Machine Learning Control technology applied to decarbonizing H2 fueled vehicles

The overall goal of this project is to improve the efficiency/emissions of H2/Diesel and H2 Hybrid systems to quickly reduce CO2 and pollutants from heavy duty long haul trucks and other heavy duty vehicles. Some of the expected outcomes are to provide robust and accurate Machine Learning Control (MLC) of an H2/Diesel engine and to also develop MLC control techniques and methods applicable to H2 fueled vehicles. In collaboration with our industrial partner, we aim to answer the question of how much Machine Learning Control (MLC) can help improve the efficiency of H2/Diesel and 100% H2 fueled transportation.


 

Premier Danielle Smith in Engine Lab

Charles Robert Koch

Government Briefings

Alberta Innovates Award

Hossein Mehnatkesh Ghadikolaei

Award

Hydrogen-Diesel Dual Fuel Combustion Characterization for an Internal Combustion Engine

Master Thesis

Real-time vehicular fuel consumption estimation using machine learning and on-board diagnostics data

Charles Robert Koch, Mahdi Shahbakhti

Peer-Reviewed Journal Article

Transfer of Reinforcement Learning-Based Powertrain Controllers From Model- to Hardware-in-The-Loop

Charles Robert Koch

Peer-Reviewed Journal Article

Transient NOx emission modeling of a hydrogen-diesel engine using hybrid machine learning methods

Charles Robert Koch, David Carl Gordon, Mahdi Shahbakhti

Peer-Reviewed Journal Article