Master Thesis Student - Battery Lifetime Analytics

30 hp –Transfer learning for battery lifetime predictions 

Thesis work is an excellent way to get closer to TRATON Group and build relationships for the future. Many of today's employees at TRATON began their career with a degree project. 

TRATON is a group of strong brands, including Scania, MAN and International, with a shared mission: to create the future of sustainable transport solutions. Development of heavy-duty battery electric vehicles (BEVs) constitute a core part of this mission. Batteries make up a large fraction of the cost of BEVs, and their capacity and performance (state of health) degrade over time in a usage-dependent way. The residual value of a used battery follows the same trend. Models that estimate, predict, and explain the degradation of vehicle batteries throughout their life cycle are therefore an important success factor for TRATON, both to help our customers get the most out of their electric vehicles and to improve future product designs. Battery degradation is a complex process that is difficult to model from first principles and expensive to characterise experimentally. Practical aging models therefore rely on data-driven approaches that combine domain expertise with data from multiple sources, and the ability to model across battery generations is potentially valuable. 

Objective 

This thesis project aims to explore methods to build lifetime models that combine data from vehicles in operation with some different data source, such as lab tests or simulations, in order to facilitate continuous and cumulative improvements. We favour Bayesian methods to enable probabilistic forecasts using complex non-linear models. 

Job description 

The student will implement battery aging models that combines models or data from lab tests with operational data, and explore the ability to refine predictions and learnings as operational accumulates over time. The work will be conducted on site at TRATON R&D in Södertälje. 

Education/program/focus 

We are looking for a student in applied mathematics or engineering with knowledge of Bayesian statistics, strong skills in numerical programming and data analysis using R or python, and experience with analytical calculations. Knowledge of SQL, time series models and probabilistic programming in Stan or a similar language is valuable, as is a scientific background from undergraduate courses in engineering or physical sciences. Knowledge of electrochemistry and battery technology is helpful but not necessary. 

Number of students: one 

Start date for the thesis work: January 2027 (flexible).  

Estimated time required: one semester. 

Contact persons and supervisors 
Martin Lindén, PhD, development engineer, Battery Lifetime Analytics team, martin.linden@scania.com 
Daniel Carlsson, head of unit Lifetime, Regulations and Safety, daniel_x.carlsson@scania.com 

Application: 
Your application must include a CV, personal letter and transcript of grades and be submitted via our website. Make sure to high-light relevant skills and course work, including ongoing courses. A background check might be conducted for this position. We are conducting interviews continuously and may close the recruitment earlier than the date specified.