Method, system, and computer program product for tactile cueing flight control

• US 6,735,500 B2
• Filed: 05/06/2003
• Issued: 05/11/2004
• Est. Priority Date: 06/10/2002
• Status: Active Grant

• Current Assignee: The Boeing Co.
• Original Assignee: The Boeing Co.
• Inventors: Miller, David G., Nicholas, Jeffrey S.
• Primary Examiner(s): ARTHUR JEANGLAUDE, GERTRUDE
• Application Number:
  US10/430,543
• Publication Number:
  US 20040010354A1
• Time in Patent Office: 371 Days
• Field of Search: 701/1, 701/3, 701/13, 701/14, 244/17.13, 244/75.R, 244/158.R, 244/184
• US Class Current: 701/3
• CPC Class Codes: B64C 13/503 Fly-by-Wire
• CPC Class Codes: B64C 27/56 characterised by the control initiating means, e.g. manually actuated

Abstract

A system, a method, and a computer program product for determining tactile cueing of a flight control input apparatus includes an interface for receiving observed parameters relating to the flight envelope of an aircraft. Upstream processing elements receive the observed states, convert dimensional aircraft state parameters into nondimensional aircraft state parameters, and provide the data to neural networks. The neural networks receive combinations of observed parameters and nondimensional aircraft state parameters and predict flight envelope limiting parameters. The neural networks are trained to predict the limiting parameters. A downstream processing element determines the most limiting flight envelope limiting parameter provided from the neural networks, therefore providing a tactile cueing position for a flight control input apparatus.

Claims

1. A flight control system for determining tactile cueing of a flight input apparatus, comprising:

an interface for receiving observed parameters relating to the flight envelope of an aircraft including observed parameters related to an aircraft state;

at least one upstream processing element for converting dimensional aircraft state parameters into nondimensional aircraft state parameters;

a plurality of predictive neural networks for receiving combinations of observed parameters and nondimensional aircraft state parameters and predicting flight envelope limiting parameters based thereupon, and

at least one downstream processing element for determining the most limiting flight envelope limiting parameter, and determining a tactile cueing position for the flight control input apparatus based on the most limiting parameter.

2. A flight control system according to claim 1, wherein the plurality of predictive neural networks further comprises neural networks providing flight envelope limiting parameters that are nondimensional.

3. A flight control system according to claim 1, wherein the plurality of predictive neural networks comprises polynomial neural networks.

4. A flight control system according to claim 1, wherein the plurality of predictive neural networks comprises hyperbolic tangent neural networks.

5. A flight control system according to claim 1, wherein the plurality of predictive neural networks are trained based on a set of trim data.

6. A flight control system according to claim 1, wherein at least one of the upstream processing elements converts dimensional aircraft state parameters into nondimensional aircraft state parameters selected from the group consisting of inflow ratio, advance ratio, thrust coefficient, torque coefficient, rotor hub roll rate, and rotor hub pitch rate.

7. A flight control system according to claim 6, wherein at least one of the upstream processing elements comprises an estimating neural network.

8. A flight control system according to claim 7, wherein the estimating neural network comprises an estimated rotor torque coefficient neural network and an estimated rotor thrust coefficient neural network.

9. A flight control system according to claim 1, wherein at least some of the plurality of predictive neural networks comprise predictive neural networks selected from the group consisting of an inflow ratio prediction neural network, a rotor thrust coefficient prediction neural network, a rotor torque coefficient prediction neural network, and an engine torque prediction neural network.

10. A method of determining tactile cueing for a flight control input apparatus, comprising:

receiving observed parameters relating to the flight envelope of an aircraft including observed parameters relating to an aircraft state;

converting at least some observed parameters relating to an aircraft state into nondimensional aircraft state parameters;

predicting flight envelope limiting parameters based on the observed parameters and nondimensional aircraft state parameters;

determining the most limiting flight envelope limiting parameter; and

determining a tactile cueing position for the flight control input apparatus based on the most limiting parameter.

11. The method according to claim 10, wherein the step of receiving observed parameters further comprises receiving aircraft state parameters selected from the group consisting of roll rate, pitch rate, rotor tip mach number, rotor rotational speed, collective pitch, and cyclic pitch.

12. The method according to claim 10, wherein the step of receiving observed parameters further comprises receiving observed parameters relating to engine state parameters selected from the group consisting of turbine gas temperature, engine transmission torque, and gas generator speed.

13. The method according to claim 10, wherein the step of receiving observed parameters further comprises receiving observed parameters relating to environmental parameters selected from the group consisting of ambient temperature and air density.

14. The method according to claim 10, wherein the step of receiving observed parameters further comprises receiving observed parameters relating to aircraft state selected from the group consisting of body-axis forward speed, body-axis sideward speed, and body-axis vertical speed.

15. The method according to claim 10, wherein the step of predicting flight envelope limiting parameters further comprises predicting flight envelope limiting parameters that are nondimensional.

16. The method according to claim 10, wherein the step of converting at least some observed parameters further comprises converting dimensional aircraft state parameters into nondimensional aircraft state parameters selected from the group consisting of inflow ratio, advance ratio, thrust coefficient, torque coefficient, rotor hub roll rate, and rotor hub pitch rate.

17. The method according to claim 10, wherein the step of predicting flight envelope limiting parameters further comprises predicting parameters selected from the group consisting of inflow ratio, rotor thrust coefficient, rotor torque coefficient, and engine torque.

18. A computer program product for determining tactile cueing limits for a flight control input apparatus, the computer program product comprising a computer-readable storage medium and computer-readable code portions stored thereon, the computer-readable codes portions comprising:

a first executable portion adapted to convert dimensional aircraft state parameters into nondimensional aircraft state parameters;

a plurality of second executable portions for implementing predictive neural networks for receiving combinations of at least one observed parameter and dimensional aircraft state parameters, and predicting flight envelope limiting parameters based thereupon;

a third executable portion capable of determining the most limiting flight envelope limiting parameter; and

a fourth executable portion capable of determining a tactile cueing position for the flight control input apparatus based on the most limiting parameter.

19. The computer program product according to claim 18, wherein at least some of the plurality of second executable portions implement predictive neural networks that predict flight envelope limiting parameters based on aircraft state parameters selected from the group consisting of roll rate, pitch rate, rotor tip mach number, rotor rotational speed, collective pitch, and cyclic pitch.

20. The computer program product according to claim 18, wherein at least some of the plurality of second executable portions implement predictive neural networks that predict flight envelope limiting parameters based on engine state parameters selected from the group consisting of turbine gas temperature and gas generator speed.

21. The computer program product according to claim 18, wherein at least some of the plurality of second executable portions implement predictive neural networks that predict flight envelope limiting parameters based on environmental parameters selected from the group consisting of ambient temperature and air density.

22. The computer program product according to claim 18, wherein at least some of the plurality of second executable portions implement predictive neural networks that predict flight envelope limiting parameters based on body-axis speed selected from the group consisting of forward speed, sideward speed, and vertical speed.

23. The computer program product according to claim 18, wherein at least some of the plurality of second executable portions implement predictive neural networks that provide flight envelope limiting parameters that are nondimensional.

24. The computer program product according to claim 18, wherein at least some of the plurality of second executable portions implement predictive neural networks that comprise polynomial neural networks.

25. The computer program product according to claim 18, wherein at least some of the plurality of second executable portions implement predictive neural networks that comprise hyperbolic tangent neural networks.

26. The computer program product according to claim 18, wherein at least some of the plurality of second executable portions implement predictive neural networks that are trained based on a set of trim data.

27. The computer program product according to claim 18, wherein the first executable portion is further adapted to convert dimensional aircraft state parameters into nondimensional aircraft state parameters selected from the group consisting of inflow ratio, advance ratio, thrust coefficient, torque coefficient, rotor hub roll rate, and rotor hub pitch rate.

28. The computer program product according to claim 27, wherein the first executable portion implements estimating neural networks.

29. The computer program product according to claim 28, wherein the first executable portion implements the estimating neural networks that predict a rotor torque coefficient and a rotor thrust coefficient.

30. The computer program product according to claim 18, wherein at least some of the plurality of second executable portions implement predictive neural networks selected from the group consisting of an induced flow prediction neural network, a rotor thrust coefficient prediction neural network, a rotor torque coefficient prediction neural network, and an engine torque prediction neural network.