Thesis Worker - Evaluation of Machine Learning Methods in VSIM

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.

Objectives and Methods:
For product development in the early phases, simplifications (heuristic or reduced order models) are critical for a rapid & robust decision-making. In this study we aim to come with a decision support methodology based on machine learning (ML). 
Primary objective is to investigate if the model development time can be reduced by using trained ML models in VSim and to investigate if the simulation time and accuracy of the results can be improved. 
•    A thorough literature survey of Model Training methods and related methods.
•    Identify the components/systems for investigation
•    Develop Trained Machine Learning models for the components selected with the help of training dataset
•    Conduct a feasibility study to implement Model Training in VSim architecture

Deliverables:
•    Present the comparison study of VSim models vs ML model with respect to simulation time and difference in results
•    Master Thesis report and presentation
•    Define scope for further work
 

Who are we?

Everything we do starts with people. Our purpose is to provide freedom to move, in a personal, sustainable and safe way. We are committed to simplifying our customers’ lives by offering better technology solutions that improve their impact on the world and bringing the most advanced mobility innovations to protect them, their loved ones and the people around them.

Volvo Cars’ continued success is the result of a collaborative, diverse, and inclusive working environment. The people of Volvo Cars are committed to making a difference in our world. Today, we are one of the most well-known and respected car brands, with over 40,000 employees across the globe. We believe in bringing out the best in each other and harnessing the true power of people. At Volvo Cars your career is designed around your talents and aspirations so you can reach your full potential. Join us on a journey of a lifetime as we create safety, autonomous driving and electrification technologies of tomorrow