SYSTEM AND METHOD FOR DETECTING VEHICLE SYSTEM FAULTS

• US 20160314632A1
• Filed: 04/24/2015
• Published: 10/27/2016
• Est. Priority Date: 04/24/2015
• Status: Active Grant

• Current Assignee: The Boeing Co.
• Original Assignee: The Boeing Co.
• Inventors: LU, Tsai-Ching, MARTIN, Charles E., MURPHY, Alice A., SLAUGHTER, Stephen C., WEZDENKO, Christopher R.
• Granted Patent: US 9,558,601 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: B64D 45/00 Aircraft indicators or protectors not otherwise provided for camouflage F41H3/00
• CPC Class Codes: B64F 5/60 Testing or inspecting aircraft components or systems
• CPC Class Codes: F02D 2041/1432 the system including a filter, e.g. a low pass or high pass filter
• CPC Class Codes: F02D 2041/288 for performing a transformation into the frequency domain, e.g. Fourier transformation
• CPC Class Codes: F02D 41/222 relating to the failure of sensors or parameter detection devices
• CPC Class Codes: G07C 5/02 Registering or indicating driving, working, idle, or waiting time only apparatus forming part of taximeters G07B13/00
• 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 5/085 using electronic data carriers
• CPC Class Codes: Y02T 10/40 Engine management systems

Abstract

A method for detecting vehicle system faults includes receiving, with a processor, a plurality of sensor signals from one or more sensors; thresholding, with the processor, the plurality of sensor signals for each respective sensor substantially in real time; and generating, with the processor, abnormal derivative frequency values for each of the plurality of thresholded sensor signals in real time and determining an operational status of at least each of the one or more sensors based on the abnormal derivative frequency values.

Claims

1. A method for detecting vehicle system faults, the method comprising:

receiving, with a processor, a plurality of sensor signals from one or more sensors;

thresholding, with the processor, the plurality of sensor signals for each respective sensor substantially in real time; and

generating, with the processor, abnormal derivative frequency values for each of the plurality of thresholded sensor signals in real time and determining an operational status of at least each of the one or more sensors based on the abnormal derivative frequency values.

2. The method of claim 1, wherein the operational status of at least each of the one or more sensors includes a measure of health of a system in which the sensor is located.

3. The method of claim 1, wherein the operational status of at least each of the one or more sensors includes a prognosis of a remaining useful life of a system in which the sensor is located.

4. The method of claim 1, further comprising determining a plurality of thresholding parameters that are derived from vehicle system constraints and empirical observations of previously recorded sensor data from the one or more sensors, where the plurality of thresholding parameters effect thresholding the plurality of sensor signals for each respective sensor.

5. The method of claim 1, wherein the processor determines the operational status of at least each of the one or more sensors in real-time.

6. The method of claim 1, wherein the plurality of signals correspond to data acquisition and data communication in an aerospace, marine or land-based vehicle system with respect to an operational state of the aerospace, marine or land-based vehicle system.

7. The method of claim 1, wherein determining an operational status of at least each of the one or more sensors includes

generating a time series of abnormal derivative frequency values;

and

transforming the time series of abnormal derivative frequency values into abnormal derivative frequency vectors by time shifting, with overlapping time steps, a time window having a predetermined size across the time series of abnormal derivative frequency values.

8. The method of claim 1, further comprising:

classifying the abnormal derivative frequency values for each of the plurality of thresholded sensor signals as being normal or abnormal; and

predicting, based on classified abnormal derivative frequency values, an impending fault in a component of a system in which a respective one of the one or more sensors is located.

9. The method of claim 8, further comprising thresholding, with the processor, the abnormal derivative frequency values for each of the plurality of thresholded sensor signals to effect classification of a respective abnormal derivative frequency value.

10. A fault detection system comprising:

a processor configured to receive a plurality of sensor signals from one or more sensors;

a thresholding module connected to the processor and configured to threshold the plurality of sensor signals for each respective sensor in substantially real time; and

an abnormal derivative computation module connected to the processor and configured to determine abnormal derivative frequency values for each of the plurality of thresholded sensor signals in substantially real time,

wherein the processor is configured to determine an operational status of at least each of the one or more sensors based on the abnormal derivative frequency values.

11. The fault detection system of claim 10, wherein the operational status of at least each of the one or more sensors includes a measure of health of a system in which the sensor is located.

12. The fault detection system of claim 10, wherein the operational status of at least each of the one or more sensors includes a prognosis of a remaining useful life of a system in which the sensor is located.

13. The fault detection system of claim 10, further comprising a threshold module connected to the processor and configured to determine a plurality of thresholding parameters that are derived from vehicle system constraints and empirical observations of previously recorded sensor data from the one or more sensors, where the plurality of thresholding parameters effect thresholding the plurality of sensor signals for each respective sensor.

14. The fault detection system of claim 10, wherein the processor is configured to determine the operational status of at least each of the one or more sensors in real-time.

15. The fault detection system of claim 10, wherein the plurality of signals correspond to data acquisition and data communication in an aerospace, marine or land-based vehicle system with respect to an operational state of the aerospace, marine or land-based vehicle system.

16. The fault detection system of claim 10, further comprising an abnormal derivative vectoring module configured to

generate a time series of abnormal derivative frequency values;

and

transform the time series of abnormal derivative frequency values into abnormal derivative frequency vectors by time shifting, with overlapping time steps, a time window having a predetermined size across the time series of abnormal derivative frequency values.

17. The fault detection system of claim 10, further comprising a classification module connected to the processor and configured to classify the abnormal derivative frequency values for each of the plurality of thresholded sensor signals as being normal or abnormal,

wherein the processor is configured to predict, based on classified abnormal derivative frequency values, an impending fault in a component of a system in which a respective one of the one or more sensors is located.

18. The fault detection system of claim 17, wherein the processor is configured to threshold the abnormal derivative frequency values for each of the plurality of thresholded sensor signals to effect classification of a respective abnormal derivative frequency value.

19. A fault detection system comprising:

a plurality of sensors disposed in one or more vehicle systems of an aerospace, marine or land-based vehicle; and

a processor configured to receive a plurality of sensor signals from the plurality of sensors, the processor being configured to

threshold the plurality of sensor signals for each respective sensor in substantially real time,

determine abnormal derivative frequency values for each of the plurality of thresholded sensor signals in substantially real time, and

determine an operational status of at least each of the one or more vehicle systems based on the abnormal derivative frequency values.

20. The fault detection system of claim 19, wherein the processor is further configured to

generate a time series of abnormal derivative frequency values;

transform the time series of abnormal derivative frequency values into abnormal derivative frequency vectors by time shifting, with overlapping time steps, a time window having a predetermined size across the time series of abnormal derivative frequency values; and

classify the abnormal derivative frequency values for each of the plurality of thresholded sensor signals as being normal or abnormal,

wherein the processor is configured to predict, based on classified abnormal derivative frequency values, an impending fault in a component of the one or more vehicle systems in which a respective one of the one or more sensors is located.