Decision making process and manual for diagnostic trend analysis

• US 6,591,182 B1
• Filed: 02/29/2000
• Issued: 07/08/2003
• Est. Priority Date: 02/29/2000
• Status: Expired due to Term

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Abernathy, Charles L., Henlein, Christopher M., Cece, Vito N.
• Primary Examiner(s): Beaulieu, Yonel
• Application Number:
  US09/515,261
• Time in Patent Office: 1,225 Days
• Field of Search: 701/29, 701/100, 701/30, 701/107, 702/182, 702/183, 702/184, 702/185, 477/30
• US Class Current: 701/100
• CPC Class Codes: F02C 9/00 Controlling gas-turbine plants; Controlling fuel supply in air- breathing jet-propulsion plants controlling air intakes F02C7/057; controlling turbines F01D; controlling compressors F04D27/00; controlling in general G05
• CPC Class Codes: F05D 2260/80 Diagnostics
• CPC Class Codes: F05D 2270/053 Explicitly mentioned power
• CPC Class Codes: F05D 2270/12 to maintain desired vehicle trajectory parameters
• CPC Class Codes: F05D 2270/309 Rate of change of parameters
• CPC Class Codes: F05D 2270/44 active, predictive, or anticipative
• CPC Class Codes: F05D 2270/708 with comparison tables
• CPC Class Codes: G05B 23/0278 Qualitative, e.g. if-then rules; Fuzzy logic; Lookup tables; Symptomatic search; FMEA
• 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 decision making process for evaluating performance shifts identified during a diagnostic trend analysis of gas turbine engine data includes first determining whether each performance shift is actionable, and then determining what maintenance action is required for actionable performance shifts. The maintenance action is determined by identifying potential causes of the actionable performance shifts and ranking the identified potential causes in most likely order. A manual is provided for guiding a user through the decision making process. The manual includes a flow chart flow chart setting forth the steps of the decision making process and a number of tables used in the process. The tables include a false data check table having a number of questions designed to determine whether performance shifts can be attributed to a cause not related to an engine condition requiring maintenance, a persistence and magnitude table for indicating whether a performance shift'"'"'s persistence and magnitude is sufficient to consider taking action on the performance shift, a notification criteria table having a number of questions designed to determine whether the gas turbine engine data indicates that an urgent condition may exist, and traditional and historical pattern match tables that identify potential causes of performance shift.

Claims

1. A decision making process for evaluating performance shifts identified during a diagnostic trend analysis of data obtained from a gas turbine engine, said process comprising the steps of:

determining whether each performance shift is actionable; and

determining what maintenance action is required for actionable performance shifts by identifying potential causes of said actionable performance shifts and ranking said identified potential causes in most likely order.

2. The decision making process of claim 1 wherein said step of determining whether each performance shift is actionable includes determining whether each performance shift can be attributed to a cause not related to an engine condition requiring maintenance.

3. The decision making process of claim 1 wherein said step of determining whether each performance shift is actionable includes checking the persistence and magnitude of each performance shift.

4. The decision making process of claim 1 wherein said step of determining whether each performance shift is actionable includes determining for each performance shift whether said gas turbine engine data indicates that an urgent condition may exist.

5. The decision making process of claim 4 further comprising the step of notifying appropriate personnel if said gas turbine engine data indicates that an urgent condition may exist.

6. The decision making process of claim 1 wherein said step of determining whether each performance shift is actionable includes determining whether said gas turbine engine has been subject to a recent maintenance action.

7. The decision making process of claim 6 further comprising the step of determining if each performance shift can be attributed to a recent maintenance action when said gas turbine engine has been subject to a recent maintenance action.

8. The decision making process of claim 1 wherein said step of identifying potential causes of said actionable performance shifts includes using traditional and historical performance shift patterns.

9. The decision making process of claim 8 wherein said traditional performance shift patterns are based on gas turbine engine theory and general maintenance experience.

10. The decision making process of claim 8 wherein said historical performance shift patterns are based on actual engine maintenance experience.

11. The decision making process of claim 1 wherein said step of ranking said identified potential causes in most likely order includes using supporting and discounting data.

12. The decision making process of claim 1 wherein said step of ranking said identified potential causes in most likely order includes using a fleet assessment Pareto chart.

13. The decision making process of claim 1 wherein said step of ranking said identified potential causes in most likely order includes giving priority to any identified potential causes that pose a significant risk.

14. A decision making process for evaluating performance shifts identified during a diagnostic trend analysis of data obtained from a gas turbine engine, said process comprising the steps of:

determining whether each performance shift can be attributed to a cause not related to an engine condition requiring maintenance;

for performance shifts that cannot be attributed to a cause not related to an engine condition requiring maintenance, checking the persistence and magnitude of each performance shift;

for performance shifts not having a sufficient persistence and magnitude, determining for each performance shift whether said gas turbine engine data indicates that an urgent condition may exist;

for performance shifts having a sufficient persistence and magnitude or where said gas turbine engine data indicates that an urgent condition may exist, determining whether said gas turbine engine has been subject to a recent maintenance action;

where said gas turbine engine has been subject to a recent maintenance action, determining if each performance shift can be attributed to said recent maintenance action;

for performance shifts that cannot be attributed to said recent maintenance action and that have a sufficient persistence and magnitude, determining for each performance shift whether said gas turbine engine data indicates that an urgent condition may exist;

for performance shifts that cannot be attributed to said recent maintenance action, using traditional and historical performance shift patterns to identify potential causes of each performance shift; and

subsequently ranking said identified potential causes in most likely order.

15. The decision making process of claim 14 further comprising the step of continuing to watch said gas turbine engine data for performance shifts that can be attributed to a cause not related to an engine condition requiring maintenance.

16. The decision making process of claim 14 further comprising the step of continuing to watch said gas turbine engine data for performance shifts not having a sufficient persistence and magnitude and where said gas turbine engine data does not indicate that an urgent condition may exist.

17. The decision making process of claim 14 further comprising the step of continuing to watch said gas turbine engine data where said gas turbine engine has been subject to a recent maintenance action and performance shifts can be attributed to said recent maintenance action.

18. The decision making process of claim 14 further comprising the step of notifying appropriate personnel if said gas turbine engine data indicates that an urgent condition may exist.

19. The decision making process of claim 14 wherein said traditional performance shift patterns are based on gas turbine engine theory and general maintenance experience.

20. The decision making process of claim 14 wherein said historical performance shift patterns are based on actual engine maintenance experience.

21. The decision making process of claim 14 wherein said step of ranking said identified potential causes in most likely order includes using supporting and discounting data.

22. The decision making process of claim 14 wherein said step of ranking said identified potential causes in most likely order includes using a fleet assessment Pareto chart.

23. The decision making process of claim 14 wherein said step of ranking said identified potential causes in most likely order includes giving priority to any identified potential causes that pose a significant risk.

24. A manual for guiding a user through a decision making process for evaluating performance shifts identified during a diagnostic trend analysis of data obtained from a gas turbine engine, said manual comprising:

a flow chart flow chart setting forth the steps of said decision making process;

a false data check table having a number of questions designed to determine whether performance shifts can be attributed to a cause not related to an engine condition requiring maintenance;

a persistence and magnitude table for indicating whether a performance shift'"'"'s persistence and magnitude is sufficient to consider taking action on said performance shift;

a notification criteria table having a number of questions designed to determine whether said gas turbine engine data indicates that an urgent condition may exist; and

traditional and historical pattern match tables that identify potential causes of performance shift.

25. The manual of claim 24 further comprising a maintenance data effect table that lists limits for acceptable performance shift magnitudes for corresponding maintenance actions.

26. The manual of claim 24 further comprising a supporting and discounting table that lists data that support and data the discount potential causes of performance shift.

27. The manual of claim 24 further comprising urgency list table that identifies potential causes of performance shift that pose significant risk to gas turbine engines.

28. The manual of claim 24 further comprising a fleet assessment Pareto chart that ranks potential causes of performance shift by the number of occurrences that each potential cause actually caused a maintenance action.