Main Research Activities
Machine learning (ML) is a tool that gives computers the ability to learn without being explicitly programmed. This PhD Thèse CIFRE is a collaboration between Ampere S.A.S and LRCS that concerns the development of Machine learning models and physics-based models to predict the lifetime of EV battery cells. By building machine learning algorithms with data from current electric vehicle (EV) fleet we can more accurately predict the battery life for EVs without deploying physical tests for each vehicle or battery chemistry in each series life. The models will account for major degradation mechanisms happening in the cells, serve as a proof of concept for implementation of a precise ML model for EVs and aid development of batteries for second life use. Ultimately, the goal of this PhD thesis is to propose protocols to optimize the performance degradation rate and lifetime of lithium ion batteries.Academic Training
Erasmus Mundus Masters in Materials for Energy Storage and Conversion (MESC+) (UPJV, 2022-2024)
Professional skills
EIS & Cyclic Voltammetry, Li-ion Cell assembly/Cycle Analyis, Multiphysics modelling of batteries, COMSOL Multiphysics, CAD, Data analysis, Machine learning techniques, Python programming.
Running Projects
CIFRE/ Ampere S.A.S
