This position is no longer available.

Internship Estimation of Li-ion batteries State-of-Safety (SoS) from Artificial Intelligence (AI) methods

Internship(4 months)
Le Bourget-du-Lac
Salary: Not specified
No remote work
Experience: < 6 months
Education: Bachelor's Degree

Powerup
Powerup

Interested in this job?

Questions and answers about the job

The position

Job description

The proposed internship will focus on studying innovative approaches based on Artificial Intelligence
(AI) methods to estimate the State-of-Safety of Li-ion batteries used in Energy Storage Systems (ESS)
and Electric Vehicles (EV).
Main work of this internship will consist of:

  • Analyze battery measurements in real operating conditions and during abuse tests in lab,
  • Manage and clean data (erroneous data, incomplete data, duplicates, etc…),
  • Test statistical / Machine Learning (ML) approaches to select the relevant features,
  • Test different ML approaches to diagnose SoS / ageing mechanisms, and more particularly indicators
    of cell imbalance and Li-plating events,
  • Define and use metrics to quantify the robustness of the SoS indicators developed (probability of
    preventing the events, probability of false alerts, etc.),
  • Perform SoS / ageing mechanisms forecasts according to different usage profiles.
    Moreover, an analyze could be done to see the impact of various ageing mechanisms on the safety
    behavior of Li-ion batteries.
    Finally, a coupling of the developed AI method(s) with the current semi-empirical approach used for
    SoS alerting could be explored.
    Few references:
    [1] Eliud Cabrera-Castillo, Florian Niedermeier, Andreas Jossen. Calculation of the state of safety (SOS)
    for lithium ion batteries. Journal of Power Sources 324, 2016, 509-520
    https://www.sciencedirect.com/science/article/pii/S0378775316306140
    [2] Fernando Almagro Yravedra and Zuyi Li. A complete machine learning approach for predicting
    lithium-ion cell combustion. The Electricity Journal 2021 34 106887
    https://www.sciencedirect.com/science/article/pii/S1040619020301792
    [3] Naha, A., Khandelwal, A., Agarwal, S. et al. Internal short circuit detection in Li-ion batteries using
    supervised machine learning. Sci Rep 10, 1301 (2020).
    https://www.nature.com/articles/s41598-020-58021-7#citeas

Preferred experience

• Data scientist (machine learning, statistical analyses, data preparation, databases,
Python/Matlab, …)
• Electrochemitry / Energy storage engineering


Recruitment process

Manager + team

Want to know more?