Non-linear model with disturbance rejection

Data processing: generic control systems or specific application – Generic control system – apparatus or process – Sequential or selective

Reexamination Certificate

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

C700S020000, C700S028000, C700S044000, C700S045000, C706S014000, C706S016000, C706S019000, C706S021000, C709S201000, C709S208000, C702S181000

Reexamination Certificate

active

07123971

ABSTRACT:
Non-linear model with disturbance rejection. A method for training a non linear model for predicting an output parameter of a system is disclosed that operates in an environment having associated therewith slow varying and unmeasurable disturbances. An input layer is provided having a plurality of inputs and an output layer is provided having at least one output for providing the output parameter. A data set of historical data taken over a time line at periodic intervals is generated for use in training the model. The model is operable to map the input layer through a stored representation to the output layer. Training of the model involves training the stored representation on the historical data set to provide rejection of the disturbances in the stored representation.

REFERENCES:
patent: 5167009 (1992-11-01), Skeirik
patent: 5353207 (1994-10-01), Keller et al.
patent: 5386373 (1995-01-01), Keeler et al.
patent: 5408406 (1995-04-01), Mathur et al.
patent: 5559690 (1996-09-01), Keeler et al.
patent: 5933345 (1999-08-01), Martin et al.
patent: 6047221 (2000-04-01), Piche et al.
patent: 6278899 (2001-08-01), Piche et al.
patent: 6725208 (2004-04-01), Hartman et al.
patent: 6950711 (2005-09-01), Havener et al.
patent: 6985781 (2006-01-01), Keeler et al.
patent: 2003/0014131 (2003-01-01), Havener et al.
patent: 2003/0078683 (2003-04-01), Hartman et al.
patent: 2005/0236004 (2005-10-01), Magnuson et al.
Steepest descent algorithms for neural network controllers and filters; Piche, S.W.; Neural Networks, IEEE Transactions on□□vol. 5, Issue 2, Mar. 1994 pp. 198-212, Digital Object Identifier 10.1109/72.279185.
The selection of weight accuracies for Madalines; Piche, S.W.; Neural Networks, IEEE Transactions on vol. 6, Issue 2, Mar. 1995 pp. 432-445, Digital Object Identifier 10.1109/72.363478.
A disturbance rejection based neural network algorithm for control of air pollution emissions; Piche, S.; Sabiston, P.; Neural Networks, 2005. IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on vol. 5, Jul. 31-Aug. 4, 2005 pp. 2937-2941.
Automated generation of models for inferential control; Piche, S.; American Control Conference, 1999. Proceedings of the 1999, vol. 5, Jun. 2-4, 1999 pp. 3125-3126 vol. 5, Digital Object Identifier 10.1109/ACC.1999.782339.
Trend visualization; Piche, S.W.; Computational Intelligence for Financial Engineering, 1995.,Proceedings of the IEEE/IAFE 1995, Apr. 9-11, 1995 pp. 146-150, Digital Object Identifier 10.1109/CIFER.1995.495268.
Robustness of feedforward neural networks; Piche, S.; Neural Networks, 1992. IJCNN., International Joint Conference on□□vol. 2, Jun. 7-11, 1992 pp. 346-351 vol. 2, Digital Object Identifier 10.1109/IJCNN.1992.226963.
The second derivative of a recurrent network; Piche, S.W.; Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on, vol. 1, Jun. 27-Jul. 2, 1994 pp. 245-250 vol. 1, Digital Object Identifier 10.1109/ICNN.1994.374169.
“Models of Linear Time-Invariant Systems”, Ljung, L., System Identificatiaons: Theory for the User, Chapter 4, Prentice Hall, Englefwood Cliffs, NJ, 1987.
“Modeling Chemical Process Systems via Neural Computation”, Bhat, N., Minderman, P., McAvoy, T., and Wang, N., IEEE Control Systems Magazine, pp. 24-30, Apr. 1990.
“Connectionist Learning for Control”, Barto, A., Neural Network for Control, edited by Miller, W., Sutton, R. and Werbos, P., MIT Press, pp. 5-58, 1990.
“Disturbance Rejection in Non-Linear Systems using Neural Networks”, Mukhopadhyay, S. and Narendra, K., IEEE Transactions on Neural Networks, vol. 4, No. 1, pp. 63-72, 1993.
“Steepest Descent Algorithms for Neural Network Controllers and Filter”, Piche, S., IEEE Transactions on Neural Ntworks, vol. 5, No. 2, Mar. 1994.
“Non-Linear Model Predictive Control using Neural Networks”, Piche, S., Sayyar-Rodsari, Johnson, D., and Gerules, M., IEEE Control Systems Magazine, vol. 20, No. 3, Jun. 2000.
“Support Vector Machines; a Non-Linear Modeling and Control Perspective”, Suykens, L., Technical Report, Katholieke Universiteit Leuven, Apr. 2001.
“Robust Redesign of a Neural Network Controller in the Presence of Unmodeled Dynamics”, G. Rovithakis, IEEE Trans. On Neural Networks, vol. 15, No. 6, aa 1482-1490, 2004.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Non-linear model with disturbance rejection 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 model with disturbance rejection, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Non-linear model with disturbance rejection will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-3638748

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.