This was still considered impractical, as the engine would need different parts to burn different fuels. For instance, burning gasoline in an engine usually needs a spark to start the fire, while in diesel engines, the fuel spontaneously combusts after it is compressed in the cylinders. Trying to burn gasoline in a diesel engine would not work, as the cylinder explosion is unpredictable or does not happen at all.
We know Cummins started work on a fuel-agnostic engine that could burn any fuel with slight modifications. This means the engine still needs to be adapted for a specific fuel, but most of the parts are the same regardless of the fuel burnt. Illinois Institute of Technology Associate Professor Carrie Hall thinks there's a better way. This only requires a software update for the engine’s management system to run on a different fuel.
Carrie Hall’s work relies on machine learning and computer modeling to figure out what’s going on inside the cylinders and when specific actions need to be performed during the combustion process to optimize burning. Her work is geared towards using gasoline instead of diesel fuel for now, but can be adapted to other fluids too, like a low-carbon fuel called dimethyl ether.
“There’s an anticipation that with electric vehicles being more common for passenger cars in the United States there’ll be a lot of extra gasoline that’s not getting used. That gasoline can be used on heavier-duty vehicles. That’s a strategy that’s still being explored,” says Hall. “Making engines smart enough to use a broader range of fuels also opens the door to other possibilities, such as using carbon-neutral or carbon-negative fuels.”
Machine-learning approach needs to be completely retrained for each new fuel, but Hall simplified the whole process and only needs to update some parameters that correspond to measurable fuel properties. Her research is part of a broader project to figure out how to use gasoline in diesel engines and was conducted in collaboration with Argonne National Laboratory, Navistar, and Caterpillar.