Complex system diagnostic service model selection method and apparatus

• US 7,254,747 B2
• Filed: 03/28/2003
• Issued: 08/07/2007
• Est. Priority Date: 03/28/2003
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Osborn, Mark David, Chen, Jieqian Cathy, Shah, Rasiklal Punjalal
• Primary Examiner(s): Iqbal; Nadeem
• Application Number:
  US10/402,874
• Publication Number:
  US 20040205398A1
• Time in Patent Office: 1,593 Days
• Field of Search: 714/37, 714/38, 714/39, 714/40, 714/47, 705/2, 705/7, 705/14
• US Class Current: 714/37
• CPC Class Codes: G05B 23/0278 Qualitative, e.g. if-then rules; Fuzzy logic; Lookup tables; Symptomatic search; FMEA
• CPC Class Codes: G06F 11/0727 in a storage system, e.g. in a DASD or network based storage system drivers for digital recording or reproducing units G06F3/06; circuits for error detection or correction within digital recording or reproducing units G11B20/18; for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS], H04L67/1097
• CPC Class Codes: G06F 11/079 Root cause analysis, i.e. error or fault diagnosis in a hardware test environment G06F11/22; in a software test environment G06F11/36
• CPC Class Codes: G06F 11/0793 Remedial or corrective actions recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40

Abstract

A technique is provided for selecting among a plurality of service models for addressing serviceable events and faults in a complex machine system. Indicators established for each of the models serve as the basis for comparison to input data acquired from the complex system or from manual or semi-automated data acquisition methods. Based upon the comparisons, and upon flexible selection criteria, one or more of the service models is selected to most efficiently address the most likely root cause of the serviceable event or fault.

Claims

1. A method for selecting a service model from a plurality of service models comprising:

accessing input data from a plurality of components of a complex system in response to a serviceable event;

comparing the input data to corresponding indicators for a plurality of service models for the plurality of components; and

selecting a service model from the plurality of service models for determination of a service action on a corresponding one of the components in response to the serviceable event based upon the comparison.

2. The method of claim 1, wherein the service model is selected based upon a number of matches between the input data and indicators for each of the service models.

3. The method of claim 1, wherein the service model is selected based upon weighting of indicators for each of the service models.

4. The method of claim 1, wherein the input data includes data representative of operational parameters of the complex system automatically collected by sensors associated with the plurality of components.

5. The method of claim 1, wherein the input data includes data representative of operational parameters of the complex system manually collected.

6. The method of claim 1, wherein the at least one service model is selected based upon selection criteria stored in a memory device.

7. The method of claim 6, wherein the selection criteria are stored in the memory device as a replaceable software module.

8. The method of claim 1, comprising identifying a recommended service action based upon the selected model.

9. The method of claim 8, comprising comparing the input data to the indicators for identification of the recommended service action.

10. A method for selecting a service model from a plurality of service models comprising:

accessing input data from a plurality of components of a complex system in response to a serviceable event;

comparing the input data to corresponding indicators for a plurality of service models for the plurality of components; and

selecting a service model from the plurality of service models for determination of a service action on a corresponding one of the components in response to the serviceable event based upon a number of matches between the input data and indicators for each of the service models.

11. The method of claim 10, wherein the service model is selected based upon weighting of indicators for each of the service models.

12. The method of claim 10, wherein the input data includes data representative of operational parameters of the complex system automatically collected by sensors associated with the plurality of components.

13. The method of claim 10, wherein the input data includes data representative of operational parameters of the complex system manually collected.

14. The method of claim 10, wherein the at least one service model is selected based upon selection criteria stored in a memory device.

15. The method of claim 14, wherein the selection criteria are stored in the memory device as a replaceable software module.

16. The method of claim 10, comprising identifying a recommended service action based upon the selected model.

17. The method of claim 16, comprising comparing the input data to the indicators for identification of the recommended service action.

18. A method for identifying a service action from a plurality of service models comprising:

accessing input data from a plurality of components of a complex system in response to a serviceable event;

comparing the input data to corresponding indicators for a plurality of service models for the plurality of components;

selecting a service model from the plurality of service models for determination of a service action on a corresponding one of the components in response to the serviceable event based upon a number of matches between the input data and indicators for each of the service models; and

identifying a recommended service action based upon the selected model.

19. The method of claim 18, comprising comparing the input data to the indicators for identification of the recommended service action.

20. The method of claim 18, wherein the service model is selected based upon weighting of indicators for each of the service models.

21. The method of claim 18, wherein the input data includes data representative of operational parameters of the complex system automatically collected by sensors associated with the plurality of components.

22. The method of claim 18, wherein the input data includes data representative of operational parameters of the complex system manually collected.

23. The method of claim 18, wherein the at least one service model is selected based upon selection criteria stored in a memory device.

24. The method of claim 23, wherein the selection criteria are stored in the memory device as a replaceable software module.

25. A system for selecting a service model from a plurality of service models comprising

a storage device for storing a plurality of service models defining to service actions responsive to serviceable events;

a set of selection criteria for selection of models of the plurality of service models based upon indicators associated with each of the models; and

a model selection module configured to select at least one of the models based upon input data from a complex system and upon the selection criteria.

26. The system of claim 25, wherein the model selection module forms a Bayesian network.

27. The system of claim 25, comprising a network link for accessing input data from the complex system.

28. The system of claim 25, wherein the service model is selected based upon a number of matches between the input data and indicators for each of the service models.

29. The system of claim 25, wherein the service model is selected based upon weighting of indicators for each of the service models.

30. The system of claim 25, wherein the input data includes data representative of operational parameters of the complex system automatically collected by sensors associated with a plurality of components.

31. The system of claim 25, wherein the input data includes data representative of operational parameters of the complex system manually collected.

32. The system of claim 25, wherein the selection criteria are stored in the memory device as a replaceable software module.

33. A system for selecting a service model from a plurality of service models comprising:

means for accessing input data from a plurality of components of a complex system in response to a serviceable event;

means for comparing the input data to corresponding indicators for a plurality of service models for the plurality of components; and

means for selecting a service model from the plurality of service models for determination of a service action on a corresponding one of the components in response to the serviceable event based upon the comparison.

34. A system for selecting a service model from a plurality of service models comprising:

means for accessing input data from a plurality of components of a complex system in response to a serviceable event;

means for comparing the input data to corresponding indicators for a plurality of service models for the plurality of components; and

means for selecting a service model from the plurality of service models for determination of a service action on a corresponding one of the components in response to the serviceable event based upon a number of matches between the input data and indicators for each of the service models.

35. A system for identifying a service action from a plurality of service models comprising:

means for accessing input data from a plurality of components of a complex system in response to a serviceable event;

means for comparing the input data to corresponding indicators for a plurality of service models for the plurality of components;

means for selecting a service model from the plurality of service models for determination of a service action on a corresponding one of the components in response to the serviceable event based upon a number of matches between the input data and indicators for each of the service models; and

means for identifying a recommended service action based upon the selected model.

36. A computer program for selecting a service model from a plurality of service models comprising:

at least one machine readable medium for storing computer code; and

computer code stored on the media for performing a series of routines including accessing input data from a plurality of components of a complex system in response to a serviceable event, comparing the input data to corresponding indicators for a plurality of service models for the plurality of components, and selecting a service model from the plurality of service models for determination of a service action on a corresponding one of the components in response to the serviceable event based upon the comparison.

37. A computer program for selecting a service model from a plurality of service models comprising:

at least one machine readable medium for storing computer code; and

computer code stored on the media for performing a series of routines including accessing input data from a plurality of components of a complex system in response to a serviceable event, comparing the input data to corresponding indicators for a plurality of service models for the plurality of components, and selecting a service model from the plurality of service models for determination of a service action on a corresponding one of the components in response to the serviceable event based upon a number of matches between the input data and indicators for each of the service models.

38. A computer program for identifying a service action from a plurality of service models comprising:

at least one machine readable medium for storing computer code; and

computer code stored on the media for performing a series of routines including accessing input data from a plurality of components of a complex system in response to a serviceable event, comparing the input data to corresponding indicators for a plurality of service models for the plurality of components, selecting a service model from the plurality of service models for determination of a service action on a corresponding one of the components in response to the serviceable event based upon a number of matches between the input data and indicators for each of the service models, and identifying a recommended service action based upon the selected model.