VIBRATION CONDITION MONITORING SYSTEM AND METHODS

• US 20150039250A1
• Filed: 07/31/2013
• Published: 02/05/2015
• Est. Priority Date: 07/31/2013
• Status: Active Grant

• Current Assignee: Baker Hughes, a GE Company, LLC (Baker Hughes Company)
• Original Assignee: General Electric Company
• Inventors: Rank, Brandon James
• Granted Patent: US 9,244,042 B2
• Time in Patent Office: Days
• US Class Current: 702/56
• CPC Class Codes: G01N 2291/2693 Rotor or turbine parts
• CPC Class Codes: G01N 2291/2696 Wheels, Gears, Bearings
• CPC Class Codes: G01N 29/14 using acoustic emission techniques echo of particles G01N29/046; measuring mechanical vibrations or acoustic waves in solids in general G01H1/00
• CPC Class Codes: G01N 29/4454 Signal recognition, e.g. specific values or portions, signal events, signatures
• CPC Class Codes: G01N 29/46 by spectral analysis, e.g. Fourier analysis or wavelet analysis spectral signal processing per se G06F17/14
• CPC Class Codes: H04R 29/00 Monitoring arrangements; Testing arrangements for hearing aids H04R25/30; detection of loudspeaker connection H04R5/04; sound-field adaptation dependent on speaker detection H04S7/308

Abstract

In one embodiment, a diagnostics system is provided. The diagnostics system include a detection system configured to capture acoustic information and contextual information related to a machine component defect. A computing system is coupled to a processor configured to receive the acoustic information and the contextual information from the detection system, select one or more algorithms based at least in part on the contextual information, and retrieve and execute the one or more algorithms to extract one or more characteristic features of the acoustic information. The processor is further configured to generate an acoustic fingerprint based at least in part on the one or more characteristic features of the acoustic information, such that the one or more characteristic features correspond to the machine component defect.

Claims

1. A system, comprising:

a diagnostics system, comprising;

a detection system configured to capture acoustic information related to an event associated with a machine component, wherein the detection system associates the acoustic information with contextual information related to the machine component;

communications circuitry configured to communicatively couple the detection system with a computing system, wherein the computing system is coupled to a processor configured to;

receive the acoustic information and the contextual information from the detection system;

select one or more algorithms based at least in part on the contextual information;

retrieve and execute the one or more algorithms to extract one or more characteristic features of the acoustic information; and

generate an acoustic fingerprint based at least in part on the one or more characteristic features of the acoustic information, wherein the one or more characteristic features correspond to the event associated with the machine component.

2. The system of claim 1, wherein the machine component is a component of an industrial system.

3. The system of claim 1, wherein the processor or an operator is configured to tag the acoustic fingerprint with the one or more extracted characteristic features to generate a tagged acoustic fingerprint.

4. The system of claim 3, wherein the tagged acoustic fingerprint is stored in a local database, a global database, or both.

5. The system of claim 1, wherein the communications circuitry is configured to communicatively couple the detection system with a service provider configured to obtain generated acoustic fingerprints from a plurality of computing systems.

6. The system of claim 5, wherein the service provider comprises a cloud-based service provider coupled to a global database, wherein the cloud-based service provider is configured to store a data repository of the generated acoustic fingerprints.

7. The system of claim 1, wherein the detection system comprises a mobile device, one or more sensors, a camera, a microphone, a hydrophone, a fiber optic sensor, a sound capturing device, or a combination thereof.

8. A method, comprising:

capturing, via a processor-based detection system, an acoustic sample related to an event associated with a machine component;

correlating contextual information related to the machine component with the acoustic information from a plurality of algorithms;

selecting one or more algorithms from the plurality of algorithms that correspond at least in part to the contextual information;

executing the one or more algorithms via a processor, wherein the one or more algorithms are configured to extract characteristic features of the acoustic sample; and

generating an acoustic fingerprint of the acoustic sample based at least in part on the extracted characteristic features of the acoustic sample.

9. The method of claim 8, comprising tagging the acoustic fingerprint with the extracted characteristic features, wherein the extracted characteristic features are representative of the event associated with the machine component.

10. The method of claim 8, comprising determining the event associated with the machine component, and tagging the acoustic fingerprint with the event associated with the machine component.

11. The method of claim 10, comprising tagging a rub condition, a misalignment, a mechanical looseness, a structural resonance, a soft foundation, a shaft bow, a bearing wear, a lost rotor blade, an imbalance, a flashback event, a flame holding event, a combustion dynamics event, a crack event, or a combination thereof, as the event associated with the machine component.

12. The method of claim 10, comprising storing the acoustic fingerprint tagged with the event associated with the machine component in a local database, a global database, or both.

13. The method of claim 8, comprising correlating the contextual information comprising information relating to a position of the detection system, a date, a time, a location, a running speed, an angle, or a combination thereof, with the acoustic information.

14. The method of claim 8, comprising defining the contextual information to the detection system through user input.

15. The method of claim 8, comprising extracting characteristic features of the acoustic sample comprising a frequency, a frequency range, an amplitude, one or more scale factors, or a combination thereof.

16. The method of claim 8, comprising generating a historical trend based at least in part on the acoustic sample and the contextual data.

17. A method, comprising:

extracting a first set of characteristic features of a first acoustic sample via one or more algorithms executed by one or more processors;

generating a first acoustic fingerprint of the first acoustic sample based at least in part on the first set of extracted characteristic features of the first acoustic sample;

determining an event associated with a machine component based at least in part on the first set of extracted characteristic features;

tagging the first acoustic sample with the event associated with the machine component to generate a tagged first acoustic sample;

storing the first acoustic fingerprint in a database;

extracting a second set of characteristic features of a second acoustic sample via the one or more algorithms executed by the one or more processors;

generating a second acoustic fingerprint of the second acoustic sample based at least in part on the second set of extracted characteristic features of the second acoustic sample; and

comparing the tagged first acoustic sample with the second set of extracted characteristic features of the second acoustic sample to determine whether a match exists, wherein the match is indicative of the event associated with the machine component within the second acoustic sample.

18. The method of claim 17, comprising retrieving the first acoustic fingerprint from the database;

and comparing the first acoustic fingerprint with the second acoustic fingerprint to determine whether the match exists.

19. The method of claim 17, comprising alerting an operator if the first acoustic sample matches the second acoustic sample within a confidence interval.

20. The method of claim 19, comprising storing the second acoustic sample within the database if the first acoustic sample does not match the second acoustic sample within the confidence interval.