Method and apparatus to diagnose mechanical problems in machinery

• US 20050154542A1
• Filed: 01/13/2005
• Published: 07/14/2005
• Est. Priority Date: 01/14/2004
• Status: Active Grant

• Current Assignee: ABB Incorporated (ABB Limited)
• Original Assignee: ABB Incorporated (ABB Limited)
• Inventors: Frerichs, Donald Karl, Johnson, Steven James, Toth, Frank Marvin
• Granted Patent: US 7,225,109 B2
• Time in Patent Office: Days
• US Class Current: 702/56
• CPC Class Codes: G01H 17/00 Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups see provisionally also G01H1/00
• CPC Class Codes: G05B 19/4065 Monitoring tool breakage, life or condition
• CPC Class Codes: G05B 2219/32201 Build statistical model of past normal proces, compare with actual process
• CPC Class Codes: G05B 2219/37435 Vibration of machine
• CPC Class Codes: Y02P 90/02 Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Abstract

A method and apparatus for detecting mechanical problems in machinery used in a process. A model of the process is developed using a modeling technique such as advanced pattern recognition and the model is used to generate predicted values for a predetermined number of the operating parameters of the process and vibration parameters of the machinery. Statistical process control methods are used to determine if the difference between the predicted and actual measured values for one or more of the parameters exceeds a configured statistical limit. A rule set is used to indicate an actual or probable fault in the machinery.

Claims

1. A method for detecting a fault in a machine used in a process, comprising:

developing a model of said process;

generating predicted values for a predetermined number of operating parameters of said process and a predetermined number of vibration parameters of said machine using said model;

comparing the value predicted by said model for each of said predetermined number of vibration and operating parameters to a corresponding actual measured value for each of said vibration and operating parameters; and

determining whether differences between said predicted and actual measured values for one or more of said predetermined number of vibration and operating parameters exceeds a configured statistical limit using numerical methods.

2. The method of claim 1 further comprising determining when said numerical methods is a Statistical Process Control (SPC) method whether differences between said predicted and actual measured values for one or more of said predetermined number of vibration and operating parameters meets a predetermined SPC data pattern test.

3. The method of claim 1 wherein said model is selected from an Advanced Pattern Recognition (APR) empirical model, a first principles model or a neural network empirical model.

4. The method of claim 3 further comprising calculating in said APR empirical model a Model Fit parameter from said differences between said predicted and actual measured values for one or more of said predetermined number of vibration and operating parameters.

5. The method of claim 1 wherein said predetermined number of operating parameters of said process depends on said process and said predetermined number of vibration parameters of said machine depends upon said machine.

6. The method of claim 1 further comprising determining for each of said predetermined number of vibration and operating parameters a difference between said predicted values for said vibration and operating parameter and said actual measured value for said vibration and operating parameter.

7. The method of claim 6 wherein said difference for selected ones of said predetermined vibration and operating parameters are each compared to an associated three sigma limit.

8. The method of claim 7 further comprising indicating:

a gross failure of an element in a machine in said process when said deviation for any three of said vibration and operating parameters are positive and statistically large for a predetermined period of time; and

a probability of a mechanical failure in a machine in said process when said deviation for any two of said vibration and operating parameters are slightly positive for a predetermined period of time.

9. A process plant comprising:

a computing device for detecting a fault in a machine used in a process operating in said plant, said computing device for developing a model of said process;

generating predicted values for a predetermined number of operating parameters of said process and a predetermined number of vibration parameters of said machine using said model;

comparing the value predicted by said model for each of said predetermined number of vibration and operating parameters to a corresponding actual measured value for each of said vibration and operating parameters; and

determining whether differences between said predicted and actual measured values for one or more of said predetermined number of vibration and operating parameters exceeds a configured statistical limit using numerical methods.

10. The process plant of claim 9 wherein said computing device is also for determining when said numerical methods is a Statistical Process Control (SPC) method whether differences between said predicted and actual measured values for one or more of said predetermined number of vibration and operating parameters meets a predetermined SPC data pattern test.

11. The process plant of claim 9 wherein said computing device is also for determining for each of said predetermined number of vibration and operating parameters a difference between said predicted values for said vibration and operating parameters and said actual measured value for said vibration and operating parameter.

12. The process plant of claim 11 wherein said computing device is also for comparing said difference for selected ones of said predetermined vibration and operating parameters to an associated three sigma limit.

13. In a plant comprising:

a process having one or more machines;

a computing device for detecting a fault in said one or more machines of said process, said computing device for developing a model of said process;

generating predicted values for a predetermined number of operating parameters of said process and a predetermined number of vibration parameters of said one or more machines using said model;

comparing the value predicted by said model for each of said predetermined number of vibration and operating parameters to a corresponding actual measured value for each of said vibration and operating parameters; and

determining whether differences between said predicted and actual measured values for one or more of said predetermined number of vibration and operating parameters exceeds a configured statistical limit using numerical methods.

14. The plant of claim 13 wherein said computing device is also for determining when said numerical methods is a Statistical Process Control (SPC) method whether differences between said predicted and actual measured values for one or more of said predetermined number of vibration and operating parameters meets a predetermined SPC data pattern test.

15. The plant of claim 13 wherein said computing device is also for determining for each of said predetermined number of vibration and operating parameters a difference between said predicted values for said vibration and operating parameter and said actual measured value for said vibration and operating parameter.

16. The plant of claim 15 wherein said computing device is also for comparing said difference for selected ones of said predetermined vibration and operating parameters to an associated three sigma limit.

17. A computer readable medium having instructions for performing a method for detecting a fault in a machine of a process operating in a plant, said instructions comprising:

developing a model of said process;

generating predicted values for a predetermined number of operating parameters of said process and for a predetermined number of vibration parameters of said machine using said model;

comparing the value predicted by said model for each of said predetermined number of vibration and operating parameters to a corresponding actual measured value for each of said vibration and operating parameters; and

determining whether differences between said predicted and actual measured values for one or more of said predetermined number of vibration and operating parameters exceeds a configured statistical limit using numerical methods.

18. The computer readable medium of claim 17 wherein said instructions further comprise determining when said numerical methods is a Statistical Process Control (SPC) method whether differences between said predicted and actual measured values for one or more of said predetermined number of vibration and operating parameters meets a predetermined SPC data pattern test.

19. The computer readable medium of claim 17 wherein said instructions further comprise determining for each of said predetermined number of operating parameters a difference between said predicted values for said vibration and operating parameters and said actual measured value for said vibration and operating parameters.

20. The computer readable medium of claim 19 wherein said instructions further comprise comparing said difference for selected ones of said predetermined number of vibration and operating parameters to an associated three sigma limit.

21. An apparatus comprising:

a processing device for;

developing a model of a process;

generating predicted values for a predetermined number of operating parameters of said process and a predetermined number of vibration parameters of said machine using said model;

comparing the value predicted by said model for each of said predetermined number of vibration and operating parameters to a corresponding actual measured value for each of said vibration and operating parameters; and

determining whether differences between said predicted and actual measured values for one or more of said predetermined number of vibration and operating parameters exceeds a configured statistical limit using numerical methods.

22. The apparatus of claim 21 wherein said process device is also for determining when said numerical methods is a Statistical Process Control (SPC) method whether differences between said predicted and actual measured values for one or more of said predetermined number of vibration and operating parameters meets a predetermined SPC data pattern test.

23. The apparatus of claim 21 wherein said process device is also for determining for each of said predetermined number of vibration and operating parameters a difference between said predicted values for said vibration and operating parameter and said actual measured value for said vibration and operating parameter.

24. The computer readable medium of claim 23 wherein said instructions further comprise comparing said difference for selected ones of said predetermined vibration and operating parameters to an associated three sigma limit.