Automatic mechanical system diagnosis

• US 9,835,594 B2
• Filed: 10/22/2012
• Issued: 12/05/2017
• Est. Priority Date: 10/22/2012
• Status: Active Grant

• Current Assignee: Augury Systems Ltd. (Augury, Inc.)
• Original Assignee: Augury Systems Ltd. (Augury, Inc.)
• Inventors: Yoskovitz, Saar, Shaul, Gal
• Primary Examiner(s): Breene, John
• Assistant Examiner(s): Liao, Christine
• Application Number:
  US13/657,037
• Publication Number:
  US 20140114612A1
• Time in Patent Office: 1,870 Days
• CPC Class Codes: G01H 1/003 of rotating machines G01H1/10 takes precedence
• CPC Class Codes: G01H 1/04 of vibrations which are transverse to direction of propagation
• CPC Class Codes: G01H 3/08 Analysing frequencies present in complex vibrations, e.g. comparing harmonics present acoustic presence detection G01V1/001
• CPC Class Codes: G01H 9/00 Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
• CPC Class Codes: G01M 13/028 Acoustic or vibration analysis
• CPC Class Codes: G01M 13/045 Acoustic or vibration analysis
• CPC Class Codes: G01M 99/005 Testing of complete machines, e.g. washing-machines or mobile phones testing of machine parts G01M13/00; testing of electric apparatus or components G01R31/50
• 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 29/2481 Wireless probes, e.g. with transponders or radio links
• 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: G05B 23/0283 Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL] preventive maintenance, i.e. planning maintenance according to the available resources without monitoring the system G06Q10/06

Abstract

A method for automatic diagnosis of a mechanical system of a group of mechanical systems sharing mechanical characteristics includes obtaining data relating to a vibration. The vibration-related data is acquired by a portable communications device configured to communicate with a remote processor. The processor automatically diagnoses the mechanical system by applying a relationship to the obtained vibration-related data. The relationship is based on sets of vibration-related data previously obtained from the mechanical systems. Each set of vibration-related data relates to vibrations of a mechanical system. The relationship is further based on sets of operation data previously obtained for mechanical systems of the group. Each set of operation data indicates a previous state of operation of a mechanical system. Each of the previous states of operation is associated with at least one of the previously obtained sets of vibration-related data.

Claims

1. A system for maintenance of at least one mechanical machine having at least one shared mechanical characteristic with a plurality of mechanical machines, the system comprising:

a plurality of operational parameter sensors coupled to a corresponding plurality of mechanical machines having at least one shared mechanical characteristic for sensing at least one operational parameter thereof, said plurality of operational parameter sensors coupled to said corresponding plurality of mechanical machines providing output indications of associated operational parameters of said corresponding plurality of mechanical machines; and

a computer comprising a processor, a memory and a non-transitory, tangible computer-readable medium in which computer program instructions are stored, which instructions, when read by said computer, cause the computer to provide the following functionalities;

receiving said output indications of associated operational parameters of said corresponding plurality of mechanical machines;

accumulating said output indications of said associated operational parameters of said corresponding plurality of mechanical machines and providing accumulated associated operational parameters;

providing an output indication of a historical correlation between said associated operational parameters of said plurality of mechanical machines based on analyzing said accumulated associated operational parameters;

receiving said output indication of said historical correlation between said associated operational parameters of said plurality of mechanical machines;

providing a human sensible output alarm indication including at least a prediction of failure of at least one given mechanical machine having said at least one shared mechanical characteristic, based on applying said historical correlation between said associated operational parameters of said plurality of mechanical machines to output indications of said at least one operational parameter of said at least one given mechanical machine sensed by a corresponding one of said plurality of operational parameter sensors; and

scheduling at least one maintenance related operation based on said human sensible output alarm indication.

2. A system for maintenance of at least one mechanical machine according to claim 1 and wherein said plurality of operational parameter sensors includes a vibration sensor.

3. A system for maintenance of at least one mechanical machine according to claim 1 and wherein said given mechanical machine is one of said plurality of mechanical machines.

4. A system for maintenance of at least one mechanical machine according to claim 1 and wherein said given mechanical machine is not one of said plurality of mechanical machines.

5. A system for maintenance of at least one mechanical machine according to claim 1 and wherein said human sensible output alarm indication is based on a current operational parameter output of said given mechanical machine as sensed by one of said plurality of operational parameter sensors.

6. A system for maintenance of at least one mechanical machine according to claim 1 and wherein said human sensible output alarm indication includes a mean time between failures (MTBF) indication.

7. A system for maintenance of at least one mechanical machine according to claim 1 and wherein said human sensible output alarm indication includes a confidence metric indication indicating the reliability of said prediction.

8. A system for maintenance of at least one mechanical machine according to claim 1 and wherein said human sensible output alarm indication includes a recommendation for at least one of a repair operation and a maintenance operation.

9. A method for scheduling maintenance of at least one mechanical machine having at least one shared mechanical characteristic with a plurality of mechanical machines, the method comprising:

coupling a plurality of operational parameter sensors to a corresponding plurality of mechanical machines having at least one shared mechanical characteristic for sensing at least one operational parameter thereof, said plurality of operational parameter sensors providing output indications of associated operational parameters of said corresponding plurality of mechanical machines; and

receiving, by a computer including a processor and a memory, said output indications of associated operational parameters of said corresponding plurality of mechanical machines;

accumulating, utilizing said computer, said output indications of said associated operational parameters of said corresponding plurality of mechanical machines and providing accumulated associated operational parameters;

providing, utilizing said computer, an output indication of a historical correlation between said associated operational parameters of said corresponding plurality of mechanical machines based on analyzing said accumulated associated operational parameters;

receiving said output indication of said historical correlation between associated operational parameters of said corresponding plurality of mechanical machines;

applying said historical correlation between said associated operational parameters to output indications of said at least one operational parameter of at least one given machine, sensed by a corresponding one of said plurality of operational parameter sensors;

providing at least one maintenance related operation human sensible output indication, including at least a prediction of failure of said at least one mechanical machine having said at least one shared mechanical characteristic, based on said applying said historical correlation; and

scheduling at least one maintenance related operation based on said at least one maintenance related operation human sensible output indication.

10. A method for scheduling maintenance of at least one mechanical machine according to claim 9 and wherein said plurality of operational parameter sensors includes a vibration sensor.

11. A method for scheduling maintenance of at least one mechanical machine according to claim 9 and wherein said given mechanical machine is one of said plurality of mechanical machines.

12. A method for scheduling maintenance of at least one mechanical machine according to claim 9 and wherein said given mechanical machine is not one of said plurality of mechanical machines.

13. A method for scheduling maintenance of at least one mechanical machine according to claim 9 and wherein said at least one maintenance related operation human sensible output indication is based on a current operational parameter output of said given mechanical machine as sensed by one of said plurality of operational parameter sensors.

14. A method for scheduling maintenance of at least one mechanical machine according to claim 9 and wherein said at least one maintenance related operation human sensible output indication includes a mean time between failures (MTBF) indication.

15. A method for scheduling maintenance of at least one mechanical machine according to claim 9 and wherein said at least one maintenance related operation human sensible output indication includes a confidence metric indication indicating the reliability of said prediction.