Method and apparatus for diagnosing difficult to diagnose faults in a complex system

• US 6,615,367 B1
• Filed: 07/03/2000
• Issued: 09/02/2003
• Est. Priority Date: 10/28/1999
• Status: Expired due to Term

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Roddy, Nicholas Edward, Unkle, C. Richard
• Primary Examiner(s): BADERMAN, SCOTT T
• Application Number:
  US09/609,469
• Time in Patent Office: 1,156 Days
• Field of Search: 714/26, 714/37, 714/45, 714/47, 714/57, 714/723, 700/49, 712/227, 706/45, 706/46, 706/47, 706/50, 706/60, 706/61
• US Class Current: 714/26
• CPC Class Codes: G05B 23/0229 knowledge based, e.g. expert systems; genetic algorithms

Abstract

A method and apparatus for determining the root cause of no trouble found events in a machine is disclosed. The actual faults occurring during a predetermined time interval prior to the no trouble found event are analyzed and correlated with the no trouble found events in an effort to identify those actual faults that have a high correlation with each no trouble found event. If a high correlation is not found, then the no trouble found event is analyzed off-line to determine the root cause.

Claims

1. A method for enhanced analysis of “

no-trouble-found-events”

from one or more machines, wherein the “

no-trouble-found-events”

designation is applied to those machine faults for which no cause could be identified, based on a first set of data, with equipment thus being characterized as being available for return to service with no remedial action being taken, but for which latent causes may exist that may recur when the equipment is returned to service, said method comprising;

(a) receiving a first set of data representing the faults experienced by the one or more machines;

(b) concluding based on the first set of data that there is a “

no-trouble-found-event”

;

(c) for the one or more machines, selecting a second set of data representing faults occurring within a predetermined time relative to the “

no-trouble-found-event”

;

(d) generating at least one distinct fault cluster based on said second set of data; and

(e) determining the correlation between the “

no-trouble-found-event” and

the at least one distinct fault cluster to identify a root cause for the “

no-trouble-found-event”

.

2. The method of claim 1, wherein the second set of data includes operational parametric information occurring at or near the time when the fault occurred.

3. The method of claim 1, wherein determining the root cause for the selected “

no-trouble-found-event”

is based on a high correlation with the at least one distinct fault cluster.

4. A method for enhanced analysis of no-trouble-found-events occurring on a machine to identify possible causes thereof, wherein the no-trouble-found-events designation is applied to those events occurring during operation of the machine for which no cause has been identified, with equipment thus being characterized as being available for return to service with no remedial action being taken, but for which latent causes may exist that may recur when the equipment is returned to service, said method comprising:

(a) receiving data representing the faults experienced by the machine;

(b) receiving no-trouble-found-event data;

(c) selecting a no-trouble-found-event from the no-trouble-found-event data;

(d) selecting the faults occurring within a predetermined time relative to the selected no-trouble-found-event;

(e) generating distinct fault clusters from the selected faults; and

(f) determining the correlation between the selected no-trouble-found-event and the distinct fault clusters.

5. The method of claim 4 wherein the fault data includes operational parametric information within a predetermined time of the fault occurrence.

6. The method of claim 4 wherein the data representing the faults includes a list of faults.

7. The method of claim 4 wherein the no-trouble-found-event data includes operational parametric information within a predetermined time of the no-trouble-found-event occurrence.

8. The method of claim 4 wherein the no-trouble-found-event data includes a list of the no-trouble-found-events.

9. The method of claim 4 wherein the predetermined time is variable.

10. The method of claim 4 wherein the step (e) further comprises:

(e1) counting the number of the selected faults;

(e2) determining the number of unique combinations that can be created based on the number of selected faults, wherein each unique combination is a distinct fault cluster; and

(e3) creating the unique fault clusters based on the results of step (e2).

11. The method of claim 4 wherein the step (f) further comprises:

(f1) creating a plurality of cases, wherein each case comprises a single no-trouble-found-event and the faults selected in step (d);

(f2) creating distinct fault clusters for each of the plurality of cases, wherein the number of distinct fault clusters within each case is equivalent to the number of unique combinations for the faults within the case;

(f3) determining the number of occurrences of the combination of the selected no-trouble-found-event and each fault cluster within the plurality of cases;

(f4) determining the number of occurrences of each fault cluster within the plurality of cases; and

(f5) wherein the correlation value is calculated by dividing the results of step (f3) by the results of step (f4).

12. The method of claim 4 further comprising a step (g) determining a possible cause for the selected no-trouble-found-event based on a high correlation with the at least one distinct fault cluster, wherein the possible cause is related to a cause for the faults within the at least one distinct fault cluster.

13. The method of claim 4 wherein a high correlation suggests that repairs known to resolve one or more of the faults within the distinct fault cluster having a high correlation with the selected no-trouble-found-event, may resolve the no-trouble-found-event.

14. The method of claim 4 wherein repairs are executed on the machine in an effort to resolve the no-trouble-found-event.

15. An article of manufacture comprising a computer program product comprising a computer-usable medium having a computer-readable code therein for enhanced analysis of “

no-trouble-found-events”

for one or more machines, wherein the “

no-trouble-found-events”

designation is applied to those machine faults for which no cause could be identified, with equipment thus being characterized as being available for return to service with no remedial action being taken, but for which latent causes may exist that may recur when the equipment is returned to service, said article of manufacture comprising;

a computer-readable program code module for receiving data representing the faults experienced by the machine;

a computer-readable program code module for selecting a no trouble found event;

a computer-readable program code module for selecting faults occurring within a predetermined time relative to the selected no trouble found event;

a computer-readable program code module for generating at least one distinct fault cluster from the selected faults; and

a computer-readable program code module for determining the correlation between the selected no trouble found event and the at least one distinct fault cluster.

16. The article of manufacture of claim 15 wherein the data representing the faults includes operational parametric information representing the operation of the machine within a predetermined time of the fault occurrence.

17. The article of manufacture of claim 15 further including a computer-readable program code module for determining a root cause of the no-trouble-found-event based on a high correlation with the at least one distinct fault cluster.

18. The article of manufacture of claim 15 further including a computer-readable program code module for determining repairs associated with the at least one distinct fault cluster.

19. The article of manufacture of claim 15 wherein repairs associated with the at least one distinct fault cluster are determined from similar machines that experienced the faults within the distinct fault cluster.