Data processing: artificial intelligence – Neural network – Learning task
Reexamination Certificate
2006-06-20
2006-06-20
Starks, Jr., Wilbert L. (Department: 2121)
Data processing: artificial intelligence
Neural network
Learning task
C700S029000, C703S013000
Reexamination Certificate
active
07065511
ABSTRACT:
A non-linear dynamic predictive device (60) is disclosed which operates either in a configuration mode or in one of three runtime modes: prediction mode, horizon mode, or reverse horizon mode. An external device controller (50) sets the mode and determines the data source and the frequency of data. In the forward modes (prediction and horizon), the data are passed to a series of preprocessing units (20) which convert each input variable (18) from engineering units to normalized units. Each preprocessing unit feeds a delay unit (22) that time-aligns the input to take into account dead time effects. The output of each delay unit is passed to a dynamic filter unit (24). Each dynamic filter unit internally utilizes one or more feedback paths that provide representations of the dynamic information in the process. The outputs (28) of the dynamic filter units are passed to a non-linear approximator (26) which outputs a value in normalized units. The output of the approximator is passed to a post-processing unit (32) that converts the output to engineering units. This output represents a prediction of the output of the modeled process. In reverse horizon mode, data is passed through the device in a reverse flow to produce a set of outputs (64) at the input of the predictive device. These are returned to the device controller through path (66). The purpose of the reverse horizon mode is to provide information for process control and optimization. The predictive device approximates a large class of non-linear dynamic processes. The structure of the predictive device allows it to be incorporated into a practical multivariable non-linear Model Predictive Control scheme, or used to estimate process properties.
REFERENCES:
patent: 5535135 (1996-07-01), Bush et al.
patent: 5659667 (1997-08-01), Buescher et al.
patent: 5877954 (1999-03-01), Klimasauskas et al.
patent: 5992383 (1999-11-01), Scholten et al.
patent: 6278962 (2001-08-01), Klimasauskas et al.
patent: 6751602 (2004-06-01), Kotoulas et al.
patent: 6823244 (2004-11-01), Breed
patent: WO 97/28669 (1997-08-01), None
patent: WO 99/17175 (1999-04-01), None
Bishop, C.M.,Neural Networks for Pattern Recognition, Oxford University Press (1995) p. 137-146.
Boyd, S. and L. Chua, “Fading Memory and the Problem of Approximating Nonlinear Operators with Volterra Series,”IEEE Trans. on Circuits and Systems, 32:11, p. 1150-1161 (Nov. 1985).
Graettinger, T.J., et al., “Model Predictive Control Using Neural Networks,”The AIChE 1994 Spring National Meeting(1994).
Qin, S.J. and Badgwell, T.J., “An Overview of Industrial Model Predictive Control Technology,”Preprints of CPC-V, Tahoe, Jan. 7-12, 1996, p. 1-31.
Sentoni, G., et al., “Approximate Models for Nonlinear Process Control,”AIChE Journal: 42(8) p. 2240-2250 (1996).
Su, H. et al., “Long-Term Predictions of Chemical Processes Using Recurrent Neural Networks: A Parallel Training Approach,”I&EC Research 31(5), p. 1338-1352 (1992).
Werbos, P., “Forms of Backpropagation for Sensitivity Analysis, Optimization, and Neural Networks,”The Roots of Back Propagation: From Ordered Derivatives to Neural Networks and Political Forecasting, p. 256-262, John Wiley and Sons (1994).
Zhao, H. et al., “NeuCOP II: A Nonlinear Multivariable Process Modeling, Control and Optimization Package,”AIChE 1997 Spring National Meeting, Houston, Texas (1997).
Kolmogorov, A.N. and S.V. Fomin,Introductory Real Analysis, pp. 1-49, Dover Publications, Inc., New York (1980).
G. Sentoni et al., “On the Evaluation of a Certain Kind of Approximation Structure,”Latin American Applied Research 25-S:35-40 (1995).
Katebi, M.R. and M.A. Johnson, “Predictive Control Design for Large Scale Systems,”Integrated Systems Engineering. A Postprint Volume from the IFAC Conference, pp. 47-52, Sep. 27, 1994.
Gibbs, B.P. and D.S. Weber, “Nonlinear Model Predictive Control for Fossil Power Plans,”Proc. American Control Conference, 4:3901-3098, Jun. 24, 1992.
Korn, Granino A., “Neural Networks and Fuzzy-Logic Control on Personal Computers and Workstations,” The MIT Press, 1995, pp. 252-253.
Guiver John P.
Sentoni Guillermo
Zhao Hong
Aspen Technology Inc.
Hamilton Brook Smith & Reynolds P.C.
Starks, Jr. Wilbert L.
LandOfFree
Non-linear dynamic predictive device does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Non-linear dynamic predictive device, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Non-linear dynamic predictive device will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3683712