MAE Graduate Seminar Speaker - Dr. Yan Wang

Dr. Yan Wang is a propulsion technology expert with more than 25 years of experience advancing sustainable transportation throughinnovative energy and powertrain technologies. Throughout his career at Ford Motor Company, Nikola Motor Company, and Cummins, he hasled the development of advanced propulsion solutions across gasoline, diesel, hybrid, battery-electric, and fuel-cell-electric vehicle platforms. Dr.Wang's expertise spans combustion systems, electrified powertrains, controls, calibration, diagnostics, optimization, and intelligent energymanagement. He has developed model-based and data-driven engineering approaches that integrate machine learning, virtual development,and connected vehicle technologies to improve vehicle efficiency, emissions performance, reliability, and development productivity. An inventor ofmore than 50 U.S. patents and author of over 60 technical publications, Dr. Wang is Chair of the IEEE Control Systems Society TechnicalCommittee on Automotive Control for Electric and Hybrid Vehicles. His work continues to focus on enabling sustainable, efficient, and intelligenttransportation systems through the convergence of advanced controls, electrification, artificial intelligence, connectivity, and digital engineering.

Intersection of model based powertrain controls with AI / ML

Traditional model-based powertrain control systems have been the foundation of vehicle operation for decades, evolving continuouslyto deliver safe, efficient, and comfortable transportation. As powertrain architectures become increasingly complex and regulatory requirementscontinue to tighten, however, achieving globally optimal control for maximum efficiency using conventional approaches has become increasinglychallenging. While AI/ML has seen widespread deployment in perception-intensive applications such as advanced driver assistance systems(ADAS) and automated driving, its adoption in production powertrain control has been more selective. This presentation explores how AI/ML cancomplement—not replace—established model-based control frameworks to enhance powertrain performance. We will discuss practicalapplications in offline calibration, online adaptive control, and digital twin development, highlighting how AI/ML can improve efficiency,robustness, and scalability while leveraging decades of existing control expertise.