Thesis Worker - Evaluation of Machine Learning Methods in VSIM

at  Volvo Cars AB

THESIS WORKER AT VOLVO CARS

Welcome to explore the world of Volvo Cars by writing your thesis with us! As a thesis worker in our organization you are supported by a supervisor who follows you during your project. All thesis projects are arranged in business critical areas and therefore you will be able to contribute to our company purpose – providing freedom to move in a safe, sustainable and personal way – from day one!

BACKGROUND AND PROBLEM DESCRIPTION:

Modelling and Simulation is a continually growing field and developers certainly need to adapt to it to make the best out of the simulations. With recent advances of Machine Learning (ML) in various disciplines, it is certainly an interesting thought to blend ML with Modelling and Simulation. However, to get the most value from Machine Learning, one must pair the best algorithms with the right tools and processes.
In the Vehicle Energy Efficiency team of Volvo Cars, driving innovation and adapting to futuristic technology is given paramount importance. We use VSim, which is a MATLAB/Simulink based application for energy flows in the complete vehicle, that is fully in-house developed. The scrum team developing VSim has the responsibility for the architecture, code base, interfaces, and model integration. The team collaborates closely with other virtual environments and model developing groups all around Volvo.
Currently, most vehicle component models are built on physical modelling which sometimes needs specific domain knowledge and time to create a robust model. Also, the complete vehicle model is a compilation of such components and corresponding subsystems which interact with each other through signal interfaces. This poses certain problems as some systems are shared between components and the interface in such cases might not be smooth. An alternative way of modelling is to make the systems modular which will further help in independent validation.
Model Training is one such method that is worth investigating. Model Training is a process in which training data is input to the Machine Learning Algorithm so that the algorithm learns from it.

Please refer the Job description for details