Dynamically configurable process for diagnosing faults in rotating machines

• US 6,560,552 B2
• Filed: 03/20/2001
• Issued: 05/06/2003
• Est. Priority Date: 03/20/2001
• Status: Expired due to Fees

• Current Assignee: Johnson Controls Technology Company (Johnson Controls International plc)
• Original Assignee: Johnson Controls Technology Company (Johnson Controls International plc)
• Inventors: Verhaalen, Rick A., Shen, Hwa N.
• Primary Examiner(s): Bui, Bryan
• Application Number:
  US09/812,924
• Publication Number:
  US 20020138217A1
• Time in Patent Office: 777 Days
• Field of Search: 702/33, 702/34, 702/35, 702/56, 702/182-183, 702/185, 702/189-190, 735/79, 736/02, 735/59, 736/60, 734/62
• US Class Current: 702/56
• CPC Class Codes: G01H 1/003 of rotating machines G01H1/10 takes precedence
• CPC Class Codes: G01M 15/12 by monitoring vibrations
• CPC Class Codes: G01R 31/343 in operation

Abstract

A technique for detecting problems in a rotating machine is configured by the user specifying components and the functional characteristics of a particular installation of a rotating machine. The machine specification are used to identify salient observations that can be derived from measurement data regarding the machine performance. Rules are specified by the user to deduce machine signatures from the salient observations and detect problems evidenced by the machine signatures.

Claims

1. A method for dynamically configuring a diagnostic apparatus for automatically and systematically diagnosing faults in a rotating machine, comprising:

creating definitions for all major components of the rotating machine and storing the definitions in a memory of the apparatus;

constructing search equations for extracting salient observations from machine measurements acquired from the rotating machine and storing the search equations in the memory; and

specifying rules for deducing machine signatures from the salient observations and identifying faults in the rotating machine from the machine signatures, and storing the rules in the memory.

2. The method of claim 1, wherein creating definitions of major components comprises specifying generic components for the rotating machine and transforming the generic components into manufacturer specific components.

3. The method of claim 2, wherein specifying generic components includes selecting the generic components from a menu of selection choices.

4. The method of claim 2, wherein transforming the generic components includes adding manufacturer specifications to the generic components.

5. The method of claim 2, wherein creating definitions of major components further comprises transforming the manufacturer specific components into site specific definitions of the components.

6. The method of claim 5, wherein transforming the manufacturer specific components comprises adding location specific information to the manufacturer specific components.

7. The method of claim 1, further including creating definitions of instrumentation attached to the rotating machine and storing the instrumentation definitions in the memory.

8. The method of claim 1, wherein the machine measurements comprise vibration data acquired from the rotating machine and the search equations define frequency bands for the vibration data in which the salient observations fall.

9. The method of claim 8, wherein the frequency bands are specified as absolute low and high frequency limits or as a center frequency with delta frequencies relative to the center frequency.

10. The method of claim 8, wherein at least one of the major components definitions, search equations, and rules are stored within a table contained in the memory.

11. The method of claim 8, wherein the rules for deducing machine signatures include signature rules comprising “

if”

-“

then”

statements having specific conditions which when satisfied indicate the presence of that signature.

12. The method of claim 11, wherein the “

if”

part of each statement involves a plurality of terms related by mathematical, logical or relational operators.

13. The method of claim 12, wherein the terms include at least one of transformed salient observations, constants and raw salient observations.

14. The method of claim 12, wherein the apparatus is a computer.

15. The method of claim 8, wherein the rules for identifying faults in the rotating machine include problem rules comprising “

if”

-“

then”

statements that test for combinations of machine signatures.

16. The method of claim 15, wherein the “

if”

part of at least one statement further tests for actual measurement data.

17. A method for automatically and systematically diagnosing faults in a rotating machine using a diagnostic apparatus, comprising:

performing a set-up phase for the apparatus, the set-up phase including;

constructing definitions of major components of the rotating machine,

constructing search equations for extracting salient observations from machine measurements, and

specifying rules for deducing machine signatures from the salient observations and identifying faults in the rotating machine from the machine signatures; and

performing an analysis phase with the apparatus, the analysis phase including;

acquiring machine measurements using a plurality of sensors mounted on the rotating machine and supplying the machine measurements to the apparatus,

extracting salient observations from the machine measurements using the search equations,

deducing machine signatures from the salient observations using the signature rules, and

identifying faults in the rotating machine using the rules.

18. The method of claim 17, wherein the machine measurements comprise vibration data acquired from the machine and the search equations define frequency bands for the vibration data in which the salient observations fall, the extracting step comprising obtaining data peaks within the frequency bands.

19. The method of claim 18, wherein the data peaks are extracted from the data by quadratic fit.

20. The method of claim 18, further comprising applying a power band calculation to the vibration data.

21. The method of claim 18, further comprising categorizing the salient observations according to their significance.

22. The method of claim 18, further comprising repeating the set-up phase whenever a change is made to the rotating machine.