Postdoctoral fellowship in Artificial Intelligence for Battery Management in Electric Vehicles

Li-ion cells should operate in a relatively tight operating temperature (20oC to 45oC) to avoid safety, battery lifetime and capacity fading issues, hence requiring active heating/cooling in conditions other than mild ambient temperatures. A battery pack operating in cold winter conditions should use its own charge capacity for both heating and cooling. The current approach in the industry is to design the battery pack based on cooling requirements, i.e., minimum pack thermal insulation to allow heat exchange with the ambient for temperature decrease and instead using active heating by PTC (Positive Thermal Resistance) in cold conditions. Moreover, Battery Management System (BMS) algorithms also need to take into account the specific requirements and operating limitations of the cold ambient temperatures including enhanced SOC (State Of Charge) and SOH (State Of Health) models. A recent innovative and promising trend is to use data-driven and machine learning approaches to capture trends and aging mechanisms in batteries. The global objective of this project is to bring to market the technology components required for a high performance and advanced Li-ion battery pack for harsh winter conditions occurring in Canada and other Nordic countries in aerospace and ground applications.

We are currently looking for a postdoctoral associate interested in performing research on health estimation and lifetime prediction of lithium-ion batteries in electric vehicles using data-driven approaches. This project proposes a novel approach to leverage the capability of machine learning algorithms to capture the complex and non-linear physical mechanisms involved in Li-ion battery degradation (cell aging) and battery pack State of Health estimation. Accurate prediction of lifetime using early-cycle data would lead to lower cost battery pack production, use and optimization leading to more widespread use of electric vehicles. This initiative is part of an effort to use artificial intelligence to tackle climate change by developing a novel battery health estimation system adapted to Nordic conditions occurring in Canada. We are looking for enthusiastic candidates who have competence in a variety of fields of science and engineering.

We encourage applicants whose fields of interest gravitate towards the following:

- Machine learning (supervised/unsupervised learning, neural networks)

- Deep learning frameworks (Pytorch and/or TensorFlow)

- Parallel computing for large simulations

- Electric vehicles

The selected candidates will have the opportunity to work with researchers from different areas (mechanical engineering, electrical engineering) and will have the chance to work collaboratively with the industrial partners of the project. The selected candidates will also be able to attend international conferences to share their research work with the scientific community. The 3IT research environment and the city of Sherbrooke are bilingual (English and French) and the project is supported by Calogy Solutions, a young and fast-growing start-up company with breakthrough battery thermal management technologies for Li-ion batteries in electric transport.

The positions are available immediately. The initial appointment is for one year, with the possibility of an additional year contingent upon satisfactory progress and review after year 1 and eventual hire in the supporting company.