The application of conventional and intelligent control paradigms to the dispensing of adhesive in the manufacture of mixed technology printed circuit boards, a real process with real time constraints and error conditions, is outlined in this paper. A description of the process and its various operation and error states is followed by a brief discussion of the application of conventional (system identification and incremental proportional control) and intelligent (knowledge-based, fuzzy logic and neural network) controllers to the system. Comments on the control and timing performance of each paradigm are given.
KinlochA. J.Adhesion and adhesives science and technology, 1987, Chapman and Hall, London).
2.
WestA. A.ChandrakerR.WilliamsD. J.MulvaneyD. J.Hybrid representations of real-time control rules for manufacturing process control in electronics manufacture. Proceedngs of the IEEE Symposium on Intelligent control, Arlington, Virginia, September 1988, pp. 745–750.
3.
ChandrakerR.WestA. A.WilliamsD. J.Intelligent control of adhesive dispensing. IJCIM, Special Issue on Intelligent Control, 1990, 3(1), 24–34.
4.
WestA. A.WilliamsD. J.HindeC. J.A benchmark of intelligent control techniques for surface mount technology (SMT) adhesive dispensing: Process overview and the application of a structured neural network controller. Trans. ASME, Mfg Aspects in Electronic Packaging, 1993, PED-65/EEP-5, 107–118.
5.
AntsaklisP. J.An introduction to intelligent and autonomous control, 1992, Kluwer, Dordrecht, The Netherlands).
6.
HarrisC. J.Advances in intelligent control, 1994, Taylor and Francis, London).
7.
LjungL.System identification: a theory for the user, 1987, Prentice-Hall, Englewood Cliffs, New Jersey).
8.
ShepherdB. A.Computer induction versus statistical classifiers in the domain of shape recognition. MPhil dissertation, University of Edinburgh, 1985.
9.
QuinlanJ. R.Discovering rules from large collections of examples. In Expert systems in the micro electronic ageMichieD.), 1979 (Edinburgh University Press).
10.
MichalskiR. S.MozeticI.HongJ.RoskarE.The multipurpose incremental learning system AQ15 and its testing application to three medical domains. Proceedings of Fifth National Conference on Artificial intelligence, Philadelphia, Pennsylvania, 1986.
PredryczW.Fuzzy control and fuzzy systems, 2nd edition, 1993 (John Wiley, New York).
13.
KoskoB.Neural networks and fuzzy systems, 1992, Prentice-Hall, Englewood Cliffs, New Jersey).
14.
MessomC. H.HindeC. J.WestA. A.WilliamsD. J.Designing neural networks for manufacturing process control systems. Seventh IEEE Intelligent Control Symposium, Glasgow, 1992, pp. 423–429.
15.
MirchandaniG.CaoW.On hidden nodes for neural nets. IEEE Trans. Circuits and Systems, 1989, 36, 661–664.
16.
FletcherG. P.HindeC. J.WestA. A.WilliamsD. J.Neural networks as a paradigm for knowledge elicitation. Proceedings of International Conference on Artificial neural networks, Sorrento, Italy, 1994, Vol. 1, Part 2, pp. 242–245 (Springer-Verlag, Berlin).
17.
AleksanderI.MortonH.An introduction to neural computation, 1990, Chapman and Hall, London).
