An Associate Professor at the Illinois Institute of Technology has developed a clever computer model that could allow diesel engines to run on alternative fuels. To take advantage of this, diesel-engined vehicles would only need to upgrade their suite of software, where applicable.
The Associate Professor, Carrie Hall, utilized a combination of machine learning (ML) and computer modeling to achieve the feat. This development is a welcome one in order to accelerate our transition away from heavily polluting fuels like diesel.
It is hoped that this development will greatly improve the sustainability of larger diesel-engined vehicles, like trucks, that are heavily reliant on diesel due to the large distances they need to regularly travel. For now, complete electrification of freight vehicle fleets is not really practicable.
The software could also help some aircraft too.
“Since we are focusing on a software upgrade, somebody can actually put that into their vehicle without incurring a lot of extra costs,” Hall explained. “They’re not really going to have to change the hardware on their vehicle.”
This software upgrade could act as an important stepping stone to help trucks move away permanently from diesel fuel.
“There’s an anticipation that with electric vehicles being more common for passenger cars in the United States that 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,” added 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.”
This could prove game-changing for heavy-duty vehicles that account for about 1/4 of all U.S. on-road fuel consumption while only comprising about 1 percent of all vehicles. Improving their efficiency, therefore, should become the focus for the short- to medium-term.
“Everything that we’re doing is looking at trying to get to cleaner and more efficient vehicles,” says Hall.
One alternative fuel that could be considered is gasoline. However, as any diesel-engined vehicle owner knows, this is not a good idea without adapting the engine.
The main reason for this is that diesel and gasoline react differently. Gasoline typically requires a spark to ignite it and the resulting explosion travels away uniformly through the engine cylinder.
Diesel, on the other hand, tends to spontaneously combust after being compressed in the cylinder. When you try to run gasoline in a traditional diesel engine, the cylinder might explode, or it might not burn at all.
The model could allow for multiple fuels to be used with a simple software update
For this reason, Hall realized, timing is everything as engine efficiency typically relies heavily on running multiple cylinders in harmony.
“If fuel burns a little too early or too late, you don’t actually get all the benefit from it, and the efficiency is worse,” explained Hall.
To make this possible, therefore, engine management systems need real-time information on when fuel has ignited.
“Things that are actually happening inside the engine cylinder are really hard to measure in a cheap way,” says Hall. “So what we’re trying to do is take the information that we get from simpler, cheaper sensors that are outside of the actual engine cylinder where the combustion is happening, and from that diagnose what’s happening inside the engine,” she added.
And all this needs to happen in a fraction of a second, all the time.
“Our models are used to provide some system feedback,” says Hall. “Understanding the timing of [fuel ignition] gives us an idea of how it was tied to something like fuel injection, which we then might want to adjust based on that feedback.”
At present, the kind of calculation speed needed can be achieved using machine learning techniques or storing large data tables. Hall, however, took a different approach.
“We’ve been trying to create models that are based on the underlying physics and chemistry, even when we have these very complicated processes,” Hall says. “Recently there’s been interest in using neural networks to model combustion. The problem is that then it’s just a black box, and you don’t really understand what’s happening underneath it, which is challenging for control, because if you're wrong, you can have something that goes very wrong.”
So, Hall looked at ways to simplify existing calculations and methods to speed up the process.
“We’ve tried to capture all the underlying effects, even if it’s in a more detailed way than we know we’re going to really be able to use for real-time control, and let that be our reference point. Then we simplify it down by using things like neural networks strategically, but we keep this overall structure so that we understand what each piece means and what it’s actually doing inside there,” says Hall.
This resulted in a leaner, more adaptable model that can be adapted for different fuels with a simple update.
This is the key to Hall's research and her recent work built on her experience with working on novel fuels in the past - like fuel blends. Hall is also is a member of a collaborative group that was recently awarded $2 million by the U.S. Department of Energy to test novel applications of a low-carbon fuel called dimethyl ether.
Hall’s control model, which Illinois Tech Research Assistant Professor Michael Pamminger (Ph.D. MAE ’21) worked on as a student in Hall’s research group, is one piece of a larger project to figure out how to use gasoline in diesel engines and was conducted in collaboration with Argonne National Laboratory, Navistar, and Caterpillar.
“We’re working with those companies to try to help them understand the underlying combustion processes, but then also to build tools that they can potentially fold into their own software, and then enable their next generation of engines to use these fuels and use them well,” says Hall.