO PONCINO, SARA VINCO
Research Groups DAUIN - GR-06 - ELECTRONIC DESIGN AUTOMATION - EDA
Thesis type RESEARCH, RESEARCH THESIS WITH A COMPANY
Description The current growth in the Electric Vehicle (EV) market, with 10 million EV sold worldwide in 2022. Sales are expected to grow by another 35% in 2023, making it clear that advancement in battery technology can not be underestimated, as battery-based propulsion still faces many challenges: low energy and power densities compared to liquid fuels, long charging times, and quick degradation over time.
To address these challenges, Battery Management System (BMS) are commonly employed in EV to ensure safe battery operation and optimize efficiency. Furthermore, digital technologies, such as the battery Digital Twin (DT), have become increasingly utilized to support various stages of the battery’s lifespan and enhance BMS functionality. A battery BMS is a digital representation that emulates battery dynamics, enabling smart management, what-if analysis, predictive maintenance, and more.
Many open activities fall in this scenario, and may become the focus of a thesis:
• Battery modeling with Deep Learning and Neural Network techniques, including Physically Informed techniques
• Exploration of the deployment of battery models on edge devices
• Design of edge-cloud architecture to allow the execution of battery models on-board and around the EV
See also battery dt thesis proposal.pdf
Required skills Programming
Notes Possible collaboration with an innovative Piedmontese company
Deadline 05/12/2024
PROPONI LA TUA CANDIDATURA