18/09/2019

Enhancing automotive simulation tools with AI

This job offer has expired


  • ORGANISATION/COMPANY
    Continental Automotive
  • RESEARCH FIELD
    Computer scienceInformatics
    Mathematics
  • RESEARCHER PROFILE
    First Stage Researcher (R1)
    Recognised Researcher (R2)
    Established Researcher (R3)
    Leading Researcher (R4)
  • APPLICATION DEADLINE
    31/10/2019 00:00 - Europe/Athens
  • LOCATION
    France › Toulouse
  • TYPE OF CONTRACT
    Temporary
  • JOB STATUS
    Full-time
  • OFFER STARTING DATE
    12/11/2019

Scientific challenge description

1. Context

Automobile manufacturers are confronted with major technological challenges regarding the development of new drive trains.

On one hand, strict legislation and regulation requiring overall and continuous reduction of fuel consumption and emission levels of new vehicles, as well as the emergence of new energy types: electric, hybrid, fuel cells.

On the other hand, rising customer demands regarding vehicle dynamics, overall comfort and affordability.

 

Continental Automotive focuses on the development of new powertrain technologies to fulfill the above demands. Continental believes that machine learning techniques can play a substantial role in the development of future drive trains, as manufacturers are increasingly reaching limits with traditional engineering methods.

 

We are willing to leverage machine learning to obtain reliable, interpretable simulation results, which can be used to predict drive train components behavior in extreme situations.

Also, we want to understand how to optimize the type and amount of data to be collected so as to optimize collection costs.

 

2. State of the art current limitations

Current physical models meet three major challenges: development complexity, output quality, execution time. We hope to overcome some or all of these challenges with data based models.

Data based models also come with their limitations: there is a trade off between interpretability and quality. Also, outcome confidence level is hard to estimate, especially when predicting outcome outside of the range of observed training data.

Scientific research themes

To be confirmed with academic partner

Success criteria

From a theoretical standpoint, we expect the candidate to develop training and validation machine learning methods that solve the challenges mentioned above.

 

From a practical standpoint, we would like to apply these methods to one or more concrete cases and integrate them seamlessly in the simulation development chain so as to improve its quality and execution speed.

Industrial applications examples

Calibration of electric engine

Polluants prediction for internal combustion engines (NOx, CO, particles)

 

Required data for the challenge

For some of the challenges, data is readily available.

For others, data is partly or not available yet and collected strategies will have to be defined and executed.



Funding category: Cifre



PHD title: PhD in Machine Learning

PHD Country: France

Offer Requirements

Specific Requirements

We are looking for a curious mind with machine learning skills, excited to push the boundaries of simulation with AI in order to enable tomorrow's mobility: safer, cleaner, connected and for everyone

Work location(s)
1 position(s) available at
Continental Automotive
France
Toulouse

EURAXESS offer ID: 446624
Posting organisation offer ID: 87437

Disclaimer:

The responsibility for the jobs published on this website, including the job description, lies entirely with the publishing institutions. The application is handled uniquely by the employer, who is also fully responsible for the recruitment and selection processes.

 

Please contact support@euraxess.org if you wish to download all jobs in XML.