Evaluating the health status of a system using groups of vibration data including images of the vibrations of the system

• US 8,572,009 B2
• Filed: 08/16/2011
• Issued: 10/29/2013
• Est. Priority Date: 08/16/2011
• Status: Active Grant

• Current Assignee: The Boeing Co.
• Original Assignee: The Boeing Co.
• Inventors: Harris, Patrick Neal
• Primary Examiner(s): Gaffin, Jeffrey A
• Assistant Examiner(s): OLUDE AFOLABI, OLATOYOSI
• Application Number:
  US13/136,972
• Publication Number:
  US 20130046714A1
• Time in Patent Office: 805 Days
• Field of Search: 706/12, 702/184, 711/108
• US Class Current: 706/12
• CPC Class Codes: G01H 1/00 Measuring characteristics of vibrations in solids by using direct conduction to the detector G01H9/00, G01H11/00 take precedence
• CPC Class Codes: G01M 13/028 Acoustic or vibration analysis
• CPC Class Codes: G01M 5/0066 by exciting or detecting vibration or acceleration vibration testing of structures G01M7/00
• CPC Class Codes: G01M 7/00 Vibration-testing of structures; Shock-testing of structures G01M9/00 takes precedence
• CPC Class Codes: Y02B 10/30 Wind power

Abstract

A method and apparatus for determining a health of the system. Groups of vibration data are identified for the system. A group of vibration data in the groups of vibration data comprises data for vibrations of the system at different frequencies over time. The groups of vibration data for the system are stored in a number of associative memories in a computer system. The health of the system is identified based on the groups of vibration data in the number of associative memories. The groups of vibration data include images of the vibrations of the system.

Claims

1. A method for determining a health of a system comprising:

identifying groups of vibration data for the system, wherein a group of vibration data in the groups of vibration data comprises data for vibrations of the system at different frequencies over time, and wherein the groups of vibration data comprise images of the vibrations of the system;

storing the groups of vibration data for the system in a number of associative memories in a computer system, wherein the number of associative memories each comprise a type of memory having an organization in which data stored in a corresponding associative memory may be accessed based on both direct and indirect relationships among different data stored in the corresponding associative memory, wherein each of the number of associative memories comprise both the data and associations between the data, and wherein each of the number of associative memories also comprise a corresponding content-addressable structure that is configured to map a set of input patterns to a set of output patterns; and

identifying the health of the system based on the groups of vibration data in the number of associative memories.

2. The method of claim 1 further comprising:

generating the groups of vibration data for the system using a sensor system.

3. The method of claim 2, wherein the sensor system comprises a number of vibration sensors.

4. The method of claim 1, wherein identifying the health of the system based on the groups of vibration data in the number of associative memories comprises:

identifying the health of the system based on the groups of vibration data in the number of associative memories using an artificial intelligence system.

5. The method of claim 4, wherein the artificial intelligence system is selected from at least one of a cognitive simulation, a knowledge-based system, a neural network, a fuzzy logic system, and a cognitive model.

6. The method of claim 1, wherein an image in the images represents the data for the vibrations using frequency, intensity, and frequency distribution.

7. The method of claim 1, further comprising:

dividing each image in the images into sections.

8. The method of claim 1, wherein identifying the health of the system based on the groups of vibration data in the number of associative memories is performed using a health analyzer and further comprising:

placing a number of groups of baseline vibration data into the number of associative memories; and

training the health analyzer using the number of groups of baseline vibration data.

9. The method of claim 1, wherein the system is an assembly of components.

10. A method for determining a health of a system, the method comprising:

storing spectrographic images of vibrations of the system in a number of associative memories in a computer system; and

identifying the health of the system based on the spectrographic images stored in the number of associative memories.

11. The method of claim 10, wherein identifying the health of the system based on the spectrographic images stored in the number of associative memories comprises:

identifying the health of the system based on groups of vibration data in the number of associative memories using an artificial intelligence system.

12. A computer health monitoring system comprising:

a number of associative memories configured by the computer to store groups of vibration data for a system, wherein the number of associative memories each comprise a type of memory having an organization in which data stored in a corresponding associative memory may be accessed based on both direct and indirect relationships among different data stored in the corresponding associative memory, wherein each of the number of associative memories comprise both the data and associations between the data, and wherein each of the number of associative memories also comprise a corresponding content-addressable structure that is configured to map a set of input patterns to a set of output patterns, and wherein a group of vibration data in the groups of vibration data comprises data for vibrations of the system at different frequencies over time, and wherein the groups of vibration data comprise images of the vibrations of the system; and

a health analyzer, comprising a processor connected to the number of associative memories, configured to identify a health of the system based on the groups of vibration data in the number of associative memories.

13. The computer health monitoring system of claim 12 further comprising:

a sensor system configured to generate the groups of vibration data for the system.

14. The computer health monitoring system of claim 13, wherein the sensor system comprises a number of vibration sensors.

15. The computer health monitoring system of claim 12, wherein the health analyzer comprises an artificial intelligence system selected from at least one of a cognitive simulation, a knowledge-based system, a neural network, a fuzzy logic system, and a cognitive model.

16. The computer health monitoring system of claim 12, wherein an image in the images represents the data for the vibrations using frequency, intensity, and frequency distribution.

17. The computer health monitoring system of claim 12, wherein the health analyzer is configured to place a number of groups of baseline vibration data into the number of associative memories;

and train the health analyzer using the number of groups of baseline vibration data.

18. The computer health monitoring system of claim 12, wherein the system is selected from one of an aircraft, a gearbox, an engine, an engine housing, a control surface, a landing gear system, a fuselage, a spacecraft, a wind turbine, a dam, a computer numerical controlled machine, a building, and a bridge.