Data processing: generic control systems or specific application – Generic control system – apparatus or process – Optimization or adaptive control
Reexamination Certificate
2006-10-03
2006-10-03
Knight, Anthony (Department: 2121)
Data processing: generic control systems or specific application
Generic control system, apparatus or process
Optimization or adaptive control
C123S601000, C123S689000, C123S695000, C706S906000, C706S015000
Reexamination Certificate
active
07117045
ABSTRACT:
A neural network controller in parallel with a proportional-plus-integral (PI) feedback controller in a control system. At least one input port of the neural network for receiving an input signal representing a condition of a process is included. A first set of data is obtained that includes a plurality of output values of the neural network obtained during a training period thereof using a plurality of first inputs representing a plurality of conditions of the process. The process/plant condition signals generally define the process/plant, and may include one set-point as well as signals generated using measured systems variables/parameters. In operation, the neural network contributes to an output of the PI controller only upon detection of at least one triggering event, at which time a value of the first set of data corresponding with the condition deviation is added-in thus, contributing to the proportional-plus-integral feedback controller. The triggering event can be characterized as (a) a change in any one of the input signals greater-than a preselected amount, or (b) a detectable process condition deviation greater-than a preselected magnitude, for which an adjustment is needed to the process/plant being controlled. Also a method for controlling a process with a neural network controller operating in parallel with a IP controller is included.
REFERENCES:
patent: 5159660 (1992-10-01), Lu et al.
patent: 5212765 (1993-05-01), Skeirik
patent: 5282261 (1994-01-01), Skeirik
patent: 5448681 (1995-09-01), Khan
patent: 5450837 (1995-09-01), Uchikawa
patent: 5471381 (1995-11-01), Khan
patent: 5477444 (1995-12-01), Bhat et al.
patent: 5566065 (1996-10-01), Hansen et al.
patent: 5570282 (1996-10-01), Hansen et al.
patent: 5579746 (1996-12-01), Hamburg et al.
patent: 5579993 (1996-12-01), Ahmed et al.
patent: 5586221 (1996-12-01), Isik et al.
patent: 5625552 (1997-04-01), Mathur et al.
patent: 5720002 (1998-02-01), Wang
patent: 5781701 (1998-07-01), Wang
patent: 5847952 (1998-12-01), Samad
patent: 5870729 (1999-02-01), Yoda
patent: 5924086 (1999-07-01), Mathur et al.
patent: 6033302 (2000-03-01), Ahmed et al.
patent: 6078843 (2000-06-01), Shavit
patent: 6095426 (2000-08-01), Ahmed et al.
patent: 6145751 (2000-11-01), Ahmed
patent: 6220517 (2001-04-01), Ichishi et al.
patent: 6278962 (2001-08-01), Klimasauskas et al.
patent: 6330484 (2001-12-01), Qin
patent: 6600961 (2003-07-01), Liang et al.
Anderson, C. W., Hittle, D., Katz, A. and Kretchmar, R.,Synthesis of Reinforcement Learning, Neural Networks, and PI Control Applied to a Simulated Heating Coil. Journal of Artificial Intelligence in Engineering, vol. 11, #4, pp. 423-431, 1997. labeled as ATTACHMENT C “(cir 1998)” of priority U.S. Appl. No. 06/318,044 filed Sep. 8, 2001.
Anderson, C. W., Hittle, D., Katz, A. and Kretchmar, R.Reinforcement Learning, Neural Networks and PI Control Applied to a Heating Coil. Solving Engineering Problems with Neural Networks: Proceedings of the International Conference on Engineering Applications of Neural Networks (EANN-96), ed. by Bulsari, A.B., Kallio, S., and Tsaptsinos, D., Systems Engineering Association, PL 34, FIN-20111 Turki 11, Finland, pp. 135-142, 1996. labeled ATTACHMENT E of priority U.S. Appl. No. 06/318,044 filed Sep. 8, 2001.
Anderson, C. W., et al, “Synthesis of Reinforcement Learning, Neural Networks, and PI Control Applied to a Simulated Heating Coil.” circa1995; earlier version of 1stabove-listed ref. (1997); labeled ATTACHMENT D of priority U.S. Appl. No. 06/318,044 filed Sep. 8, 2001.
European Patent Specification EP 0 721 087 B1 (filed Dec. 19, 1995), Priority Jan. 6, 1995 US 369781 Ahmed, et al.).
Crites, R.H., and A. G. Barto, “Improving Elevator Performance Using Reinforcement Learning”, Touretzky, et al. eds., Advances in Neural Information Processing Systems 8. MIT Press, Cambridge MA, 1996.
Singh, S., and Dimitri Bertsekas, “Reinforcement Learning for Dynamic Channel Allocation in Cellular Telephone Systems.”.
Anderson, C. W., and W. T. Miller, “Challenging Control Problems,” MIT Press text appendix, pp. 474-509, 1990.
Anderson Charles
Anderson Michael
Delnero Christopher
Hittle Douglas C.
Young Peter M.
Chang Sunray
Colorado State University Research Foundation
Knight Anthony
Macheledt Bales & Heidmiller LLP
LandOfFree
Combined proportional plus integral (PI) and neural network... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Combined proportional plus integral (PI) and neural network..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Combined proportional plus integral (PI) and neural network... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3692991