Rotorcraft structural fault-detection and isolation using virtual monitoring of loads

Patent metadata

Field	Value
Publication number	US-10460536-B2
Application number	US-201615748001-A
Country	US
Kind code	B2
Filing date	Jul 27, 2016
Priority date	Aug 4, 2015
Publication date	Oct 29, 2019
Grant date	Oct 29, 2019

Abstract

A system, method, and computer program for detecting and isolating structural faults is provided. To detect and isolate structural faults, a plurality of sensed features that corresponds to sensor data from the monitoring sub-system and a plurality of estimated features that corresponds to the plurality of sensed features can be generated. Further, the plurality of sensed features and the plurality of estimated features can be compared to produce a plurality of residuals. From the plurality of residuals, at least one structural fault within the vehicle are determined and isolated for further use of maintenance decision support.

First claim

The invention claimed is:

1. A method for detection and isolation of at least one structural fault, comprising:
generating, by a computing device communicatively coupled to a monitoring sub-system that is physically coupled to a vehicle and communicatively coupled to one or more sensors, a plurality of sensed features that correspond to sensor data from the monitoring sub-system;
generating based on one or more models, by the computing device, a plurality of estimated features that correspond to the plurality of sensed features;
comparing, by the computing device, the plurality of sensed features and the plurality of estimated features to produce a plurality of residuals, a number of the plurality of residuals being determined based on a number of the plurality sensed features and a number of the one or more models;
determining, by the computing device, from the plurality of residuals whether the at least one structural fault exists within the vehicle; and
isolating, by the computing device, the at least one structural fault from the plurality of residuals,
wherein the generation of the plurality of sensed features is based on at least one of the one or more sensors generating multiple sensed features.

2. The method of claim 1 , further comprising:
receiving, by the computing device from the monitoring sub-system, the sensor data, the sensor data being detected by at least one sensor of the monitoring sub-system, the at least one sensor being physically coupled to the vehicle.

3. The method of claim 1 , wherein the generating of the plurality of estimated features based on the one or more models further comprises:
receiving by the computing device stored sensor information;
processing the stored sensor information in accordance with the model to produce estimated data; and
processing, via signal processing techniques, the estimated data to produce the plurality of estimated features.

4. The method of claim 1 , wherein the sensor data includes low-frequency state parametric data or high frequency state parametric data.

5. The method of claim 1 , wherein each residual includes a magnitude and polarity that are utilized with respect to a threshold range during the determining of whether the at least one structural fault exists.

6. The method of claim 1 , wherein the computing device is a ground based device.

7. The method of claim 1 , wherein the vehicle is an aircraft.

8. The method of claim 7 , wherein the computing device is integral to the aircraft.

9. A structural diagnostic system, comprising a processor and a memory having program instructions for detection and isolation of at least one structural fault embodied therewith, the program instructions executable by the processor to cause:
generating, by the processor communicatively coupled to a monitoring sub-system that is physically coupled to a vehicle and communicatively coupled to one or more sensors, a plurality of sensed features that correspond to sensor data from the monitoring sub-system;
generating based on one or more models, by the processor, a plurality of estimated features that correspond to the plurality of sensed features;
comparing, by the processor, the plurality of sensor features and the plurality of estimated features to produce a plurality of residuals, a number of the plurality of residuals being determined based on a number the plurality sensed features and a number of the one or more models;
determining, by the processor, from the plurality of residuals whether the at least one structural fault exists within the vehicle; and
isolating, by the processor, the at least one structural fault from the plurality of residuals,
wherein the generation of the plurality of sensed features is based on at least one of the one or more sensors generating multiple sensed features.

10. The structural diagnostic system of claim 9 , wherein the program instructions are further executable by the processor to cause:
receiving by the processor from the monitoring sub-system the sensor data from the monitoring sub-system, the sensor data being detected by at least one sensor of the monitoring sub-system, the at least one sensor being physically coupled to the vehicle.

11. The structural diagnostic system of claim 9 , wherein, with respect to the generating of the plurality of estimated features based on the model, the program instructions are further executable by the processor to cause:
receiving by the processor stored sensor information;
processing the stored sensor information in accordance with the model to produce estimated data; and
processing via signal processing techniques the estimated data to produce the plurality of estimated features.

12. The structural diagnostic system of claim 9 , wherein the sensor data includes low-frequency state parametric data or high frequency state parametric data.

13. The structural diagnostic system of claim 9 , wherein each residual includes a magnitude and polarity that are utilized with respect to a threshold range during the determining of whether the at least one structural fault exists.

14. The structural diagnostic system of claim 9 , wherein the computing device is a ground based device.

15. The structural diagnostic system of claim 9 , wherein the vehicle is an aircraft.

16. The structural diagnostic system of claim 9 , wherein the isolation of the at least one structural fault from the plurality of residuals is based on a categorical decision model; and
wherein the number of the plurality sensed features is multiplied by the number of the one or more models to determine the number of the plurality of residuals.

17. The structural diagnostic system of claim 16 , wherein the categorical decision model utilizes at least one of: damage metrics, maintenance schedules, and maintenance policies.

18. The structural diagnostic system of claim 9 , wherein the system is further operable to provide a maintenance recommendation based on a determination of whether the at least one structural fault exists within the vehicle.

19. The method of claim 1 , wherein the isolation of the at least one structural fault from the plurality of residuals is based on a categorical decision model.

20. The method of claim 19 , wherein the categorical decision model utilizes at least one of: damage metrics, maintenance schedules, and maintenance policies.

Assignees

• Sikorsky Aircraft Corp

Inventors

• Isom Joshua D
• Davis Mark W
• Cycon James Peter

Classifications

• F02C3/10

  with another turbine driving an output shaft but not driving the compressor · CPC title

• B64D2045/0085

  Devices for aircraft health monitoring, e.g. monitoring flutter or vibration · CPC title

• B64C27/32

  Rotors · CPC title

• G01H1/006 Primary

  of the rotor of turbo machines · CPC title

• B64C27/04

  Helicopters · CPC title