Harvester with intelligent hybrid control system

• US 20030014171A1
• Filed: 07/16/2001
• Published: 01/16/2003
• Est. Priority Date: 07/16/2001
• Status: Active Grant

• Current Assignee: Deere & Company
• Original Assignee: Deere & Company
• Inventors: Ma, Xinghan, Beck, Folker, Mertins, Karl-Heinz Otto
• Granted Patent: US 6,553,300 B2
• Time in Patent Office: Days
• US Class Current: 701/50
• CPC Class Codes: A01D 41/127 Control or measuring arrangements specially adapted for combines
• CPC Class Codes: Y10S 706/904 Manufacturing or machine, e.g. agricultural machinery, machine tool

Abstract

A control system for a harvester or similar implement includes a supervisory controller, a set of low-level controllers and a neuro-fuzzy inference system. The supervisory controller employs human expert knowledge and fuzzy logic. The controller monitors the quality of the harvesting process, such as gain loss, dockage, grain damage and the like. Based on the measurements, setpoints for all critical functional elements of the implement are determined. The neuro-fuzzy inference system determines machine settings according to operating conditions and learns from harvester experience. The parameters of the neuro-fuzzy inference system are stored in on-board memory. The neuro-fuzzy system can be used for harvester set-up and as one of the knowledge sources for repeated adjustments during the harvest.

Claims

1. A control system for controlling an agricultural implement operable in varying operating conditions and having a plurality of adjustable output devices affecting implement operation, the control system comprising:

a plurality of actuators connected to the output devices;

feedback devices providing feedback signals indicative of the adjustments of the output devices;

a plurality of sensors providing input signals indicative of implement input condition and controlled variables;

an automatically adjustable controller connected to the actuators and responsive to the feedback signals and the input signals for automatically controlling the output devices; and

wherein the automatically adjustable controller includes a neuro-fuzzy inference system that learns and stores parameters from implement experience, the inference system thereby providing one of the knowledge sources to the control system.

2. The control system as set forth in claim 1 wherein the control system includes a closed-loop supervisory control system continually adjusting a preferred response to the signals.

3. The control system as set forth in claim 1 wherein the control system includes human expert knowledge, fuzzy logic and neural nets, and defines an intelligent hybrid control system.

4. The system as set forth in claim 3 wherein the signals from the feedback devices and the sensors includes imprecise data, wherein the intelligent hybrid control system works effectively with the imprecise data.

5. The system as set forth in claim 4 wherein the inference system is used for implement set-up so that set-up is responsive to prior implement performance.

6. The system as set forth in claim 4 wherein the implement includes initial input structure for inputting initial controller setting information to the processor.

7. The system as set forth in claim 6 wherein at least a portion of the initial controller setting information is based on the implement history.

8. The system as set forth in claim 6 wherein the initial input structure includes a neuro-fuzzy interface for inputting information on one or more of the following:

weather conditions;

crop properties;

harvest conditions;

acceptable crop loss; and

acceptable crop damage.

9. The system as set forth in claim 1 wherein the implement comprises a harvester and the output devices include threshing/separating and cleaning shoe systems, and wherein the adjustments to the preferred response include on-the-go adjustments of the preferred response of the threshing/separating and cleaning shoe systems.

10. The system as set forth in claim 1 wherein the feedback devices provide feedback information to the controller on conditions of crop, environment, machine and adjustments, wherein the controller is responsive to the feedback information to automatically adjust the preferred response in response to the conditions.

11. A control system for controlling an agricultural implement operable in varying operating conditions and having a plurality of adjustable output devices affecting implement output, the control system comprising:

a plurality of actuators connected to the output devices;

a plurality of sensors providing implement input condition signals;

control sensors for providing implement output performance information;

an automatically adjustable controller connected to the actuators and responsive to the input condition signals for automatically controlling the output devices; and

wherein the automatically adjustable controller comprises an adaptive neurofuzzy inference system, and a supervisory controller connected to the actuators and the neuro-fuzzy inference system, wherein the neuro-fuzzy inference system learns implement operation and adapts automatic control of the output devices to the learned implement operation to optimize implement output.

12. The control system as set forth in claim 11 wherein the implement comprises a combine, and the actuators include one or more of the following:

a rotor speed controller;

a concave clearance controller;

a fan speed controller;

a chaffer opening controller;

a sieve opening controller and an implement speed controller.

13. The control system as set forth in claim 11 wherein the control system includes human expert knowledge, fuzzy logic and neural nets, and defines an intelligent hybrid control system.

14. The system as set forth in claim 13 wherein the signals from the sensors includes one or more imprecise signals, wherein the intelligent hybrid control system works effectively with the imprecise signals.

15. The system as set forth in claim 11 wherein the controller remembers learned implement operation and utilizes the learned implement operation as a source of knowledge for implement set-up.

16. The system as set forth in claim 15 wherein the implement includes initial input structure for inputting initial implement setting information to the controller, at least a portion of the initial controller setting information based on the learned implement operation.

17. The system as set forth in claim 11 wherein the supervisory controller comprises a plurality of fuzzy controllers, a fuzzy controller selector, and a setpoint calculator.

18. The system as set forth in claim 12 wherein the combine includes initial input structure for inputting initial implement setting information to the processor, the initial input structure including means for inputting information on one or more of the following:

weather conditions;

crop properties;

harvest conditions;

acceptable crop loss; and

acceptable crop damage.

19. The system as set forth in claim 12 wherein the outputs include threshing/separating and cleaning shoe systems, and wherein the adjustments to the preferred response include on-the-go adjustments of the preferred response of the threshing/separating and cleaning shoe systems.

20. The system as set forth in claim 11 including feedback control sensors connected to the output devices and providing feedback signals to the controller indicative of changes in crop, fields, implement hardware, and performances of the adjustable controller.

21. A control system for controlling a combine operable in varying operating harvesting conditions and having a plurality of adjustable output devices affecting implement output, the control system comprising:

a plurality of actuators connected to the output devices;

feedback control sensors providing machine performance feedback signals;

a plurality of sensors providing implement input condition signals;

an automatically adjustable controller connected to the actuators and responsive to the input condition signals and the feedback signals for automatically controlling the output devices on-the-go during harvesting;

an operator interface connected to the automatically adjustable controller for entering adjustment information; and

wherein the automatically adjustable controller comprises an adaptive neurofuzzy inference system for receiving the signals and learning operating conditions, a supervisory controller connected to the actuators and the neuro-fuzzy inference system, the supervisory controller including a selector responsive to input condition signals and the adjustment information for facilitating determination of the control of the output devices, and fuzzy controller structure connected to the selector and providing quantitative information for output device control.

22. The control system as set forth in claim 21 wherein the supervisory controller learns sets of device settings to remember and directs the adaptive neurofuzzy inference system to incorporate the sets of device settings as initial settings and as a knowledge source for control.

23. The control system as set forth in claim 22 including an inquiry line connecting the supervisory controller and the adaptive neuro-fuzzy inference system, and wherein the supervisory controller sends an inquiring signal via the inquiry line asking for the settings for use as the initial settings and as a knowledge source for control.

24. The control system as set forth in claim 21 wherein the supervisory controller includes a setpoint calculator connected to the fuzzy controller and to the actuators.

25. The control system as set forth in claim 21 wherein the fuzzy controller structure comprises fuzzy controllers providing adjustment information for one or more controlled combine variables, including:

a) rotor speed;

b) concave clearance;

c) fan speed;

d) chaffer opening;

e) sieve opening; and

f) combine speed.

26. The control system as set forth in claim 25 including a setpoint calculator connected to the fuzzy controllers and determining adjustment setpoints for the controlled variables.

27. The control system as set forth in claim 26 wherein the setpoint calculator communicates with low level controllers to achieve combine output control, the low level controllers including:

a) a rotor speed controller;

b) a concave clearance controller;

c) a fan speed controller;

d) a chaffer opening controller;

e) a sieve opening controller; and

f) a combine speed controller.

28. The control system as set forth in claim 21 including feedback devices connected to the output devices and providing feedback signals to the automatically adjustable controller.

29. The control system as set forth in claim 28 wherein the controlled variables comprise grain loss, dockage and grain damage.