Fault isolation method and apparatus in artificial intelligence based air data systems

• US 7,257,470 B2
• Filed: 10/29/2004
• Issued: 08/14/2007
• Est. Priority Date: 10/29/2004
• Status: Active Grant

• Current Assignee: Rosemount Aerospace, Inc. (Rtx Corporation)
• Original Assignee: Rosemount Aerospace, Inc. (Rtx Corporation)
• Inventors: Cronin, Dennis James, Hongerholt, Derrick David
• Primary Examiner(s): BEAULIEU, YONEL
• Application Number:
  US10/977,442
• Publication Number:
  US 20070150122A1
• Time in Patent Office: 1,019 Days
• Field of Search: 701 1- 3, 701/6, 701/8, 701/29, 701/36, 701/40, 701/14, 702/138, 731/82
• US Class Current: 701/3
• CPC Class Codes: G01P 13/025 indicating air data, i.e. flight variables of an aircraft, e.g. angle of attack, side slip, shear, yaw

Abstract

A method providing fault isolation, in an air data system which uses artificial intelligence to generate an air data parameter, includes generating the air data parameter as a function of a plurality of measured values such as static pressures. Then, estimates of each of the plurality of measured values is generated as a function of the generated air data parameter. Each measured value can then be compared to its corresponding estimate to determine if a difference between the measured value and its corresponding estimate exceeds a threshold and therefore indicates a fault in a device which provides the measured value.

Claims

1. A method of providing fault isolation in an air data system which uses artificial intelligence to generate an air data parameter, the method comprising:

generating the air data parameter as a function of a plurality of measured values; and

generating estimates of each of the plurality of measured values as a function of the generated air data parameter; and

comparing each measured value to a corresponding estimate to determine if a difference between the measured value and the corresponding estimate exceeds a threshold and therefore indicates a fault in a device which provides the measured value, and thereby providing fault isolation in the air data system.

2. The method of claim 1, wherein generating the air data parameter comprises generating a global air data parameter for an air vehicle.

3. The method of claim 2, wherein generating the global air data parameter as a function of the plurality of measured values further comprises generating the global air data parameter as a function of a plurality of local static pressures.

4. The method of claim 2, wherein generating the global air data parameter as a function of the plurality of measured values further comprises generating the global air data parameter as a function of a measured value indicative of one of a control surface position, a control surface loading, a force, a vehicle mass at take-off, a vehicle mass balance, a remaining fuel mass, an engine thrust, satellite information, an altitude, an air temperature, a vehicle acceleration, a vehicle attitude, and a landing gear position.

5. The method of claim 1, wherein the step of generating the estimates of each of the plurality of measured values as a function of the generated air data parameter further comprises generating the estimate of each particular measured value as a function of the generated air data parameter and as a function of at least some of the others of the plurality of measured values.

6. The method of claim 5, wherein generating the air data parameter as a function of the plurality of measured values further comprises generating the air data parameter using a first artificial intelligence algorithm having the plurality of measured values as inputs.

7. The method of claim 6, wherein generating the estimates of each of the plurality of measured values further comprises generating each estimate using a further artificial intelligence algorithm having the generated air data parameter and at least some of the others of the plurality of measured values as inputs.

8. The method of claim 7, wherein the plurality of measured values includes N local static pressures provided by N static pressure sensing devices, wherein generating the air data parameter further comprises generating a global air data parameter using the first artificial intelligence algorithm having the N measured static pressures as inputs, and wherein generating the estimates of each of the N static pressures further comprises generating each estimate using the further artificial intelligence algorithm having the generated global air data parameter and the N−

1 others of the N static pressures as inputs.

9. The method of claim 8, wherein the step of generating the global air data parameter using the first artificial intelligence algorithm further comprises generating the global air data parameter using a first neural network, and wherein the step of generating each estimate using the further artificial intelligence algorithm further comprises generating each estimate using a further neural network.

10. The method of claim 5, wherein generating the air data parameter further comprises generating at least one of an angle of attack for an air vehicle, an angle of sideslip for the air vehicle, and a Mach number for the air vehicle.

11. The method of claim 5, and before the step of generating the air data parameter, further comprising obtaining the plurality of measured values in the form of a plurality of static pressures from a plurality of flush or semi-flush static sensing ports.

12. The method of claim 1, wherein the step of generating the air data parameter as a function of the plurality of measured values further comprises generating a plurality of air data parameters as a function of the plurality of measured values, and wherein generating the estimates of each of the plurality of measured values as a function of the generated air data parameter further comprises generating the estimates of each of the plurality of measured values as a function of the plurality of generated air data parameters.

13. An air data system comprising:

a plurality of static pressure sensing ports each providing one of a plurality of measured static pressures; and

air data computer circuitry configured to use artificial intelligence to generate an air data parameter as a function of the plurality of measured static pressures, and configured to use artificial intelligence to generate estimates of each of the plurality of measured static pressures as a function of the generated air data parameter.

14. The air data system of claim 13, wherein the air data computer circuitry is further configured to compare each measured static pressure to a corresponding estimate to determine if a difference between the measured static pressure and the corresponding estimate exceeds a threshold and therefore indicates a fault in the corresponding static pressure sensing port.

15. The air data system of claim 14, wherein the air data computer circuitry is configured to generate the estimates of each of the plurality of measured static pressures as a function of the generated air data parameter and as a function of at least some of the others of the plurality of measured static pressures.

16. The air data system of claim 15, wherein the plurality of static pressure sensing ports comprises N static pressure sensing ports each providing one of N measured static pressures, and wherein the air data computer circuitry is configured to generate the estimates of each of the N measured static pressures as a function of the generated air data parameter and as a function of the N−

1 others of the N static pressures.

17. The air data system of claim 14, wherein the air data computer circuitry is configured to generate a plurality of air data parameters as a function of the plurality of measured static pressures, and is configured to generate the estimates of each of the plurality of measured static pressures as a function of the plurality of generated air data parameters.

18. The air data system of claim 14, wherein the air data computer circuitry is configured to implement the artificial intelligence using neural networks.

19. The air data system of claim 14, wherein the air data computer circuitry is configured to implement the artificial intelligence using support vector machines.

20. The air data system of claim 14, wherein the air data parameter includes at least one of an angle of attack for an air vehicle, an angle of sideslip for the air vehicle, a Mach number for the air vehicle, a static pressure for the air vehicle, and a total pressure for the air vehicle.

21. The air data system of claim 14, wherein the plurality of static pressure sensing ports comprise a plurality of flush or semi-flush static sensing ports.