Fuzzy logic design generator using a neural network to generate

Details Fuzzy logic design generator using a neural network to generate Fuzzy logic design generator using a neural network to generate

1993-03-24

1996-11-26

Downs, Robert W.

395 3, 395 22, 395900, G06F 944, G06F 1580

Patent

active

055794394

ABSTRACT:
A fuzzy logic design generator for providing a fuzzy logic design for an intelligent controller in a plant control system includes an artificial neural network for generating fuzzy logic rules and membership functions data. These fuzzy logic rules and membership functions data can be stored for use in a fuzzy logic system for neural network based fuzzy antecedent processing, rule evaluation and defuzzification, thereby avoiding heuristics associated with conventional fuzzy logic algorithms. The neural network, used as a fuzzy rule generator to generate fuzzy logic rules and membership functions for the system's plant controller, is a multilayered feed-forward neural network based upon a modified version of a back-propagation neural network and learns the system behavior in accordance with input and output data and then maps the acquired knowledge into a new non-heuristic fuzzy logic system. Interlayer weights of the neural network are mapped into fuzzy logic rules and membership functions. Antecedent processing is performed according to a weighted product of the antecedents. One layer of the neural network is used for performing rule evaluation and defuzzification.

REFERENCES:
patent: 5168549 (1992-12-01), Takagi et al.
Keller, et al, "Fuzzy Logic Inference Neural Networks," SPIE vol. 1192 Intell. Robots and Comp. Vision, 1989, 582-591.
Cox, E. "Integrating Fuzzy Logic into Neural Nets," AI Expert, Jun. 1992, 43-47.
Horikawa, et al, "On Fuzzy Modeling Using Fuzzy Neural Networks with the Back-Propagation Algorithm," IEEE Trans. on Neural Networks, Sep. 1992, 801-806.
Cela, et al, "Towards A Neural Fuzzy Controller," Int'l. Conf. Syst., Man, and Cybernetics, 1992, 1277-1282.
Hamid R. Berenji, "Refinement of Approximate Reasoning-Based Controllers By Reinforcement Learning", Machine Learning: Proceedings of the Eighth International Workshop, Evanston, Illinois, Jun. 27-29, 1991 (5 pages).
Junhong Nie and D. A. Linkens, "Fuzzy Reasoning Implemented by Neural Networks", IEEE 1992, pp. II-702--II-707.
James J. Buckley, Yoichi Hayashi and Ernest Czogala, "On the Equivalence of Neural Networks and Fuzzy Expert Systems" IEEE 1992, pp. II-691--II-695.
D. E. Rumelhart, G. E. Hinton and R. J. Williams, "Learning Internal Representations By Error Propagation", 1986, Chapter 41, pp. 675-682.
Sun, et al., `Fuzzy Modeling Based on Generalized Neural Networks and Fuzzy Clustering Objective Functions`, IEEE Conference on Decision and Control, Dec. 1991, Brighton, vol. 3, pp. 2924-2929.
Kawamura, et al., `A Prototype of Neuro-Fuzzy Cooperation System`, IEEE International Conference on Fuzzy Systems, Mar. 8-12, 1992, San Diego, US, pp. 1275-1282.
E. Nishiguchi and K. Sueko, Japanese Kokai Patent Application No. 2-292602 (Dec. 1990), translated from Japanese; includes the Japanese version.

Affiliated with

Also associated with

Rating

Fuzzy logic design generator using a neural network to generate does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Fuzzy logic design generator using a neural network to generate , we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Fuzzy logic design generator using a neural network to generate will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1979966