Multi-function air data probes employing neural networks for determining local air data parameters

• US 20040122615A1
• Filed: 12/23/2002
• Published: 06/24/2004
• Est. Priority Date: 12/23/2002
• Status: Active Grant

• Current Assignee: Rosemount Aerospace, Inc. (Raytheon Technologies Corporation d/b/a RTX)
• Original Assignee: Rosemount Aerospace, Inc. (Raytheon Technologies Corporation d/b/a RTX)
• Inventors: Mack, Andrew P., Drutowski, Karl G., Cronin, Dennis J.
• Granted Patent: US 7,379,839 B2
• Time in Patent Office: Days
• US Class Current: 702/138
• CPC Class Codes: B64D 43/02 for indicating aircraft speed or stalling conditions
• 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

An air data sensing probe or MFP includes a barrel having multiple pressure sensing ports for sensing multiple pressures. Instrumentation coupled to the pressure sensing ports provides electrical signals related to the multiple pressures. A neural network, coupled to the instrumentation, receives as inputs the electrical signals related to the multiple pressures, and in response, the neural network provides, as an output, electrical signals indicative of at least one local air data parameter for the air data sensing probe.

Claims

1. An air data sensing probe comprising:

a plurality of pressure sensing ports sensing a plurality of pressures;

instrumentation coupled to the plurality of pressure sensing ports providing electrical signals related to the plurality of pressures; and

a neural network coupled to the instrumentation, the neural network configured to receive as inputs the electrical signals related to the plurality of pressures, and in response, the neural network configured to provide as an output electrical signals indicative of at least one local air data parameter for the air data sensing probe.

2. The air data sensing probe of claim 1, wherein the electrical signals related to the plurality of pressures are indicative of dimensional pressure values corresponding to separate ones of the sensed plurality of pressures.

3. The air data sensing probe of claim 2, wherein a number of dimensional pressure values that the neural network is configured to receive as inputs is at least three.

4. The air data sensing probe of claim 1, wherein the electrical signals related to the plurality of pressures are indicative of non-dimensional quantities obtained as a result of non-dimensionalization of at least some of the plurality of pressures.

5. The air data sensing probe of claim 4, wherein a number of non-dimensional quantities that the neural network is configured to receive as inputs is at least two.

6. The air data sensing probe of claim 1, wherein the plurality of pressure sensing ports include first and second angle of attack sensing ports for sensing first and second angle of attack pressures Pα

₁ and Pα

₂, respectively, and wherein the electrical signals related to the plurality of pressures include electrical signals indicative of the first and second angle of attack pressures Pα

₁ and Pα

₂.

7. The air data sensing probe of claim 6, wherein the plurality of sensing ports include a Pitot sensing port for sensing a Pitot pressure P_t, and wherein the electrical signals related to the plurality of pressures include electrical signals indicative of the Pitot pressure P_t.

8. The air data sensing probe of claim 7, wherein the neural network is configured to provide, as the output, electrical signals indicative of a local Mach number M₁ for the air data sensing probe.

9. The air data sensing probe of claim 7, wherein the neural network is configured to provide as the output electrical signals indicative of a local angle of attack α

₁ for the air data sensing probe.

10. The air data sensing probe of claim 7, wherein the neural network is configured to provide as the output electrical signals indicative of local static pressure P₁ for the air data sensing probe.

11. The air data sensing probe of claim 7, wherein the neural network is configured to provide as the output electrical signals indicative of a non-dimensional quantity related to local static pressure P_s1 for the air data sensing probe.

12. The air data sensing probe of claim 1, and further comprising a barrel having the plurality of pressure sensing ports.

13. The air data sensing probe of claim 1 wherein the neural network is a static neural network.

14. The air data sensing probe of claim 1 wherein the neural network is an adaptive neural network.

15. The air data sensing probe of claim 1 wherein the neural network is a cascade neural network.

16. The air data sensing probe of claim 1 wherein the neural network is a feed-forward network.

17. The air data sensing probe of claim 1 wherein the neural network is single neural network configured to provide electrical signals indicative of a plurality of local air data parameters for the air data sensing probe.

18. The air data sensing probe of claim 1 wherein the neural network comprises a plurality of single neural networks, each single neural network of the plurality of single neural networks configured to provide an electrical signal indicative of a different one of a plurality of local air data parameters for the air data sensing probe.

19. An air data sensing probe comprising:

pressure sensing means for sensing a plurality of pressures;

electrical signal generating means for providing electrical signals related to the plurality of pressures; and

neural network means coupled to the electrical signal generating means for receiving as inputs the electrical signals related to the plurality of pressures, and for providing in response electrical signals indicative of at least one local air data parameter for the air data sensing probe.

20. The air data sensing probe of claim 19, wherein the electrical signals generated by the electrical signal generating means are indicative of dimensional pressure values corresponding to separate ones of the sensed plurality of pressures.

21. The air data sensing probe of claim 19, wherein a number of dimensional pressure values that the neural network means receives as inputs is at least three.

22. The air data sensing probe of claim 19, wherein the electrical signals generated by the electrical signal generating means are indicative of non-dimensional quantities obtained as a result of non-dimensionalization of at least some of the plurality of pressures.

23. The air data sensing probe of claim 22, wherein a number of non-dimensional quantities that the neural network means receives as inputs is at least two.

24. The air data sensing probe of claim 19, wherein the pressure sensing means includes a barrel having a plurality of pressure sensing ports.