Complex system diagnostic analysis model correction method and apparatus

• US 20040205397A1
• Filed: 03/28/2003
• Published: 10/14/2004
• Est. Priority Date: 03/28/2003
• Status: Abandoned Application

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Graichen, Catherine Mary, Rajiv, Vrinda, Joshi, Amey Sudhakar, Shah, Rasiklal Punjalal
• Application Number:
  US10/402,838
• Publication Number:
  US 20040205397A1
• Time in Patent Office: Days
• US Class Current: 714/25
• CPC Class Codes: G05B 17/02 electric
• CPC Class Codes: G05B 23/0278 Qualitative, e.g. if-then rules; Fuzzy logic; Lookup tables; Symptomatic search; FMEA
• CPC Class Codes: H04L 41/16 using machine learning or artificial intelligence

Abstract

A technique is provided for improving and correcting serviceability models for complex machine systems. A model is developed and implemented and several or a large number of such models may be developed and implemented for individual field replaceable units, components, functions, and subsystems of a complex system. The models, once implemented, result in serviceable events and service being rendered to the system. Based upon feedback from such service actions analysis is performed which correlates correct and incorrect assumptions or other aspects of the models such that improvement of the models can be made, improvements in the identification of which model should best be selected for addressing a serviceable event can be made, and the system can be improved so as to facilitate the use and performance of models.

Claims

1. A method for refining a serviceability model comprising:

accessing data representative of service actions taken with respect to at least one component of a plurality of components of a serviced system in response to a serviceable event;

comparing the data to parameters of a service model for the at least one component to identify parameters of the service model that do not accurately address a root cause of a serviceable event; and

modifying the service model based upon the identified parameters.

2. The method of claim 1, wherein the serviceable event includes a failure mode, and the service actions are taken after occurrence of a failure in accordance with the failure mode.

3. The method of claim 1, wherein the data is accessed remotely from the system via a network link.

4. The method of claim 1, wherein the data is accessed from an event or configuration log for at least a subsystem of the system.

5. The method of claim 1, wherein the data includes an assessment by service personnel of a service action performed, and the parameters include a service action recommendation made by the service model.

6. The method of claim 1, wherein the parameters include an assessment of likelihood of occurrence of a predetermined failure mode.

7. The method of claim 1, wherein the parameters include an assessment of likelihood of failure of a predetermined component, function, subsystem or field replaceable unit.

8. The method of claim 1, wherein the data includes states of a plurality of operational indicators prior to or at times the service actions are taken or recommended, and the parameters include anticipated states of corresponding indicators providing detection or isolation of predetermined failure modes.

9. A method for refining a serviceability model comprising:

accessing data representative of service actions taken with respect to at least one component of a plurality of components of a serviced system in response to a serviceable event, the data including a plurality of operational indicators prior to or at times the service actions are taken or recommended;

comparing the data to parameters of a service model for the at least one component to identify parameters of the service model that do not accurately address a root cause of a serviceable event, the parameters including anticipated states of corresponding indicators providing detection or isolation of predetermined failure modes; and

generating a report based upon the identified parameters.

10. The method of claim 9, comprising modifying the service model based upon the report.

11. The method of claim 9, wherein the data is accessed from an event or configuration log for at least a subsystem of the system.

12. The method of claim 9, wherein the data includes an assessment by service personnel of a service action performed, and the parameters include a service action recommendation made by the service model.

13. The method of claim 9, wherein the parameters include an assessment of likelihood of occurrence of a predetermined failure mode.

14. The method of claim 9, wherein the parameters include an assessment of likelihood of failure of a predetermined component, function, subsystem or field replaceable unit.

15. A method for refining a serviceability model comprising:

accessing data representative of service actions taken with respect to at least one component of a plurality of components of a serviced system in response to a serviceable event, the data including a plurality of operational indicators at times the service actions are taken, accessed from an event or configuration log for at least a subsystem of the system;

comparing the data to parameters of a service model for the at least one component to identify parameters of the service model that do not accurately address a root cause of a serviceable event, the parameters including anticipated states of corresponding indicators providing detection or isolation of predetermined failure modes; and

generating a report based upon the identified parameters.

16. The method of claim 15, wherein the data is accessed remotely from the system via a network link.

17. The method of claim 15, comprising modifying the service model based upon the report.

18. The method of claim 15, comprising modifying the system based upon the report.

19. The method of claim 15, wherein the data includes an assessment by service personnel of a service action performed, and the parameters include a service action recommendation made by the service model.

20. The method of claim 15, wherein the parameters include an assessment of likelihood of occurrence of a predetermined failure mode.

21. The method of claim 15, wherein the parameters include an assessment of likelihood of failure of a predetermined component, function, subsystem or field replaceable unit.

22. A system for refining a serviceability model comprising:

at least one memory circuit for storing indicator data representative of operational states of a complex system corresponding to serviceable events, and service data representative of service actions performed in response to the serviceable events;

a network for accessing the indicator data from the memory circuit;

an analysis module configured to generate a report evaluating a service model for at least one failure mode based upon the indicator data and the service data.

23. The system of claim 22, wherein the indicator data includes realtime indicator data and manual indicator data.

24. The system of claim 22, wherein the service data includes data derived from an event or configuration log.

25. The system of claim 22, wherein the service data includes an assessment by service personnel regarding the service actions.

26. A system for refining a serviceability model comprising:

means for accessing data representative of service actions taken with respect to at least one component of a plurality of components of a serviced system in response to a serviceable event;

means for comparing the data to parameters of a service model for the at least one component to identify parameters of the service model that do not accurately address a root cause of a serviceable event; and

means for modifying the service model based upon the identified parameters.

27. A system for refining a serviceability model comprising:

means for accessing data representative of service actions taken with respect to at least one component of a plurality of components of a serviced system in response to a serviceable event, the data including a plurality of operational indicators at times the service actions are taken;

means for comparing the data to parameters of a service model for the at least one component to identify parameters of the service model that do not accurately address a root cause of a serviceable event, the parameters including anticipated states of corresponding indicators providing detection or isolation of predetermined failure modes; and

means for generating a report based upon the identified parameters.

28. A system for refining a serviceability model comprising:

means for accessing data representative of service actions taken with respect to at least one component of a plurality of components of a serviced system in response to a serviceable event, the data including a plurality of operational indicators at times the service actions are taken accessed from an event or configuration log for at least a subsystem of the system;

means for comparing the data to parameters of a service model for the at least one component to identify parameters of the service model that do not accurately address a root cause of a serviceable event, the parameters including anticipated states of corresponding indicators providing detection or isolation of predetermined failure modes; and

means for generating a report based upon the identified parameters.

29. A computer program for refining a service model 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 data representative of service actions taken with respect to at least one component of a plurality of components of a serviced system in response to a serviceable event, comparing the data to parameters of a service model for the at least one component to identify parameters of the service model that do not accurately address a root cause of a serviceable event, and modifying the service model based upon the identified parameters.

30. A computer program for refining a service model 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 data representative of service actions taken with respect to at least one component of a plurality of components of a serviced system in response to a serviceable event, the data including a plurality of operational indicators at times the service actions are taken, comparing the data to parameters of a service model for the at least one component to identify parameters of the service model that do not accurately address a root cause of a serviceable event, the parameters including anticipated states of corresponding indicators providing detection or isolation of predetermined failure modes, and generating a report based upon the identified parameters.

31. A computer program for refining a service model 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 data representative of service actions taken with respect to at least one component of a plurality of components of a serviced system in response to a serviceable event, the data including a plurality of operational indicators at times the service actions are taken accessed from an event or configuration log for at least a subsystem of the system, comparing the data to parameters of a service model for the at least one component to identify parameters of the service model that do not accurately address a root cause of a serviceable event, the parameters including anticipated states of corresponding indicators providing detection or isolation of predetermined failure modes, and generating a report based upon the identified parameters.