Method, Apparatus And Computer Program Product For Predicting And Avoiding A Fault

• US 20090228160A1
• Filed: 03/10/2008
• Published: 09/10/2009
• Est. Priority Date: 03/10/2008
• Status: Active Grant

• Current Assignee: Neil H. Eklund, Xiao Hu
• Original Assignee: Neil H. Eklund, Xiao Hu
• Inventors: Hu, Xiao, Eklund, Neil H.
• Granted Patent: US 8,155,820 B2
• Time in Patent Office: Days
• US Class Current: 701/3
• CPC Class Codes: G06F 11/008 Reliability or availability analysis

Abstract

A method, apparatus and computer program product are provided to not only predict an impending fault, but also to avoid the occurrence of the fault such that continued operations are permitted with a reduced likelihood of the occurrence of the fault. In this regard, a plurality of features are provided to at least one model, such as a random forest classification model. The plurality of features include features representative of at least one prior operational sequence as well as features representative of at least one upcoming operational sequence. The plurality of features are then processed with at least one model to determine a likelihood of a fault during the upcoming operational sequence. The method also alters the characteristics of the upcoming operational sequence without requiring maintenance of the equipment to thereby permit the upcoming operational sequence to be conducted with a reduced likelihood of the fault.

Claims

1. A method of avoiding a fault during equipment operation, the method comprising:

providing data representative of a plurality of features to at least one model, wherein the plurality of features are representative of an upcoming operational sequence;

processing the data representative of the plurality of features with the at least one model to determine a likelihood of a fault during the upcoming operational sequence; and

altering characteristics of the upcoming operational sequence without requiring maintenance of the equipment to thereby permit the upcoming operational sequence to be conducted with a reduced likelihood of the fault.

2. A method according to claim 1 wherein the upcoming operational sequence comprises a next operational sequence.

3. A method according to claim 1 wherein the upcoming operational sequence comprises any one of a plurality of subsequent operational sequences.

4. A method according to claim 1 wherein the equipment comprises an aircraft, and wherein the features representative of the upcoming operational sequence comprises at least one of weight, forecasted throttle angle or forecasted ambient temperature.

5. A method according to claim 4 wherein altering the characteristics of the upcoming operational sequence comprises reducing the weight to permit flight of the aircraft with a reduced likelihood of the fault and without requiring maintenance of the aircraft.

6. A method according to claim 1 further comprising training the at least one model with parametric data, nonparametric data or both parametric data and nonparametric data from at least one prior operational sequence.

7. A method according to claim 1 wherein processing the data representative of the plurality of features comprises processing the plurality of features with a random forest classification model.

8. A method according to claim 1 wherein processing the data representative of the plurality of features comprises processing the data representative of the plurality of features with a plurality of models and then fusing outputs of the plurality of models to determine a likelihood of a fault during the upcoming operational sequence.

9. An apparatus for avoiding a fault during equipment operation, the apparatus comprising:

a processing element configured to provide data representative of a plurality of features to at least one model, wherein the plurality of features comprise features representative of an upcoming operational sequence, said processing element also configured to process the data representative of the plurality of features with the at least one model to determine a likelihood of a fault during the upcoming operational sequence, said processing element further configured to provide an output indicating that characteristics of the upcoming operational sequence should be altered to permit the upcoming operational sequence to be conducted with a reduced likelihood of the fault and without requiring maintenance of the equipment.

10. An apparatus according to claim 9 wherein the upcoming operational sequence comprises a next operational sequence.

11. An apparatus according to claim 9 wherein the upcoming operational sequence comprises any one of a plurality of subsequent operational sequences.

12. An apparatus according to claim 9 wherein the equipment comprises an aircraft, and wherein the features representative of the upcoming operational sequence comprises at least one of weight, forecasted throttle angle or forecasted ambient temperature.

13. An apparatus according to claim 12 wherein said processing element is configured to provide an output indicating that the weight of the aircraft should be reduced to permit flight of the aircraft with a reduced likelihood of the fault and without requiring maintenance of the aircraft.

14. An apparatus according to claim 9 wherein said processing element is further configured to train the at least one model with parametric data, nonparametric data or both parametric data and nonparametric data from at least one prior operational sequence.

15. An apparatus according to claim 9 wherein said processing element is configured to process the data representative of the plurality of features with a random forest classification model.

16. An apparatus according to claim 9 wherein said processing element is configured to process the data representative of the plurality of features with a plurality of models and to then fuse outputs of the plurality of models to determine a likelihood of a fault during the upcoming operational sequence.

17. A computer program product comprising at least one computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:

a first executable portion for providing data representative of a plurality of features to at least one model, wherein the plurality of features comprise features representative of an upcoming operational sequence;

a second executable portion for processing the data representative of the plurality of features with the at least one model to determine a likelihood of a fault during the upcoming operational sequence; and

a third executable portion for providing an output indicating that characteristics of the upcoming operational sequence should be altered to permit the upcoming operational sequence to be conducted with a reduced likelihood of the fault and without requiring maintenance of the equipment.

18. A computer program product according to claim 17 wherein the upcoming operational sequence comprises a next operational sequence.

19. A computer program product according to claim 17 wherein the upcoming operational sequence comprises any one of a plurality of subsequent operational sequences.

20. A computer program product according to claim 17 wherein the equipment comprises an aircraft, and wherein the features representative of the upcoming operational sequence comprises at least one of weight, forecasted throttle angle or forecasted ambient temperature.

21. A computer program product according to claim 20 wherein the third executable portion is further configured to provide an output indicating that the weight of the aircraft should be reduced to permit flight of the aircraft with a reduced likelihood of the fault and without requiring maintenance of the aircraft.

22. A computer program product according to claim 17 further comprising a fourth executable portion for training the at least one model with parametric data, nonparametric data or both parametric data and nonparametric data from at least one prior operational sequence.

23. A computer program product according to claim 17 wherein the second executable portion is further configured to process the data representative of the plurality of features with a plurality of models and to then fuse outputs of the plurality of models to determine a likelihood of a fault during the upcoming operational sequence.