Share Email Print
cover

Proceedings Paper

Expert system and process optimization techniques for real-time monitoring and control of plasma processes
Author(s): Jie Cheng; Zhaogang Qian; Keki B. Irani; Hossein Etemad; Michael E. Elta
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

To meet the ever-increasing demand of the rapidly-growing semiconductor manufacturing industry it is critical to have a comprehensive methodology integrating techniques for process optimization real-time monitoring and adaptive process control. To this end we have accomplished an integrated knowledge-based approach combining latest expert system technology machine learning method and traditional statistical process control (SPC) techniques. This knowledge-based approach is advantageous in that it makes it possible for the task of process optimization and adaptive control to be performed consistently and predictably. Furthermore this approach can be used to construct high-level and qualitative description of processes and thus make the process behavior easy to monitor predict and control. Two software packages RIST (Rule Induction and Statistical Testing) and KARSM (Knowledge Acquisition from Response Surface Methodology) have been developed and incorporated with two commercially available packages G2 (real-time expert system) and ULTRAMAX (a tool for sequential process optimization).

Paper Details

Date Published: 1 March 1991
PDF: 12 pages
Proc. SPIE 1392, Advanced Techniques for Integrated Circuit Processing, (1 March 1991); doi: 10.1117/12.48931
Show Author Affiliations
Jie Cheng, Univ. of Michigan (United States)
Zhaogang Qian, Univ. of Michigan (United States)
Keki B. Irani, Univ. of Michigan (United States)
Hossein Etemad, Univ. of Michigan (United States)
Michael E. Elta, Univ. of Michigan (United States)


Published in SPIE Proceedings Vol. 1392:
Advanced Techniques for Integrated Circuit Processing
James A. Bondur; Terry R. Turner, Editor(s)

© SPIE. Terms of Use
Back to Top