Machine Learning for Monitoring and Control of Automotive Vehicles

EAISI lecture by visiting Professor Mahdi Shahbakhti

Date
Wednesday April 17, 2024 from 3:30 PM to 4:30 PM
Location
Neuron 0.262
Price
free

Machine Learning for Monitoring and Control of Automotive Vehicles

Professor Mahdi Shahbakhti, Professor at the University of Alberta, Canada, is a guest of Frank Willems, Full Professor of Control Systems Technology at the department of Mechanical Engineering.

Title  |  Machine Learning for Monitoring and Control of Automotive Vehicles 

The automotive industry is undergoing major changes, with substantial growth in the areas of connectivity and autonomy. The majority of new vehicles sold in North America/Europe have capability for connectivity and data transfer. There are currently over 230 million connected vehicles worldwide [statista.com]. Data from vehicles can be used to monitor and decrease both vehicular emissions and energy consumption, reduce traffic congestion, and improve mobility. In this talk, integration of machine learning (ML) for control of automotive systems will be discussed. In particular, five areas for integration of machine learning and model predictive control (MPC) will be illustrated. These areas include ‘‘ML in the model structure of MPC’’, ‘‘ML in control structure of MPC’’, ‘‘ML in optimization of MPC’’, ‘‘ML in imitation of MPC’’, and ‘‘MPC for safe learning controller’’. This talk will include presentation of real-world light-duty and heavy-duty vehicle test data in Canada along with the test cell laboratory data for monitoring and control of tailpipe emissions and fuel consumption from powertrains/vehicles. 

Mahdi Shahbakhti

Mahdi Shahbakhti, Associate Professor of Mechanical Engineering at the University of Alberta in Canada, was previously a faculty member at Michigan Tech University (2012-2019), a post-doctoral scholar at the University of California-Berkeley (2010-2012) and received his PhD in Mechanical Engineering from the University of Alberta in 2009. His research has centered on developing data-driven/physical dynamical models and model-based control techniques with applications in energy systems in vehicles and buildings. He has co-authored more than 200 peer-reviewed publications in the field of controls and energy systems. His research has been funded by, among others, Canada Natural Sciences and Engineering Research Council, SSHRC, the US National Science Foundation, ARPA-E, the US Department of Energy, Ford Motor Company, General Motors, Toyota Motor Company, Cummins, and Westport. Dr. Shahbakhti is the former chair (2020-2022) of ASME Dynamic Systems Control Division (DSCD) Automotive and Transportation Systems Technical Committee and the former chair (2018-2020) of Energy Systems Technical Committee. He served as the Associate Editor for ASME Journal of Dynamic Systems, Measurement, and Control (2017-2023), and the International Journal of Powertrains (2014-2020).

URL: https://sites.ualberta.ca/~mahdi/index.html
 

Organizer

Eindhoven Artificial Intelligence Systems Institute

EAISI brings together all AI activities of the TU/e. Top researchers from various departments and research groups work together to create new and exciting AI applications with a direct impact on the real world. All this in close collaboration with our students and representatives from industry.