Integrated computer-assisted process management

Managing a manufacturing process involves monitoring, diagnosis, and control. An architecture that merges existing data collection and analysis systems with AI-based pattern-detection, interpretation, and decision-making facilities is described. Functions are performed by agents that distribute tasks and control in a way that can be closely tailored to the manufacturing environment. Technical principles and the development strategy are discussed, together with experiences on already operating components.<<ETX>>

[1]  Eric Horvitz,et al.  A Framework for Comparing Alternative Formalisms for Plausible Reasoning , 1986, AAAI.

[2]  C. Robert Kenley,et al.  Gaussian influence diagrams , 1989 .

[3]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[4]  D. I. Sikka.  Automated feature detection and characterization in sort wafer maps , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[5]  J.Y.-C. Pan,et al.  AESOP: a simulation-based knowledge system for CMOS process diagnosis , 1989 .