| KEYWORD |
Data driven models for battery second life
keywords AUTOMOTIVE, BATTERY, GREEN ENERGY, HARVESTING, CIRCULAR ECONOMY, MACHINE LEARNING, SUSTAINABILITY
Reference persons MASSIMO PONCINO, SARA VINCO
External reference persons Alessandro Ferraris, BeonD
Research Groups DAUIN - GR-06 - ELECTRONIC DESIGN AUTOMATION - EDA
Thesis type RESEARCH AND DEVELOPMENT, RESEARCH THESIS WITH A COMPANY
Description When batteries reach the end of their ‘automotive’ life cycle, they still have a residual capacity of about 70-80% and can be applied for different usage after their initial lifecycle has come to an end. As part of the solutions for the energy transition, storage and batteries are tools to enable sustainability and, at the same time, they themselves must be fully sustainable. Extending the life of batteries means reducing their carbon footprint and increasing the amount of renewable energy on the grid.
To make the second life of a battery appealing and profitable, it is crucial to estimate the remaining lifetime (i.e., state of health, SOH) of a battery with a solution that is fast and requires few measurements. It is thus necessary to:
- build data driven models that can estimate the residual lifetime of a second life battery from few experimental measurements
- build a battery passport, i.e., a document that stores relevant battery data throughout the entire battery lifecycle, including detailed information about a battery's production, testing and recycling.
This thesis deals with these topics, and will require to work in conjunction with BeonD, an innovative company based in Grugliasco. Founded in 2013 as a spin-off of Politecnico di Torino, BeonD is listed by il Sole 24ore as "Leader della crescita 2024".
Reading list:
- https://corporate.enelx.com/en/our-commitment/sustainability/ev-second-life-battery
- https://www.mdpi.com/2313-0105/10/5/153
- https://www.beond.net/
Required skills Programming
Basis of machine learning and artificial intelligence
Deadline 17/05/2025
PROPONI LA TUA CANDIDATURA