Intelligent Semiconductor Manufacturing Using AI and Neural Networks

EECS Joint Colloquium Distinguished Lecture Series

pic of Gary May

Professor Gary S. May
School of Electrical and Computer Engineering and Microelectronics Research Center, Georgia Institute of Technology

Wednesday, April 12, 2000
Hewlett Packard Auditorium, 306 Soda Hall
4:00-5:00 p.m.


The development of efficient computer-aided manufacturing systems is critical to increasing productivity and efficiency in high-volume semiconductor fabrication. CAM systems can alleviate process fluctuation, yield loss and equipment downtime through the application of in-situ process monitoring, process/equipment modeling, real-time process monitoring and control, and equipment malfunction diagnosis. Although these techniques have traditionally relied on statistically-based methods in their implementation, several researchers have recently explored the feasibility of using artificial neural networks as an alternative approach. In several studies, neural networks have been shown to exhibit superior accuracy and predictive capability in the process modeling application. Based on these findings, it is anticipated that the innovative use of neural networks can have a significant impact in process monitoring and control, recipe generation, and equipment diagnosis as well.

At the Georgia Tech Microelectronics Research Center, research is underway to use neural networks and other artificial intelligence techniques to: 1) build accurate and robust process models; 2) use these models for process recipe optimization and synthesis; 3) design a real-time, closed-loop neural process control scheme based on these models; and 4) provide malfunction identification in a hybrid diagnostic expert system. This talk will provide a general overview of the potential value of neural networks in semiconductor manufacturing, with a particular emphasis on the areas listed above. In addition, the talk will touch on other aspects of CAM research being conducted by the Intelligent Semiconductor Manufacturing group at Georgia Tech, including sensor development and parametric yield modeling.


Gary S. May received the B.S. degree in electrical engineering from the Georgia Institute of Technology in 1985 and the M.S. and Ph.D. degrees in electrical engineering and computer science from the University of California at Berkeley in 1987 and 1991, respectively. He is currently an Associate Professor in the School of Electrical and Computer Engineering and Microelectronics Research Center at the Georgia Institute of Technology. His research is in the field of computer-aided manufacturing of integrated circuits, and his interests include semiconductor process and equipment modeling, process simulation and control, automated process and equipment diagnosis, and yield modeling.

Dr. May was a National Science Foundation "National Young Investigator," and has been an Editor-in-Chief of IEEE Transactions on Semiconductor Manufacturing since 1997. He has published over 100 articles, authored four book chapters, and given over 70 technical presentations in the area of computer-aided manufacturing of ICs. He was a National Science Foundation and an AT&T Bell Laboratories graduate fellow, and has worked as a member of the technical staff at AT&T Bell Laboratories in Murray Hill, NJ. He is currently Chairperson of the National Advisory Board of the National Society of Black Engineers and Vice-Chairperson of the NSF Committee for Equal Opportunity in Science and Engineering.