Predictive eBoost for Volkswagen
- Matlab, Pandas, Python, Pytorch, simulink, sklearn, Tensorflow
Home » Success Stories »
Description
The aim of this project is to design new strategies, based on machine learning algorithms and data analysis, to improve the efficiency and performance of electric vehicle motors and batteries.
The batteries of electric vehicles are increasingly powerful and have more autonomy but also need adequate thermal management. Current strategies only take into account the current temperature of vehicle components to decide when to cool or heat them. The development of smarter decision-making systems, such as machine learning models, will enable better efficiency and consumption criteria to be achieved.
The focus of this project is to use information about the vehicle’s route, such as the slope of the road or the speed of circulation, to decide when to activate the cooling of the battery and, thus, to improve current strategies.
Final Career, Master’s or Thesis Projects
Articles and presentations
- La UPC, SEAT i Volkswagen Group Innovation cerquen noves estratègies per millorar el rendiment del ‘powertrain’ i de les bateries dels vehicles elèctrics del futur (Premsa UPC)
- La UPC, SEAT i Volkswagen Group Innovation col·laboren per millorar el rendiment de les bateries dels vehicles elèctrics del futur (GENCAT)
- El proyecto Predictive eBoost aplicará sistemas inteligentes para aumentar el rendimiento del VE (SMART GRIDS INFO)
- La UPC, SEAT y Volkswagen buscan mejorar los motores y las baterías de los vehículos eléctricos (AUTO-REVISTA)
- Video Predictive eBoost