Automated Engineering with Genetic Algorithms

from the AI-in-action dept.

An early example of automated engineering guided by AI was reported in mid-June.

A press release decribes work using computer models developed at the University of Wisconsin-Madison that employ genetic algorithms to design high-performance deisel engines. The new designs simultaneously increase fuel efficiency and reduce pollution.

The development of automated engineering was anticipated by Eric Drexler in Engines of Creation (see "Automated Engineering" in the Glossary, for example).

According to the press release:

The computer models sort through billions of combinations of factors that determine engine performance to reduce pollution emissions without sacrificing fuel efficiency, and vice versa. Normally, engine designers who concentrate on solving one problem end up with major tradeoffs in the other.

The results have been dramatic. Using a Silicon Graphics supercomputer at UW-Madison's Engine Research Center, Senecal created a diesel engine design that reduces nitric oxide emissions by three-fold and soot emissions by 50 percent over the best available technology. At the same time, the model reduced fuel consumption by 15 percent.

While it's not nanotechnology, this sort of automated engineering will become more and more common as increased computing power becomes available, and will eventually be applied to the complexities of designing molecular machine systems.

Leave a comment