Systems and methods for detecting faults within operative sub-systems of a vehicle

• US 9,349,226 B2
• Filed: 10/09/2014
• Issued: 05/24/2016
• Est. Priority Date: 10/09/2014
• Status: Active Grant

• Current Assignee: The Boeing Co.
• Original Assignee: The Boeing Co.
• Inventors: Sundareswara, Rashmi N., Lu, Tsai-Ching, Betz, Franz David
• Primary Examiner(s): LANG, MICHAEL DEAN
• Application Number:
  US14/510,294
• Publication Number:
  US 20160104329A1
• Time in Patent Office: 593 Days
• US Class Current: 1/1
• CPC Class Codes: G01M 17/00 Testing of vehicles testing fluid tightness G01M3/00; testing elastic properties of bodies or chassis, e.g. torsion-testing, G01M5/00; testing alignment of vehicle headlight devices G01M11/06; testing of engines G01M15/00
• CPC Class Codes: G07C 5/006 Indicating maintenance
• CPC Class Codes: G07C 5/0816 Indicating performance data, e.g. occurrence of a malfunction

Abstract

A vehicle may include at least one operative sub-system that includes at least one sensor configured to output one or more sensor signals related to the at least one operative sub-system. A fault detection system may be in communication with the operative sub-system(s). The fault detection system is configured to generate at least one early warning signal based on the one more sensor signals, and determine at least one derivative of the early warning signal(s).

Claims

1. A vehicle comprising:

at least one operative sub-system, wherein the at least one operative sub-system includes at least one sensor configured to output one or more sensor signals related to the at least one operative sub-system; and

a fault detection system in communication with the at least one operative sub-system, wherein the fault detection system is configured to;

determine a first time window having a first step size;

generate at least one early warning signal with respect to the first time window based on the one more sensor signals;

determine a second time window size having a second step size; and

determine at least one derivative of the at least one early warning signal by subtracting a mean of a first product from a second product, wherein the first product is the first product of the at least one early warning signal and a first sum that includes the second step size and the second window, and wherein the second product is the second product of the at least one early warning signal and a second sum that includes the second window size.

2. The vehicle of claim 1, wherein the fault detection system is further configured to compare the at least one derivative to at least one fault threshold.

3. The vehicle of claim 2, wherein the fault detection system is further configured to detect at least one fault of the at least one operative sub-system in response to the at least one derivative crossing the at least one fault threshold.

4. The vehicle of claim 1, wherein the fault detection system comprises:

an early warning signal monitoring unit that is configured to generate the at least one early warning signal based on the one or more sensor signals; and

an early warning signal derivative-determining unit that is configured to determine the at least one derivative of the at least one early warning signal.

5. The vehicle of claim 4, wherein the fault detection system further comprises a fault alert unit that is configured to output a fault alert signal in response to the at least one derivative crossing at least one fault threshold.

6. The vehicle of claim 1, wherein the at least one derivative represents a rate of change of the at least one early warning signal with respect to time.

7. The vehicle of claim 1, wherein the at least one derivative correlates to a transition of the at least one operative sub-system from a stable operating state to an unstable operating state when the at least one derivative crosses a fault threshold.

8. The vehicle of claim 1, wherein the at least one operative sub-system comprises a plurality of operative sub-systems, and wherein the at least one sensor comprises a plurality of sensors.

9. The vehicle of claim 1, wherein the fault detection system is configured to generate the at least one early warning signal by determining one or both of a covariance matrix and a correlation matrix.

10. The vehicle of claim 1, wherein the first time window is at least four times the number of the at least one sensor.

11. A system comprising:

a fault detection system in communication with at least one sensor of at least one operative sub-system, wherein the fault detection system is configured to;

determine a first time window having a first step size;

generate at least one early warning signal with respect to the first time window based on one more sensor signals received from the at least one sensor;

determine a second time window size having a second step size; and

determine at least one derivative of the at least one early warning signal by subtracting a mean of a first product from a second product, wherein the first product is the first product of the at least one early warning signal and a first sum that includes the second step size and the second window, and wherein the second product is the second product of the at least one early warning signal and a second sum that includes the second window size.

12. The system of claim 11, wherein the fault detection system is further configured to compare the at least one derivative to at least one fault threshold, and detect at least one fault of the at least one operative sub-system in response to the at least one derivative crossing the at least one fault threshold.

13. The system of claim 11, wherein the fault detection system comprises:

an early warning signal monitoring unit that is configured to generate the at least one early warning signal based on the one or more sensor signals;

an early warning signal derivative-determining unit that is configured to determine the at least one derivative of the at least one early warning signal; and

a fault alert unit that is configured to output a fault alert signal in response to the at least one derivative crossing at least one fault threshold.

14. The system of claim 11, wherein the fault detection system is configured to generate the at least one early warning signal by determining one or both of a covariance matrix and a correlation matrix.

15. A method of detecting at least one fault within a vehicle, the method comprising:

receiving one or more sensor signals related to at least one operative sub-system of the vehicle;

generating at least one early warning signal based on the one more sensor signals, wherein the generating the at least one early warning signal comprises determining a first time window having a first step size, and generating the at least one early warning signal with respect to the first time window;

determining at least one derivative of the at least one early warning signal, wherein the determining the at least one derivative comprises determining a second time window size having a second step size, and determining the at least one derivative by subtracting a mean of a first product from a second product, wherein the first product is the first product of the at least one early warning signal and a first sum that includes the second step size and the second window, and wherein the second product is the second product of the at least one early warning signal and a second sum that includes the second window size;

comparing the at least one derivative to at least one fault threshold; and

detecting the at least one fault in response to the at least one derivative crossing the at least one fault threshold.

16. The method of claim 15, further comprising outputting a fault alert signal in response to the at least one derivative crossing at least one fault threshold.

17. The method of claim 15, wherein the detecting the at least one fault comprises correlating the at least one derivative with a transition of the at least one operative sub-system from a stable operating state to an unstable operating state when the at least one derivative crosses the at least one fault threshold.