System for intelligent control based on soft computing

• US 6,415,272 B1
• Filed: 10/22/1998
• Issued: 07/02/2002
• Est. Priority Date: 10/22/1998
• Status: Expired due to Fees

• Current Assignee: Yamaha Hatsudoki Kabushiki Kaisha (Yamaha Corporation), Yamaha Motor Company Limited (Yamaha Corporation)
• Original Assignee: Yamaha Hatsudoki Kabushiki Kaisha (Yamaha Corporation)
• Inventors: Ulyanov, Sergei V.
• Primary Examiner(s): Davis, George B.
• Application Number:
  US09/177,466
• Time in Patent Office: 1,349 Days
• Field of Search: 706/10, 706/2, 706/13, 706/903
• US Class Current: 706/2
• CPC Class Codes: G05B 13/0265 the criterion being a learning criterion
• CPC Class Codes: G05B 13/0285 using neural networks and fuzzy logic
• CPC Class Codes: Y10S 706/903 Control

Abstract

A reduced control system suitable for control of a nonlinear or unstable plant is described. The reduced control system is configured to use a reduced sensor set for controlling the plant without significant loss of control quality (accuracy) as compared to an optimal control system with an optimum sensor set. The control system calculates the information content provided by the reduced sensor set as compared to the information content provided by the optimum set. The control system also calculates the difference between the entropy production rate of the plant and the entropy production rate of the controller. A genetic optimizer is used to tune a fuzzy neural network in the reduced controller. A fitness function for the genetic optimizer provides optimum control accuracy in the reduced control system by minimizing the difference in entropy production while maximizing the sensor information content.

Claims

1. A method for controlling a plant, comprising the steps of:

measuring first information from a plant by using a first plurality of sensors;

providing said first information to a first control system, said first control system configured to provide a desired accuracy for said plant, said first control system providing a first control signal;

measuring second information from said plant by using a second plurality of sensors, where said second plurality of sensors comprises fewer sensors than said first plurality of sensors;

providing said second information to a second control system, said second control system providing a second control signal; and

configuring said second control system using a training signal, said training signal calculated from said first control signal and said second control signal to configure said second control system to reduce an entropy production of said plant.

9. The method of claim 1, further comprising the steps of:

analyzing one or more nonlinear operation characteristics of said plant by using a Lyapunov function.

10. The method of claim 1, further comprising the steps of:

evolving a control rule for a fuzzy neural network by using a genetic algorithm, said genetic algorithm using fitness function that reduces an entropy production of said plant and increases an information criteria for accuracy and reliability.

2. A method for controlling a plant, comprising the steps of:

measuring first information from a plant by using a first plurality of sensors;

providing said first information to a first control system, said first control system configured to provide a desired accuracy for said plant, said first control system providing a first control signal;

measuring second information from said plant by using a second plurality of sensors, where said second plurality of sensors comprises fewer sensors than said first plurality of sensors;

providing said second information to a second control system, said second control system providing a second control signal; and

configuring said second control system using said first control signal and said second control signal, wherein said step of configuring comprises generating an entropy-based physical criteria and generating an information criteria.

3. The method of claim 2, wherein said physical criteria is calculated by an entropy model.

4. The method of claim 3, wherein said physical criteria is calculated by an entropy model using data from said second control system.

5. The method of claim 4, wherein said second control system is adapted to reduce an entropy production in said plant.

6. The method of claim 2, wherein said optimizer uses a generic algorithm having a fitness function, said fitness function based on entropy.

7. The method of claim 2, wherein said step of configuring further comprises providing said physical criteria and said information criteria to a genetic algorithm having a fitness function, said fitness function based on entropy.

8. The method of claim 2, wherein said step of configuring further comprises providing a training signal to a fuzzy neural network in said second control system.