IP Library › Granted Patent US 11,385,632
Granted Patent B2
US 11,385,632 · App. 16/230,938 · Granted Jul 12, 2022

Sensor fault detection and identification using residual failure pattern recognition

Inventors: Brian T. Whitehead (Renton, WA); Sherwin C. Li (Edmonds, WA); Brian K. Rupnik (Lake Stevens, WA); Kioumars Najmabadi (Bellevue, WA)
Assignee: The Boeing Company
G05B23/0275G01R19/0038G05D1/0055
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,385,632
App. No.
16/230,938
Granted
Jul 12, 2022
Kind
B2
Abstract

Systems, methods, and apparatus for sensor fault detection and identification using residual failure pattern recognition are disclosed. In one or more embodiments, a method for sensor fault detection and identification for a vehicle comprises sensing, with sensors located on the vehicle, data. The method further comprises performing majority voting on the data for each of the types of data to generate a single voted value for each of the types of data. Also, the method comprises generating, for each of the types of data, estimated values by using some of the voted values. In addition, the method comprises generating residuals by comparing the estimated values to the voted values. Further, the method comprises analyzing a pattern of the residuals to determine which of the types of the data is erroneous to detect and identify a fault experienced by at least one of the sensors on the vehicle.

Claims (46)

1. A method for sensor fault detection and identification for a vehicle, the method comprising:

obtaining data from sensor measurements performed by sensors located on the vehicle, wherein the data comprises in number types of data, and in is an integer greater than two;

performing, by at least one processor, majority voting on the data for each of the types of data to generate a corresponding single voted value for each of the types of data;

generating, by the at least one processor, for each of the types of data, in number of corresponding estimated values of the respective different in types of data by using n number of the voted values, wherein n is equal to in minus one, and wherein for each of the types of data, the corresponding voted value is not used to generate the corresponding estimated values;

generating, by the at least one processor, residuals by comparing the estimated values to the voted values; and

analyzing, by the at least one processor, a pattern of the residuals to determine which, if any, of the types of the data is erroneous to detect and identify a fault experienced by at least one of the sensors on the vehicle, wherein the determining comprises:

generating, by the at least one processor, a visual and/or audio alert signal if any of the types of data is determined to be erroneous; and

generating a synthetic data signal indicating to use synthetic data instead of erroneous sensed data.

2. The method of claim 1 , wherein:

the residuals comprise a separate residual associated with each estimated value; and

the alert signal is generated based on determining, for at least one of the types of data, that the corresponding estimated values are associated with the residuals not exceeding, or less than, first thresholds, and the remaining estimated values are associated with the residuals exceeding, or greater than or equal to, second thresholds.

3. The method of claim 1 , wherein the sensors comprise at least two of a pitot tube, a pitot-static tube, a static port, a static tube, an angle of attack (AOA) resolver, or an accelerometer.

4. The method of claim 1 , wherein the types of data comprise at least three of total pressure, static pressure, angle of attack (AOA), or acceleration.

5. The method of claim 1 , wherein the vehicle is one of an airborne vehicle, a terrestrial vehicle, or a marine vehicle.

6. The method of claim 5 , wherein the airborne vehicle is one of an airplane, an unmanned aerial vehicle (UAV), or a helicopter.

7. The method of claim 1 , wherein the method further comprises removing, by the at least one processor, known corruption effects from at least some of the data.

8. The method of claim 7 , wherein the known corruption effects are removed by the at least one processor by utilizing at least one of dynamic pressure, Mach number, angle of attack (AOA), flap position, gear position, excess thrust, or ground effect terms.

9. The method of claim 1 , wherein the at least one processor generates the estimated values by utilizing at least one statistical filter.

10. The method of claim 9 , wherein the at least one statistical filter is an extended Kalman filter (EKF).

11. The method of claim 1 , wherein:

the residuals comprise a separate residual associated with each estimated value; and

the alert signal is generated based on determining, for at least one of the types of data, that:

for the estimated values corresponding to the types of data other than the at least one of the types of data, the estimated values of the at least one of the types of data are associated with the residuals which exceed, or are greater than or equal to, first thresholds; and

for the estimated values corresponding to the at least one of the types of data, the estimated values of the types of data other than the at least one of the types of data are associated with the residuals which do not exceed, or are less than, second thresholds.

12. A system for sensor fault detection and identification for a vehicle, the system comprising:

sensors, located on the vehicle and configured to perform measurements, wherein the system is configured to obtain data from the measurements,

wherein the data comprises m number types of data, and wherein m is an integer greater than two; and

at least one processor configured to:

perform majority voting on the data for each of the types of data to generate a corresponding single voted value for each of the types of data; and

generate for each of the types of data, m number of corresponding estimated values of the respective different m types of data by using n number of the voted values, wherein n is equal to m minus one;

wherein for each of the types of data, the corresponding voted value is not used to generate the corresponding estimated values,

wherein the at least one processor is configured to generate residuals by comparing the estimated values to the voted values and to analyze a pattern of the residuals to determine which, if any, of the types of the data is erroneous to detect and identify a fault experienced by at least one of the sensors on the vehicle,

wherein the at least one processor is further configured to generate a visual and/or audio alert signal if any of the types of data is determined to be erroneous, and

wherein the at least one processor is further configured to generate a synthetic data signal indicating whether to use synthetic data instead of erroneous sensed data.

13. The system of claim 12 , wherein the sensors comprise at least two of a pitot tube, a pitot-static tube, a static port, a static tube, an angle of attack (AOA) resolver, or an accelerometer.

14. The system of claim 12 , wherein the types of data comprise at least three of total pressure, static pressure, angle of attack (AOA), or acceleration.

15. The system of claim 12 , wherein the at least one processor is further configured to generate the estimated values by utilizing at least one statistical filter.

16. The system of claim 12 , wherein:

the residuals comprise a separate residual associated with each estimated value; and

the alert signal is configured to be generated based on determining, for at least one of the types of data, that:

for the estimated values corresponding to the types of data other than the at least one of the types of data, the estimated values of the at least one of the types of data are associated with the residuals which exceed, or are greater than or equal to, first thresholds; and

for the estimated values corresponding to the at least one of the types of data, the estimated values of the types of data other than the at least one of the types of data are associated with the residuals which do not exceed, or are less than, second thresholds.

17. The system of claim 12 , wherein the system further comprises at least one of:

at least one indicator light to generate a visual alert based on information contained in the alert signal;

at least one display to display a visual display alert based on the information contained in the alert signal; or

at least one speaker to generate an audio alert based on the information contained in the alert signal.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 21, 2018
From: WHITEHEAD, BRIAN T.; LI, SHERWIN C.; RUPNIK, BRIAN K.; NAJMABADI, KIOUMARS
To: THE BOEING COMPANY
Reel/Frame 047846/0746 →
Continuity (1)
Related Publication 20200201312A1 · Jun 25, 2020
Cited By (3)
US 12,441,483 US 12,539,982 US 12,673,785