Method for steady-state identification based upon identified dyn

Details Method for steady-state identification based upon identified dyn Method for steady-state identification based upon identified dyn

1997-10-03

2000-04-04

Gordon, Paul P.

Data processing: generic control systems or specific application

Generic control system, apparatus or process

Optimization or adaptive control

700 46, 700 71, 700 29, 327185, 327198, 399 77, G05B 1302

Patent

active

060472219

ABSTRACT:
A method for modeling a steady-state network in the absence of steady-state historical data. A steady-state neural network can be tied by impressing the dynamics of the system onto the input data during the training operation by first determining the dynamics in a local region of the input space, this providing a set of dynamic training data. This dynamic training data is then utilized to train a dynamic model, gain thereof then set equal to unity such that the dynamic model is now valid over the entire input space. This is a linear model, and the historical data over the entire input space is then processed through this model prior to input to the neural network during training thereof to remove the dynamic component from the data, leaving the steady-state component for the purpose of training. This provides a valid model in the presence of historical data that has a large content of dynamic behavior. A single dynamic model is required for each output variable in a multi-input multi-output steady-state model such that for each output there is a separate dynamic model required for pre-filtering. They are combined in a single network made up of multiple individual steady-state models for each output. The dynamic model can be identified utilizing a weighting factor for the gain to force the dynamic gain of the dynamic model to the steady-state gain by weighting the difference thereof during optimization of the dynamic model. The steady-state model is optimized utilizing gain constraints during the optimization procedure such that the gain of the network is prevented from exceeding the gain constraints.

REFERENCES:
patent: 4868754 (1989-09-01), Matsumoto
patent: 4922412 (1990-05-01), Lane et al.
patent: 4964120 (1990-10-01), Mostashari
patent: 5251285 (1993-10-01), Inoue et al.
patent: 5477444 (1995-12-01), Bhat et al.
patent: 5781432 (1998-07-01), Keeker et al.
"Introduction to System Dynamics", Shearer, J.L., Murphy, A.T., and H.H., Richardson, Addison-Wesley, Reading, Massachusetts, 1967.
"System Identification", Eykhoff, P., John Wiley & Sons, New York, NY, 1974.
"Digital Signal Processing", A.V. Oppenheim and R.W. Schafer, Prentice-Hall, Englewood Cliffs, New Jersey 1975.
"Time Series Analysis", Box, G.E.B. and G.M. Jenkins, Holden-Day, San Francisco, 1976.
"Digital Parameter--Adaptive Control of Processe with Unknown Dead Time", Kurz, H. and W. Goedecke, Automatica, vol. 17, No. 1, 1981, pp. 245-252.
European Patent Office Patent Abstract, Application No. 01138748, Sekine, et al., filed May 31, 1989.
"Process Dynamics and Control", D.E. Seborg, T.F. Edgar and D.A. Mellichamp, Wiley and Sons, New York, NY 1989.
"Model Predictive Control Using Neural Networks", T.J. Graettinger, N.V. Bhat, K. Heckendorn, J.S. Buck, AIChE, pp. 1-11, Apr. 1994.
"Gain Scheduled Model Predictive Control of A Crude Oil Distillation Unit", Muske, Kenneth R., Logue, Dan A., Keaton, Michael M., AIChE, Aug. 15, 1991, pp. 1-12.
"Integration of Multilayer Perceptron Networks and Linear Dynamic Models: A Hammerstein Modeling Approach", Su, H.-T. and T.J. McAvoy, I&EC Fundamentals, Jul. 1992.
"Model Predictive Control: Theory and Practice--A Survey", C.E. Garcia, D.M. Prett and M. Morari, Automatica, 25:335-348, 1989.
"Adaptive Control with NeuCOP, the Neural Control and Optimixation Package", T. Graettinger, N.V. Bhat, J.S. Buck, IEEE International Conference, 1994.
"Systematic Process Modeling and Identification for Prediction, Control and Optimization", G.D. Martin, Pavilion Invention Disclosure Description, Jun. 9, 1995.
PCT Search Report for PCT/US97/-8473, dated Sep. 3, 1997.

Affiliated with

Also associated with

Rating

Method for steady-state identification based upon identified dyn does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method for steady-state identification based upon identified dyn, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for steady-state identification based upon identified dyn will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-373767