System for intelligent control of a vehicle suspension based on soft computing

• US 6,463,371 B1
• Filed: 10/22/1998
• Issued: 10/08/2002
• 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., Hagiwara, Takahide
• Primary Examiner(s): Cuchlinski, Jr., William A.
• Assistant Examiner(s): MANCHO, RONNIE M
• Application Number:
  US09/177,169
• Time in Patent Office: 1,447 Days
• Field of Search: 701/36, 701/37, 701/39, 701/40, 701/42, 701/43, 701/44, 701/102
• US Class Current: 701/40
• CPC Class Codes: B60G 17/018 characterised by the use of a specific signal treatment or control method
• CPC Class Codes: B60G 17/019 characterised by the type of sensor or the arrangement thereof B60G17/01941 takes precedence
• CPC Class Codes: B60G 2600/09 Feedback signal
• CPC Class Codes: B60G 2600/124 Error signal
• CPC Class Codes: B60G 2600/14 Differentiating means, i.e. differential control
• CPC Class Codes: B60G 2600/16 Integrating means, i.e. integral control
• CPC Class Codes: B60G 2600/17 Proportional control, i.e. gain control
• CPC Class Codes: B60G 2600/18 Automatic control means
• CPC Class Codes: B60G 2600/90 other signal treatment means
• CPC Class Codes: B60G 2800/702 Improving accuracy of a sensor signal
• CPC Class Codes: B60G 2800/91 Suspension Control

Abstract

A reduced control system suitable for control of an active suspension system as a controlled plant is described. The reduced control system is configured to use a reduced sensor set for controlling the suspension 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 vehicle suspension system, comprising the steps of:

measuring first information from said suspension system by using a first plurality of sensors;

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

measuring second information from said suspension system 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 suspension control system, said second suspension control system providing a second control signal; and

configuring said second suspension control system using said first suspension control signal and said second suspension control signal such that said second suspension control system will provide acceptable control accuracy when used to control said vehicle suspension system without said first suspension control system.

2. The method of claim 1, wherein said step of configuring comprises generating a physical criteria and generating an information criteria.

7. The method of claim 2, wherein said step of configuring further comprises optimizing said second control system using an optimizer, wherein said optimizer uses a genetic algorithm having a fitness function, wherein a portion of said fitness function based on entropy.

8. 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.

9. 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.

10. The method of claim 1, wherein said second plurality of sensors comprises a vertical accelerometer.

12. The method of claim 1, wherein said second control signal is provided by a fuzzy neural network, wherein said fuzzy neural network is trained in an off-line mode.

3. A method for controlling a vehicle suspension system, comprising the steps of:

measuring first information from said suspension system by using first plurality of sensors;

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

measuring second information from said suspension system 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 suspension control system, said second suspension control system providing a second control signal; and

configuring said second suspension control system using said first suspension control signal and said second suspension control signal, wherein said step of configuring comprises generating a physical criteria and generating an information criteria, and wherein said physical criteria is calculated by an entropy model based on thermodynamic properties of said suspension.

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

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

6. The method of claim 5, wherein said thermodynamic model is based on suspension pitch angle and roll angle.

11. A method for controlling a vehicle suspension system, comprising the steps of:

measuring first information from said suspension system by using first plurality of sensors;

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

measuring second information from said suspension system 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 suspension control system, said second suspension control system providing a second control signal; and

configuring said second suspension control system using said first suspension control signal and said second suspension control signal, wherein said first plurality of sensors comprises a pitch angle sensor, a roll angle sensor, a position sensor, and an angle sensor.

13. A control apparatus configured to control a suspension, said apparatus comprising:

suspension control means for generating a suspension control signal based on information from a plurality of sensors measuring said suspension, said suspension control means trained by optimizer means for generating a training signal, said optimizer means generating said training signal using said control signal and an enhanced control signal provided by an enhanced control means, said enhanced control means and said suspension control means used concurrently while training said suspension control means, said suspension control means used without said enhanced control means to control said suspension after said suspension control means has been trained.

14. A control system adapted to control a suspension, comprising:

a first plurality of sensors configured to measure first information about said suspension, a first suspension controller configured to receive at least a portion of said first information, said first suspension controller trained in an off-line mode by using said first suspension controller to produce a first control signal and using a second suspension controller to produce a second control signal and developing a training signal from said first control signal and said second control signal, where said first suspension controller is trained to use at least a portion of said first information signal in order to reduce an entropy production of said suspension when said first suspension controller is used in an online mode without said second suspension controller.

15. The apparatus of claim 14, wherein said first suspension controller comprises a fuzzy neural network configured to be trained by a genetic analyzer having a first fitness function, said first fitness function configured to increase mutual information between said first control signal and said second control signal, said second control signal provided by said second controller configured to receive information from a second plurality of sensors, wherein said second plurality of sensors is greater than said first plurality of sensors.

16. The apparatus of claim 15, wherein said genetic analyzer further comprises a second fitness function configured to reduce entropy production rate of said suspension.

17. The apparatus of claim 16, wherein said genetic analyzer is configured to use said second fitness function to realize a node correction in said fuzzy neural network.

18. The apparatus of claim 15, wherein said first plurality of sensors comprises a vertical accelerometer.

19. A control system adapted to control a suspension, comprising:

a first plurality of sensors configured to measure first information about said suspension, a first suspension controller configured to receive at least a portion of said first information, said first suspension controller trained to produce a first control signal, where said first suspension controller is trained to use at least a portion of said first information signal in order to reduce an entropy production of said suspension, wherein said first suspension controller comprises a fuzzy neural network configured to be trained by a genetic analyzer having a first fitness function, said first fitness function configured to increase mutual information between said first control signal and a second control signal, said second control signal provided by a second controller configured to receive information from a second plurality of sensors, wherein said second plurality of sensors is greater than said first plurality of sensors, and wherein said second plurality of sensors comprises a pitch angle sensor and a roll angle sensor.

20. A control system adapted to control a suspension, comprising:

a first plurality of sensors configured to measure first information about said suspension, a first suspension controller configured to receive at least a portion of said first information, said first suspension controller trained to produce a first control signal, where said first suspension controller is trained to use at least a portion of said first information signal in order to reduce an entropy production of said suspension, wherein said first suspension controller comprises a fuzzy neural network configured to be trained by a genetic analyzer having a first fitness function, said first fitness function configured to increase mutual information between said first control signal and a second control signal, said second control signal provided by a second controller configured to receive information from a second plurality of sensors, wherein said second plurality of sensors is greater than said first plurality of sensors, and wherein said first control signal comprises a hydraulic valve control signal configured to control hydraulic fluid in a shock absorber.