Thesis: ML-Based Model Order Reduction for Complete-Vehicle Structural Models
Göteborg, SE, 417 15
Transport is at the core of modern society. Imagine using your expertise to shape sustainable transport and infrastructure solutions for the future. If you seek to make a difference on a global scale, working with next-gen technologies and the sharpest collaborative teams, then we could be a perfect match.
Background
Complete finite element (FE) models of trucks are used throughout development to guide design work and verify structural integrity and performance. These models contain all necessary components, such as tires, suspension, frame, and cab, to simulate the dynamic behavior of the entire vehicle.
In recent years, there has been an increased interest in model order reduction (MOR) techniques. The essential idea is to take large, high-fidelity, models and reduced them to a simple form while preserving essential dynamics and accuracy. The purpose is usually to enable rapid simulations and create models that can be shared and easily deployed in various software applications. This is closely related to digital twins, as reduction techniques plays a significant role in enabling the creation and efficient operation of digital twins.
With recent advances in machine learning (ML), there are now algorithms that could potentially enable model order reduction for complete vehicle models. This has many interesting applications. Vehicle models run on dedicated FE-software and are typically computationally intensive. All the input/output signals produced by a vehicle model could serve as training data for a surrogate ML-model. This surrogate model can then be easily spread in the organization and utilized in other software applications.
Aim and Scope
This thesis work will investigate different strategies to perform ML-based model order reduction. Various neural network architectures, including neural operators, will be tested to determine their suitability for vehicle vibration data. Both purely data-driven and physics-informed methods will be explored.
This work will utilize a combination of complete FE models and simple linear models with a few degrees of freedom. These models will generate training data to various ML algorithms. A significant part of the work involves developing a methodology for physics-informed machine learning. Simplified vehicle models will serve as a starting point, as both training data and the underlying equations of motion are available.
Who are you?
We are seeking one or two master's program students (preferably two) in engineering, specializing in Applied Mechanics, Physics, Machine Learning, or equivalent. Knowledge of vehicle dynamics is advantageous. The thesis work will be conducted at Volvo GTT in Gothenburg, written in English, and will primarily utilize Python/Matlab and Nastran as the main tools.
Contact:
Andreas Josefsson (GTT, Vehicle analysis)
Mail: andreas.josefsson@volvo.com
Application:
Please apply no later than the 1st of November, please note that this position may be filled prior to the last application date.
We value your data privacy and therefore do not accept applications via mail.
Who we are and what we believe in
We are committed to shaping the future landscape of efficient, safe, and sustainable transport solutions. Fulfilling our mission creates countless career opportunities for talents across the group’s leading brands and entities.
Applying to this job offers you the opportunity to join Volvo Group. Every day, you will be working with some of the sharpest and most creative brains in our field to be able to leave our society in better shape for the next generation. We are passionate about what we do, and we thrive on teamwork. We are almost 100,000 people united around the world by a culture of care, inclusiveness, and empowerment.
Group Trucks Technology are seeking talents to help design sustainable transportation solutions for the future. As part of our team, you’ll help us by engineering exciting next-gen technologies and contribute to projects that determine new, sustainable solutions. Bring your love of developing systems, working collaboratively, and your advanced skills to a place where you can make an impact. Join our design shift that leaves society in good shape for the next generation.