Thesis Worker - Thermal Estimation Model of Inverter Power Modules using Neural Network i Göteborg

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
Electric vehicles are propelled by an electric machine which is being controlled by an inverter. The inverter has a DC-link capacitor, PowerModule, and AC/DC rails among other components. When current passes through these sub-components, due to resistances and power losses, heat is generated causing temperature to rise, which can damage the device if not monitored accurately and controlled.

Scope
Deliver Electro-Thermal Neural Network Model in Matlb-Simulink to live estimate and predict Inverter PowerModules’ temperatures, in different driving scenarios and for different operating modes  (Normal operation, Charging, Active Discharge, etc..). 

Large data sets shall be collected from our Inverter lab with varying electrical inputs, parameters, and output target temperatures, across these scenarios, to be used to train the model.

The aim is to run the developed trained machine learning model to estimate PowerModule temperature live in the vehicle, for the different electrical inputs and parameters that affects the temperature.

Optimization in the method/algorithm/computations/paramaters to be made to adapt running the model on embedded system CPU target. 

This work is combined knowledge domains of Electrical, PowerElectronics, Thermal, Modern Control Theory, and Machine Learning.
•    Make Thermal Observer Simulink Model for the Power Modules Temperature using Neural Networks.
•    Tune and train the model using the large data sets collected from Inverter Lab to estimate the  Temperature as output based on the varying inputs/parameters affecting it. 
•    Possibility to run same methodology developed, on electric machine rotor and stator temperatures.
•    Final report which describes findings and the selected model and potential issues or limitations of the method.

Do you fit the profile
We are looking for you within Master of Science program with Electrical, Power Electronics, Data Science & AI, Complex Adaptive System, Controls Theory, or Signals & Systems. You should be interested in solving challenges individually and in collaboration with positive mindset. 

Duration
•    20 weeks / 30 points
•    Start date February or earlier (can be discussed)
•    Number of student: 2 (we prefer that you apply as a couple)

How to learn more and apply
Selection will be ongoing during the application period, so do not hesitate to send in your application. Attach your Cv and personal letter stating your interests within the given area and your thoughts and credentials.

Apply as soon as possible but no later than 18th of October. Please note that applications via email will not be accepted.
For questions about the thesis work please contact, Mohamed.hifnawy@volvocars.com
 

We are Volvo Cars

Volvo Cars is a company on a mission to bring traditional car manufacturing into a connected, sustainable and smart future. Since 1927, we've been known for our commitment to safety and for creating innovative cars that make life less complicated. In 2010, we decided to radically redefine our business, resulting in a totally new generation of cars and technology, as well as steady growth and record sales - and we're only getting started. By 2025, we aim to have yearly sales of 1.2 million cars, 50% of which will be electric vehicles and sold directly to customers through digital channels. We also intend to strengthen our position as a modern, progressive employer committed to diversity and gender and racial equality. We believe in the power of people. Join us and be part of Volvo Cars' transformation.