Development of AI-Based Data-Driven Aging Model for Li-Ion Batteries

Background

The rapid development of energy storage technologies, particularly Li-ion batteries, has driven innovation in electric vehicles, renewable energy systems, and other sustainable applications. Understanding and predicting battery aging is critical for enhancing performance, reliability, and longevity. Leveraging advanced AI techniques, this project aims to develop a robust, data-driven model to predict the aging of Li-ion batteries based on historical pack- and cell-level data. This master thesis is part of an ongoing project in collaboration with KTH-EGI , Northvolt  and Einar Mattsson . However, the student will be mostly working at KTH-EGI. 

Objective

The goal of this thesis is to create an AI-based aging model for Li-ion batteries using extensive historical data from the PV-ESS project  (pack level) and Northvolt (cell level). The model will provide insights into battery degradation, helping optimize design and operation strategies.

Research Area

• Artificial Intelligence & Machine Learning

• Energy Storage Systems

• Battery Technology and Aging Models

Description/Tasks

As part of this thesis, you will:

1. Data Collection and Preprocessing:

   • Gather historical data on Li-ion batteries from the PV-ESS project (pack level) and Northvolt (cell level).

   • Clean and preprocess the data to ensure it is suitable for AI-based modeling.

   • Employ data augmentation techniques to enhance data robustness.

2. Model Development:

   • Design an AI-based model architecture, potentially leveraging deep learning techniques.

   • Train the AI model on preprocessed Li-ion battery data.

3. Model Optimization and Validation:

   • Optimize the model to reduce computational complexity while maintaining or improving accuracy.

   • Validate the model using experimental data to ensure reliability.

4. Outcome:

   • Deliver a validated, data-driven aging model for Li-ion batteries that predicts degradation patterns accurately.

   • Final Thesis Report and a presentation for the relevant stakeholders

You are invited to contribute to a scientific publication and shape the future of energy research.

How to Apply

• Prepare a short (one page – 1 to max 3 paragraphs) motivation letter about why you with to take on this topic

• Attach your transcript of your MSc studies

• Attach a CV

• KTH students are prioritised, but not limited to

Send to: Linda Lundmark  and Farzin Golzar

Subject: [MSc Aging Li-Ion] FirstName - LastName

We look forward to receiving your application!

Supervisor and examiner