Machine prognostics and health monitoring using speech recognition techniques

• US 20070255563A1
• Filed: 04/28/2006
• Published: 11/01/2007
• Est. Priority Date: 04/28/2006
• Status: Abandoned Application

• Current Assignee: Pratt & Whitney Canada Corporation (Rtx Corporation)
• Original Assignee: Pratt & Whitney Canada Corporation (Rtx Corporation)
• Inventors: Dooley, Kevin
• Application Number:
  US11/412,901
• Publication Number:
  US 20070255563A1
• Time in Patent Office: Days
• US Class Current: 704/236
• CPC Class Codes: F02D 2200/025 Engine noise, e.g. determined by using an acoustic sensor
• CPC Class Codes: F02D 41/22 Safety or indicating devices for abnormal conditions in air/fuel ratio feedback systems F02D41/1495, in electric control linkage F02D11/107, in purge control systems F02M25/0809
• CPC Class Codes: G01M 15/12 by monitoring vibrations
• CPC Class Codes: G01M 15/14 Testing gas-turbine engines or jet-propulsion engines
• CPC Class Codes: G07C 3/00 Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: Y02T 10/40 Engine management systems

Abstract

A method of monitoring the health of a machine by capturing sound data of the machine in operation and comparing the sound data to known sounds, preferably using human speech recognition techniques. Diagnostic and/or prognostic information about the machine'"'"'s operation may then be determined based at least in part on such comparison.

Claims

1. A method of monitoring the health of a machine using a health monitoring system, the method comprising the steps of:

a. capturing sound produced by the machine during operation thereof; and

b. comparing the sound to known reference sounds.

2. The method of claim 1, wherein the step of comparing includes using at least one human speech recognition algorithm to compare the sound to the known reference sounds.

3. The method of claim 1, wherein the step of capturing further comprises capturing the sound intermittently.

4. The method of claim 3, wherein the step of capturing includes using a controller of the machine to at least one of start and stop sound capture based on a machine parameter.

5. The method of claim 4, wherein the machine parameter is a pre-determined machine speed.

6. The method of claim 1, wherein the step of capturing is followed by the step of recording the sound.

7. The method of claim 2, wherein the sound is conditioned prior to said comparing step, to adjust at least a frequency component of the sound.

8. The method of claim 1, further comprising the step of transmitting data corresponding to the sound to a remote location.

9. The method of claim 1, further comprising detecting a known condition of the machine and setting a signal indicative of a required action associated with the known condition.

10. The method of claim 1, wherein the step of capturing includes using at least one microphone to capture the sound produced by the machine.

11. The method of claim 10, further comprising performing a calibration of the health monitoring system.

12. The method of claim 11, wherein the step of calibration includes performing a self-check of the health monitoring system using a sound generator.

13. The method of claim 12, further comprising integrating the sound generator within the at least one microphone.

14. A method of monitoring the health of a machine using a health monitoring system, the method comprising the steps of:

a. intermittently capturing sound data of the machine in operation; and

b. comparing the sound data to known sound data using a human speech recognition algorithm to determine a health condition of the machine.

15. The method of claim 14, wherein the step of intermittently capturing includes using a controller to at least one of start and stop sound capture based on a machine operating parameter.

16. The method of claim 15, wherein said at least one of starting and stopping the sound capture is based on an operating speed of the machine.

17. The method of claim 14, wherein the step of comparing includes using at least one speech recognition algorithm to compare the sound data to the known sound data.

18. The method of claim 14, further comprising recording and storing the sound data along with additional machine operational data associated with the sound data.

19. The method of claim 14, wherein the step of intermittently capturing further comprises using at least one microphone to capture sound produced by the machine.

20. The method of claim 14, further comprising indicating the presence of an abnormal condition of the machine when the captured sound data differs from the known sound data.

21. The method of claim 14, further comprising performing a calibration of the health monitoring system.

22. The method of claim 21, wherein the step of calibration includes performing a self-check of the health monitoring system using a sound generator.

23. The method of claim 22, further comprising integrating the sound generator within the health monitoring system.

24. A gas turbine engine health monitoring system comprising at least one microphone communicating with a sound recognition system employing a human speech recognition software algorithm.

25. The gas turbine engine health monitoring system of claim 24, wherein the sound recognition system includes a data analyzer having said human speech recognition software algorithm installed therein.

26. The gas turbine engine health monitoring system of claim 25, wherein the sound recognition system includes a signal conditioner adapted to modify at least data produced by said microphone representing sound outside an input frequency range expected by the human speech recognition software algorithm.