Vehicle health management systems and methods

• US 9,725,187 B2
• Filed: 12/10/2014
• Issued: 08/08/2017
• Est. Priority Date: 07/02/2004
• Status: Active Grant

• Current Assignee: The Boeing Co.
• Original Assignee: The Boeing Co.
• Inventors: Swearingen, Kevin, Keller, Kirby J.
• Primary Examiner(s): Nguyen, Nga X
• Application Number:
  US14/566,558
• Publication Number:
  US 20160347470A1
• Time in Patent Office: 972 Days
• Field of Search: 701 3, 701 314, 701 339
• CPC Class Codes: B60R 16/0232 for measuring vehicle parameters and indicating critical, abnormal or dangerous conditions
• CPC Class Codes: B60R 16/0234 related to maintenance or repairing of vehicles
• CPC Class Codes: B64D 2045/0085 Devices for aircraft health monitoring, e.g. monitoring flutter or vibration
• CPC Class Codes: B64D 45/00 Aircraft indicators or protectors not otherwise provided for camouflage F41H3/00
• CPC Class Codes: G05D 1/0816 to ensure stability
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G07C 5/0808 Diagnosing performance data testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005
• CPC Class Codes: G07C 5/0816 Indicating performance data, e.g. occurrence of a malfunction
• CPC Class Codes: G07C 5/0841 Registering performance data recording measured values G01D; information storage G11B
• CPC Class Codes: G08G 5/0021 located in the aircraft

Abstract

A method includes receiving first vehicle data from a sensor on a vehicle at one or more processors executing a first software module. The method includes determining a risk value, a confidence value associated with whether the first vehicle data matches a validated vehicle state, and a benefit value associated with providing the first vehicle data to a second software module. The method includes calculating a health score associated with the first vehicle data based on the risk value, the confidence value, and the benefit value. The method includes, in response to the health score meeting a threshold value, determining whether the first vehicle data is internally consistent, externally consistent, and stable over time. The method further includes, in response to the first vehicle data being internally consistent, externally consistent, and stable over time, providing the first vehicle data to a vehicle flight control system.

Claims

1. A method comprising:

receiving first vehicle data from a sensor on a vehicle at one or more processors executing a first software module;

determining, by the first software module, one or more of a risk value associated with the first vehicle data, a confidence value associated with whether the first vehicle data matches a validated vehicle state, or a benefit value associated with providing the first vehicle data to a second software module comprising an evaluator and a filter;

calculating, by the evaluator, a health score associated with the first vehicle data based on the risk value, the confidence value, and the benefit value;

transferring the first vehicle data to the filter in response to the health score meeting a threshold value;

determining, by the filter, whether the first vehicle data is internally consistent;

determining, by the filter, whether the first vehicle data is externally consistent with second vehicle data from the sensor;

determining, by the filter, whether the first vehicle data is stable over time; and

providing the first vehicle data to a vehicle flight control system in response to determining that the first vehicle data is internally consistent, externally consistent, and stable over time.

2. The method of claim 1, wherein the risk value includes a first value associated with a risk resulting from an actuator failure relative to a control surface that affects a position of the vehicle.

3. The method of claim 1, wherein the confidence value is determined by comparing a current state of the vehicle with a state of the vehicle when the first software module is tested.

4. The method of claim 1, wherein determining whether the first vehicle data is externally consistent with the second vehicle data comprises:

receiving the second vehicle data from the sensor, wherein the first vehicle data has a higher fidelity than the second vehicle data; and

comparing the first vehicle data and the second vehicle data, wherein the first vehicle data is externally consistent if the first vehicle data corresponds to the second vehicle data.

5. The method of claim 1, wherein the first vehicle data indicates a position of an actuator, and wherein the second vehicle data includes an error message if the actuator is in an unexpected position.

6. The method of claim 1, wherein determining whether the first vehicle data is internally consistent comprises determining whether particular data fields of the first vehicle data are populated, wherein the first vehicle data is internally consistent if the particular data fields are populated.

7. The method of claim 6, further comprising modifying a vehicle flight control algorithm of the vehicle flight control system based on the first vehicle data.

8. The method of claim 1, further comprising verifying vehicle state information by performing a parameter identification test, the parameter identification test including:

adjusting an actuator command;

capturing actual vehicle response data;

comparing the actual vehicle response data to expected vehicle response data as predicted by a vehicle model; and

providing a correction to the vehicle flight control system based on a result from performing the parameter identification test.

18. The method of claim 1, further comprising, in response to determining that the first vehicle data is not externally consistent with the second vehicle data, filtering, by the filter, the first vehicle data to remove external inconsistencies based on the second vehicle data.

19. The method of claim 1, further comprising conditionally filtering, by the filter, the first vehicle data based on whether the first vehicle data is internally consistent, whether the first vehicle data is externally consistent, and whether the first vehicle data is stable over time.

20. The method of claim 1, further comprising verifying vehicle state information by performing a neural net correction test, the neural net correction test including providing correction factors to the vehicle flight control system to compensate for unexpected vehicle responses.

9. A non-transitory computer-readable medium comprising instructions which, when executed by one or more processors, cause the one or more processors to perform operations including:

receiving first vehicle data from a sensor on a vehicle at a first software module executable by the one or more processors;

determining one or more of a risk value associated with the first vehicle data, a confidence value associated with whether the first vehicle data matches a validated vehicle state, or a benefit value associated with providing the first vehicle data to a second software module comprising an evaluator and a filter;

calculating, by the evaluator, a health score associated with the first vehicle data based on the risk value, the confidence value, and the benefit value;

transferring the first vehicle data to the filter in response to the health score meeting a threshold value;

determining, by the filter, whether the first vehicle data is internally consistent;

determining, by the filter, whether the first vehicle data is externally consistent with second vehicle data from the sensor;

determining, by the filter, whether the first vehicle data is stable over time; and

providing the first vehicle data to a vehicle flight control system in response to determining that the first vehicle data is internally consistent, externally consistent, and stable over time.

10. The non-transitory computer-readable medium of claim 9, wherein the risk value includes a first value associated with a risk resulting from an actuator failure.

11. The non-transitory computer-readable medium of claim 9, wherein the confidence value is determined by comparing a current state of the vehicle with a state of the vehicle when the first software module is tested.

12. The non-transitory computer-readable medium of claim 9, wherein determining whether the first vehicle data is stable over time comprises comparing the first vehicle data to a rate of change threshold, wherein the first vehicle data is stable over time if the first vehicle data is less than or equal to the rate of change threshold.

13. The non-transitory computer-readable medium of claim 12, wherein the first vehicle data corresponds to data regarding an actuator of the vehicle, and wherein the second vehicle data corresponds to second data regarding an actuator of the vehicle.

14. A system comprising:

one or more processors;

a memory comprising instructions which, when executed by the one or more processors, cause the one or more processors to perform operations including;

receiving first vehicle data from a sensor on a vehicle at one or more processors executing a first software module;

determining one or more of a risk value associated with the first vehicle data by the one or more processors, a confidence value associated with whether the first vehicle data matches a validated vehicle state by the one or more processors, or a benefit value associated with providing the first vehicle data to a second software module comprising an evaluator and a filter;

calculating, by the evaluator, a health score associated with the first vehicle data based on the risk value, the confidence value, and the benefit value;

transferring the first vehicle data to the filter in response to the health score meeting a threshold value;

determining, by the filter, whether the first vehicle data is internally consistent;

determining, by the filter, whether the first vehicle data is externally consistent with second vehicle data from the sensor;

determining, by the filter, whether the first vehicle data is stable over time; and

providing the first vehicle data to a vehicle flight control system in response to determining that the first vehicle data is internally consistent, externally consistent, and stable over time.

15. The system of claim 14, wherein the risk value includes a first value associated with a risk resulting from an actuator failure.

16. The system of claim 14, wherein the confidence value is determined by comparing a current state of the vehicle with a state of the vehicle when the first software module is tested.

17. The system of claim 14, wherein the first vehicle data is high fidelity data from the sensor, and wherein the second vehicle data is low fidelity data from the sensor.