Method of feed-forward control using control logic with anticipatory learning control

• US 6,415,273 B1
• Filed: 02/12/1999
• Issued: 07/02/2002
• Est. Priority Date: 02/12/1998
• Status: Expired due to Fees

• Current Assignee: Yamaha Hatsudoki Kabushiki Kaisha (Yamaha Corporation)
• Original Assignee: Yamaha Hatsudoki Kabushiki Kaisha (Yamaha Corporation)
• Inventors: Fujime, Yoko
• Primary Examiner(s): Davis, George B.
• Application Number:
  US09/249,194
• Time in Patent Office: 1,236 Days
• Field of Search: 706/16, 706/48, 706/903, 706/23
• US Class Current: 706/16
• CPC Class Codes: F02D 2041/1418 Several control loops, either as alternatives or simultaneous
• CPC Class Codes: F02D 2041/1433 using a model or simulation of the system
• CPC Class Codes: F02D 2200/0402 the parameter being determined by using a model of the engine intake or its components
• CPC Class Codes: F02D 2200/0411 Volumetric efficiency
• CPC Class Codes: F02D 2200/0614 Actual fuel mass or fuel injection amount
• CPC Class Codes: F02D 41/1404 Fuzzy logic control
• CPC Class Codes: F02D 41/1405 Neural network control
• CPC Class Codes: F02D 41/1456 with sensor output signal being linear or quasi-linear with the concentration of oxygen
• CPC Class Codes: F02D 41/2454 Learning of the air-fuel ratio control
• CPC Class Codes: F02D 41/2477 characterised by the method used for learning
• CPC Class Codes: F02D 41/248 using a plurality of learned values
• CPC Class Codes: G05B 13/0285 using neural networks and fuzzy logic
• CPC Class Codes: Y10S 706/903 Control

Abstract

A machine control system for controlling an unstable or transition running condition of a machine which is operable by a causative signal and the performance of which is indicatable by an indicative signal. The control system includes: (a) a model-based control unit for outputting an estimated value of a causative signal when receiving an indicative signal, which model-based control unit undergoes learning based on teacher data; (b) a feedback control unit for providing first teacher data to the model-control unit upon receiving feedback information from the machine; and (c) an anticipatory control unit for providing second teacher data to the model-based control unit. The anticipatory control unit includes: (i) a deviation detection program programmed to determine whether the running condition of the machine deviates from a predetermined stable running condition; and (ii) a compensation formulation program programmed to formulate anticipatory compensations to compensate for deviation of the machine from the predetermined stable running condition based on feedback information received from the machine, output from which program is provided to the model-based control unit as second teacher data.

Claims

1. A machine control system for controlling performance of a machine which is operable by a causative signal and the performance of which is indicatable by an indicative signal, said control system comprising:

a model-based control unit for outputting an estimated value of a causative signal when receiving an indicative signal, wherein the input-output relationship of the model-based control unit is the inverse of that of the machine, said model-based control unit receiving a target value of the indicative signal and being provided with a learning function which modifies output from the model-based control unit based on teacher data;

a feedback control unit for providing first teacher data to the model-control unit, said feedback control unit receiving feedback information of an actual value of the indicative signal from the machine, and providing the feedback information to the model-based control unit as first teacher data, wherein the model-based control unit undergoes leaning using the first teacher data to modify its output of the causative signal, said feedback control unit being inactivated if the running condition of the machine deviates from a stable running condition; and

an anticipatory control unit for providing second teacher data to the model-based control unit, comprising;

a deviation detection program programmed to determine whether the running condition of the machine deviates from a predetermined stable running condition, output from which program is provided to the feedback control unit; and

a compensation formulation program programmed to formulate anticipatory compensations to compensate for deviation of the machine from the predetermined stable running condition based on feedback information received from the machine, output from which program is provided to the model-based control unit as second teacher data, wherein the model-based control unit undergoes learning using the second teacher data to modify output of the causative signal.

2. The machine control system according to claim 1, wherein the anticipatory control unit provides the second teacher data to the model-based control unit when the feedback control unit is inactivated.

3. The machine control system according to claim 1, wherein the feedback information received by the anticipatory control unit is previous feedback control patterns.

4. The machine control system according to claim 1, wherein the feedback information received by the anticipatory control unit is information from the feedback control unit when the feedback control unit is inactivated.

5. The machine control system according to claim 1, wherein the model-based control unit comprises:

a forward model or map defining and simulating the input-output relationship of the machine, wherein the model or map outputs an estimated value of the indicative signal when receiving a causative signal, said forward model provided with the learning function; and

a feedback controller for outputting the estimated value of the causative signal when receiving and comparing the target value of the indicative signal and the estimated value of the indicative signal from the forward model or map, output from said feedback controller being provided to the forward model unit;

wherein the model-based control unit outputs the estimated value of the causative signal when receiving the target value of the indicative signal.

6. The machine control system according to claim 1, wherein the learning function provided in the model-based control unit is a fuzzy neural network, neural network, or cerebellar model arithmetic computer (CMAC).

7. A method for controlling an unstable running condition of a machine which is operable by a causative signal and the performance of which is indicatable by an indicative signal, said method being achieved using a control system comprising:

(a) a mode-based control unit for outputting an estimated value of a causative signal when receiving an indicative signal, wherein the input-output relationship of the model-based control unit is the inverse of that of the machine, said model-based control unit receiving a target value of the indicative signal and being provided with a learning function which modifies output from the model-based control unit based on teacher data; and

(b) a feedback control unit for providing first teacher data to the model-control unit, said feedback control unit receiving feedback information of an actual value of the indicative signal from the machine, and providing the feedback information to the model-based control unit as first teacher data, said method comprising the steps of;

(a) providing the feedback information as first teacher data to the model-control unit from the feedback control unit, wherein the model-based control unit undergoes learning using the first teacher data to modify its output of the causative signal;

(b) determining whether the running condition of the machine deviates from a predetermined stable running condition;

(c) inactivating the feedback control unit when the running condition of the machine deviates from a stable running condition;

(d) formulating anticipatory compensations to compensate for deviation of the machine from the predetermined stable running condition based on feedback information received from the machine; and

(e) providing the anticipatory compensations to the model-based control unit as second teacher data, wherein the model-based control unit undergoes learning using the second teacher data to modify output of the causative signal.

8. The method according to claim 7, wherein the feedback information received in step (d) is previous feedback control patterns.

9. The method according to claim 8, wherein the previous feedback control patterns are stored in a memory, and based on the previous feedback control patterns, the second teacher data are increased or decreased in a direction compensating for the deviation of the machine.

10. The method according to claim 7, wherein the feedback information received in step (d) is information from the feedback control unit when the feedback control unit is inactivated.

11. The method according to claim 10, wherein the information obtained when the feedback control unit is inactivated is the duration of the stable running condition of the machine or the sum of the compensations by the first teacher data from when the feedback control unit is activated.

12. The method according to claim 7, wherein the model-based control unit comprises:

a forward model or map defining and simulating the input-output relationship of the machine, wherein the model or map outputs an estimated value of the indicative signal when receiving a causative signal, said forward model provided with the learning function; and

a feedback controller for outputting the estimated value of the causative signal when receiving and comparing the target value of the indicative signal and the estimated value of the indicative signal from the forward model or map, output from said feedback controller being provided to the forward model unit;

wherein the model-based control unit outputs the estimated value of the causative signal when receiving the target value of the indicative signal.