from the Automated-engineering dept.
According to a press release (22 January 2002), a new method promises to change how companies create materials — using artificial intelligence and a technique that simultaneously tests thousands of formulations — dramatically speeding up the discovery process. The system, which combines hardware and software, was developed by Jochen Lauterbach, an associate professor of chemical engineering at Purdue University in West Lafayette, Indiana.
According to the press release, Lauterbach has developed an automated system that uses combinatorial chemistry, in which equipment systematically creates and tests thousands of chemical samples at the same time using thousands of tiny plastic beads coated with different catalysts. All of the beads, each bearing its own individual catalyst, are tested simultaneously. The system then uses infrared sensor technology to quickly screen each sample to evaluate its performance. A small percentage of the catalysts created are effective. Information is collected from both the best catalysts and the failed catalysts and fed into software that employs hybrid neural networks and genetic algorithms to mimics the logical and intuitive thought processes of chemists. Even though the majority of the catalysts created are not effective, the software uses the wealth of information gained from those failures to come up with entirely new catalysts.