Method and system for autonomously resolving a failure

• US 6,886,472 B2
• Filed: 02/20/2003
• Issued: 05/03/2005
• Est. Priority Date: 02/20/2003
• Status: Expired due to Fees

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Bharadwaj, Raj Mohan, Jammu, Vinay Bhaskar
• Primary Examiner(s): Jules, Frantz F.
• Application Number:
  US10/370,824
• Publication Number:
  US 20040164206A1
• Time in Patent Office: 803 Days
• Field of Search: 701/27, 701/34, 701/50, 701/45, 701/31, 701/29, 105/26.05, 104/26.1
• US Class Current: 105/26.05
• CPC Class Codes: B60L 2200/26 Rail vehicles
• CPC Class Codes: B60L 3/0023 Detecting, eliminating, remedying or compensating for drive train abnormalities, e.g. failures within the drive train
• CPC Class Codes: B61L 15/0081 On-board diagnosis or maintenance
• CPC Class Codes: G05B 23/0286 Modifications to the monitored process, e.g. stopping operation or adapting control

Abstract

In a railroad locomotive having a plurality of systems which collectively are used for locomotive operations, a method of self-healing a system of the plurality of systems comprising monitoring operational conditions of the system, detecting at least one of a pending and a current failure, determining a self-healing procedure to correct the failure, and applying the self-healing procedure comprising at least one of a safe mode technique, a redundancy technique, and an automatic configuration technique.

Claims

1. In a railroad locomotive having a plurality of systems which collectively are used for locomotive operations a method of autonomously self-healing each of said plurality of systems comprising:

a. monitoring operational conditions of each of said plurality of system;

b. detecting at least one of a pending and a current failure in at least one of said systems;

c. determining a self-healing procedure to correct said failure in at least one of said systems; and

d. applying said self-healing procedure comprising at least one of a self-healing control technique, a redundancy technique, and an automatic fix technique to correct said failure in at least one of said systems.

2. The method of claim 1 further comprising verifying that said self-healing procedure corrected said failure.

3. The method of claim 2 further comprising logging an alert if at least one of said self-healing techniques did not correct said failure and said level of confidence does not exceed said desired threshold.

4. The method of claim 1 wherein said self-healing control technique comprises using a control strategy that uses an alternate control strategy that bypasses said failure.

5. The method of claim 1 wherein said self-healing control technique comprises operating said system in a safe mode condition.

6. The method of claim 1 wherein said safe-healing control technique comprises operating said system at a less than an optimal operating condition.

7. The method of claim 1 wherein said self-healing control technique comprises providing a control algorithm in a controller and operating said controller at less than an optimal level white using an alternate control algorithm to perform said controller functions.

8. The method of claim 7 wherein said hardware and software redundancy technique further comprises ceasing use of said system experiencing said failure and using a redundant system.

9. The method of claim 7 wherein said hardware and software redundancy technique further comprises ceasing use of a software program associated with said system experiencing said failure and using a redundant copy of said software program.

10. The method of claim 7 wherein said hardware and software redundancy technique further comprises applying an analytical model to estimate a measurable value generated by said system when said value can not be measured due to said failure.

11. The method of claim 1 wherein said self-healing control technique comprises using a hardware and software redundancy technique.

12. The method of claim 11 wherein said hardware and software redundancy technique further comprises reprogramming said redundant system to replace said system experiencing said failure.

13. The method of claim 1 wherein said self-healing procedure comprises using an automatic fix technique.

14. The method of claim 1 wherein said automatic fix technique comprises automatically resetting said system when a pending fault is detected.

15. The method of claim 1 wherein said automatic fix technique comprises automatically upgrading a software version.

16. The method of claim 13 the step of wherein automatically upgrading a software version further comprises at least one of maintaining a repository of various versions of software, maintaining a matrix identifying a software version to use with said system and determining said software version based on said matrix.

17. The method of claim 1 wherein at least two of said self-healing control technique, said redundancy technique and said automatic fix technique are applied simultaneously.

18. The method of claim 1 wherein detecting a failure further comprising detecting an impending failure.

19. The method of claim 1 wherein determining a self-healing procedure further comprises determining a level of confidence as to determine a cause of said failure.

20. The method of claim 19 wherein said level of confidence is greater than 51 percent.

21. The method of claim 19 further comprising requiring a user to answer questions specific to said locomotive when said level of confidence is below said desired threshold.

22. The method of claim 1 wherein determining said self-healing technique further comprises evaluating said failure with a matrix comprising a list of failures fixable with said self-healing technique.

23. In a railroad locomotive having a plurality of subsystems which collectively are used for locomotive operations, a system for self-healing each subsystem of said plurality of subsystems comprising:

a. a sensor connected to at least one of said subsystems to monitor and collect operating condition data;

b. a diagnostics system that receives said data sad isolates at least one of a pending and a current failure in at least one of said subsystems;

c. a processor connected to said diagnostics system to determine a self-healing technique for said failure; and

d. wherein said self-healing technique comprising at least one of a self-healing control technique a redundancy technique, and an automatic fix technique.

24. The system of claim 23 further comprising a memory device connected to said processor.

25. The system of claim 23 wherein said diagnostics system uses at least one of a rule-based reasoning, case-based reasoning, and a belief network to isolate said fault.

26. The system of claim 23 wherein said processor is integrated in said diagnostics system.

27. The system of claim 23 wherein said self-healing control technique comprises at least one of a technique comprising operating in a safe mode, operating in at a less than optimal operating condition and operating with an alternate control algorithm.

28. The system of claim 23 wherein said redundancy technique comprises using at least one of a redundant hardware and a redundant software program when a fault is associated with at least one of another piece of hardware and another software program.

29. The system of claim 28 wherein said redundant hardware is programmed to replace a function of said hardware associated with said fault.

30. The system of claim 23 wherein said automatic fix technique comprises at least one of automatically resetting at least one of a component and a subsystem and automatically upgrading a software version.