Patent
1994-12-16
1997-07-15
Davis, George B.
395 23, 395903, 395906, G06F 1518
Patent
active
056490631
ABSTRACT:
Feedback control of a process to reduce process variations is advantageously accomplished by the combination of a signal processor (26) and an artificial neural network (27). The signal processor (26) first determines which of a plurality of process outputs has the greatest deviation from a corresponding desired value for that output. Having determined which of the process outputs has the greatest deviation from its corresponding desired value, the process controller (25) then adjusts the output having the greatest deviation to yield an estimated process output vector T.sub.m.sup.n supplied to the artificial neural network (27) trained to represent an inverse model of the process. In response to the estimated process output vector T.sub.m.sup.n, the artificial neural network (27) generates a process control vector c.sub.n that controls the process in accordance with the first order variation between the actual process output and a desired value therefor to reduce process variations.
REFERENCES:
patent: 5113483 (1992-05-01), Keeler et al.
patent: 5119468 (1992-06-01), Owens
patent: 5159660 (1992-10-01), Lu et al.
patent: 5175678 (1992-12-01), Ferichs et al.
patent: 5203984 (1993-04-01), Sakai et al.
patent: 5204872 (1993-04-01), Staib et al.
patent: 5220373 (1993-06-01), Kanaya
patent: 5250766 (1993-10-01), Hikita et al.
patent: 5305230 (1994-04-01), Matsumoto et al.
patent: 5311421 (1994-05-01), Nomura et al.
patent: 5367612 (1994-11-01), Bozich et al.
patent: 5402519 (1995-03-01), Inoue et al.
patent: 5422983 (1995-06-01), Castelaz et al.
patent: 5428559 (1995-06-01), Kano
patent: 5471381 (1995-11-01), Khan
Bleuler et al, "Nonlinear Neural Network Control with Application Example", Inter-Neural Network Conf., IEEE 1990.
Guez et al, "Neural Network Architecture for Control", IEEE Control System Magazine, 1988.
Gupta et al, "Learning and Adaptive Neural Controller", IEEE ICNN, 1991.
Pourboghrat et al, "Neural Network Models for the Learning Control of Dynamical Systems with Application to Robotics", Southern Illinois University, 1989.
Su et al, "Neural Model Predictive Control of Nonlinear Chemical Processes", IEEE Proceeding of the 1993 Inter. Symp. on Intelligent Control, 1993.
Ungar et al, "Adaptive Networks for Fault Diagnosis and Process Control" Computer & Chemical Engineering Journal, Nos. 4-5, pp. 561-572, May 1990.
Bhat et al, "Use of Neural Nets for Dynamic Modeling and Control of Chemical Process Systems", Computer and Chemical Engineering Journal, vols. 4-5, pp. 573-583, May 1990.
Nadi et al, "Use of Influence Diagrams and Neural Networks in Modeling Semi-Conductor Manufacturing Processes", IEEE Transactions on Semi-Conductor Manufacturing, vol. 4 No. 1 Feb. 1991, pp. 52-58.
Lee et al, "Adaptive Power System Control with Neural Networks", ISCNN Jun. 7-11, 1992, pp. 838-843 vol. 2.
Hinton et al, "Learning Internal Representation by Error Propagation" in the Text Parallel Distributed Processing, Explorations in the Microstructure of Cognition, vol. 1, MIT Press, 1986.
"Supervised Learning and Systems with Excess Degrees of Freedom", COINS Technical Report 88-27, 1988, Department of Computer Science and Information, University of Massachusetts and Amherst Massachusetts.
D. Psaltis, A. Sideris, and A. A. Yamamura, "A Multilayered Neural Network Controller," IEEE Control Systems Magazine, Apr. 1988, pp. 17-21.
E. A. Rietman and R. C. Frye, "Neural Control of a Nonlinear System with Inherent Time Delays," ACM Conference 1991, Analysis of Neural Network Applications, ANNA-91, May 29-30, 1991.
Davis George B.
Levy Robert B.
Lucent Technologies - Inc.
LandOfFree
Feedback process control using a neural network parameter estima does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Feedback process control using a neural network parameter estima, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Feedback process control using a neural network parameter estima will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1497982