Researchers at the University of Missouri-Rolla have developed a neural network controller that can learn how best to mix fuel and air and adjust an engine to run more efficiently.
Dr. Jagannathan Sarangapani, professor of electrical and computer engineering at UMR, and Dr. Jim Drallmeier, professor of mechanical and aerospace engineering at UMR, and their students have spent the last two years developing the controller, aimed at making engines cleaner and greener.
The controller has produced good results with exhaust gas recirculation (EGR), a technique used to reduce nitrogen oxide emissions. The device could be used to reduce the amount of fuel in a fuel/air mixture or dilute the mixture with inert gases.
The researchers created a neural network controller that is implemented as a software program. The neural network observer part of the controller assesses the total air and fuel in a given cylinder in a given time. It then sends that estimate to another neural network, which generates the fuel commands and tells the engine how much fuel to use in each cycle. The engine performance can then adjust accordingly within a matter of milliseconds in time for the next cycle.
Significant theoretical challenges encountered during controller design must be overcome before the controller can be implemented on the hardware, Sarangapani says.
“Very limited information is known to the controller from the engine, and the controller must generate an appropriate fuel command signal per cycle while ensuring overall performance,” Sarangapani says. “The actor-critic neural network learns on-the-fly using reinforcement signals.”
Although increasing EGR can reduce nitrogen oxide emissions, it can cause significant cyclic dispersion in heat release.
“Cyclic dispersion is a cycle-to-cycle variability in engine output,” Drallmeier says. “A good example of people experiencing cyclic dispersion is when they’re sitting in their car at a stop light and they feel their car shaking. The more EGR you can add, the lower your nitrogen oxide emissions. The question is how far can we push it and still keep cyclic dispersion in a reasonable range.”
A smart controller could be developed that reduces cyclic dispersion and increases engine efficiency still further. It could also help reduce emissions when catalytic converters don’t work to full capacity, such as on a cold start.