>using a Silicon Graphics Origin 2000 supercomputer with 32 processors it took more than two weeks of continuous operation to find an optimal set of parameters.
>Dr. Senecal's test engine consumed 15 percent less fuel than a standard engine while producing one-third as much nitric oxide and half the soot.
Unfortunately I have no idea if anything ever came of this or not. I can't find anything. It'd be incredibly sad if this actually worked and then was never implemented.
This was done just with a dumb genetic algorithm on 2000 era computers, a population size of 5, run for 50 generations, and only tweaking a handful of parameters. I believe there is more potential in stuff like this.
Here (http://www.nytimes.com/2000/09/19/science/putting-a-darwinia...) is an old story about a group who used genetic algorithm to design a more efficient diesel engine.
>using a Silicon Graphics Origin 2000 supercomputer with 32 processors it took more than two weeks of continuous operation to find an optimal set of parameters.
>Dr. Senecal's test engine consumed 15 percent less fuel than a standard engine while producing one-third as much nitric oxide and half the soot.
Unfortunately I have no idea if anything ever came of this or not. I can't find anything. It'd be incredibly sad if this actually worked and then was never implemented.
This was done just with a dumb genetic algorithm on 2000 era computers, a population size of 5, run for 50 generations, and only tweaking a handful of parameters. I believe there is more potential in stuff like this.