Thesis - OBM Pinpointing with Reinforcement Learning

Job-ID: T-TD Powertrain Systems -22502

Thesis - OBM Pinpointing with Reinforcement Learning

______

Students   —  Thesis 

Berlin

This challenge awaits you:

The innovations of the EU7 On-Board Monitoring (OBM) system aim to detect high emitters among combustion vehicles that are not detected by the individual fault analysis of the On-Board Diagnostic (OBD) system. This means that there may be combinations of component ageing (e.g. sensors, actuators) that can lead to an increase in emissions. The increase in NOx emissions is measured by the NOx sensor in both gasoline and diesel engines. The problem with this is that although the sensor recognizes the increase in emissions, there may be no indication from the OBD system as to which components are defective/aged. Targeted troubleshooting is therefore not possible in the workshop.

The aim of this work is to recognize these combined deviations with the help of machine learning, so that if an increase in emissions is detected in the workshop, it can be assigned which components need to be replaced. Simply put, a neural network modeling NOx emissions should be corrected/adjusted at its inputs so that the model reflects the sensor value as accurately as possible. To achieve this, the resulting software module must be compact enough to be implemented in existing ECUs.

Your Tasks:

• You will familiarize yourself with the basics of combustion and exhaust gas theory of combustion engines.

• You will analyze and evaluate measurement and simulation files with Python.

• You will deal with machine learning with Python (e.g. neural network, reinforcement learning).

• You visualize and validate the results of machine learning algorithms with Python.  

• You optimize the algorithm with a focus on the trade-off between complexity and accuracy.

Necessary Skills:

• Ongoing studies in a technical field, e.g. automotive engineering, physics 

• Interest in physics, thermodynamics, computer science 

• Experience in working with Python

• Interest in the field described 

• Ability to work independently and think analytically 

• Good language skills in English on at least B2 level (thesis will be written in English) 

   

The salary is based on our collective wage and salary agreement. The current monthly salary for this position is EUR 979. 

Desired Skills:

As a student at IAV, you don't work just anywhere, but right in the middle of things. In real projects. On exciting future tasks. Fully integrated and in close cooperation with IAV experts. A lot of responsibility and at the same time a lot of freedom to combine university and work: This creates the best prospects for your professional development. With attractive remuneration according to our company collective agreement.

Diversity and equal opportunities are important to us. What counts for us is the individual with their personality and strengths.

You won’t just be working anywhere as a student at IAV. You’ll be right in the middle of it all. Real projects. Exciting future tasks. Completely integrated and side-by-side with IAV experts. Lots of responsibility and at the same time lots of freedom, combining university and work. The result is the best prospects for your professional development. And attractive compensation in accordance with our company wage agreements.
Diversity and equal opportunity are important to us. What matters to us is the individual, with his or her character and strengths.