Description of the thesis topic

The thesis aims to develop a comprehensive and robust solution for battery diagnostics and assessment, drawing on several complementary approaches. It will begin with the creation of a clean, structured, and rich data platform, obtained through rigorous preparation and labeling. This database will reflect the variability of electrical topologies (AC, DC, three-phase) and will integrate both standard and atypical wear cases.

On this basis, high-performance artificial intelligence models will be developed. By combining neural networks, ensemble algorithms, and other advanced architectures, the objective will be to accurately predict the state of health (SoH) of batteries in the short, medium, and long term, including under extreme or poorly documented conditions.

In parallel, a reliable state of charge (SoC) estimation strategy will be implemented. It will rely in particular on the implementation of Kalman filters and AI techniques capable of operating in real time, even in dynamic or unstable conditions.

Finally, all of these developments will be validated in an industrial context through concrete demonstrators. Whether through bench tests or on-site trials, these proofs of concept will demonstrate the benefits in terms of safety, operational efficiency, and battery life extension.

Work Context

The work will be carried out within the Laboratory of Reactivity and Solid Chemistry (LRCS) as part of the FTJ Basecamp 10kWh Project.

The position is located in a sector under the protection of scientific and technical potential (PPST), and therefore requires, in accordance with the regulations, that your arrival is authorized by the competent authority of the MESR.

Constraints and risks

.

Additional Information

.