ECE Ph.D. student Zubin Mevawalla and Gary May, his advisor and Steve W. Chaddick School Chair, won the Best Student Abstract Award for "Neural Networks for Advanced Process Control" at the Advanced Semiconductor Manufacturing Conference, which was held in San Francisco in July 2010. This honor is shared with a third coauthor, Mark Kiehlbauch, of Micron Technology in Boise, Idaho. This award is sponsored by the International SEMATECH Manufacturing Initiative.

In the research described in this abstract, sequential neural network models were developed to characterize critical steps in fabricating integrated circuits. The data used were collected from an industrial process, a distinguishing feature of this research.

The models performed well, with testing errors below 5 percent, demonstrating the flexibility of the sequential neural network modeling process. Additionally, the models were used in a sensitivity analysis to study the output response to the various inputs. Future work will include using the models as part of a model-based supervisory control system.