System and Method for Inferring Vehicle Health

• US 20160063418A1
• Filed: 09/03/2014
• Published: 03/03/2016
• Est. Priority Date: 09/03/2014
• Status: Abandoned Application

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Roddy, Nicholas Edward, Garvey, Dustin Ross, Xu, Rui
• Application Number:
  US14/476,030
• Publication Number:
  US 20160063418A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06Q 10/06315 Needs-based resource requirements planning or analysis

Abstract

A system and method for inferring vehicle health are disclosed. The computer-implemented method comprises identifying a plurality of candidate vehicles for consideration for use for a task, and receiving corresponding event data for at least one of the plurality of candidate vehicles. The event data may correspond to at least one occurrence of at least one suspected problem for the corresponding candidate vehicle. A corresponding health score can be generated for each one of the plurality of candidate vehicles. The corresponding health score for the at least one of the plurality of candidate vehicles can be generated based on the corresponding event data for the at least one of the plurality of candidate vehicles. The generated health scores can indicate a likelihood of failure for their corresponding candidate vehicles.

Claims

1. A computer-implemented method comprising:

identifying a plurality of candidate vehicles for consideration for use for a task;

receiving corresponding event data for at least one of the plurality of candidate vehicles, the event data corresponding to at least one occurrence of at least one suspected problem for the corresponding candidate vehicle; and

generating, by a machine having a memory and at least one processor, a corresponding health score for each one of the plurality of candidate vehicles, the corresponding health score for the at least one of the plurality of candidate vehicles being generated based on the corresponding event data for the at least one of the plurality of candidate vehicles, the generated health scores indicating a likelihood of failure for their corresponding candidate vehicles.

2. The computer-implemented method of claim 1, wherein the event data comprises an identification of the at least one suspected problem.

3. The computer-implemented method of claim 1, wherein the event data comprises an indication of a severity level of the at least one suspected problem.

4. The computer-implemented method of claim 1, wherein the event data comprises a quantity of occurrences of the at least one suspected problem.

5. The computer-implemented method of claim 1, wherein the event data comprises a status of the at least one suspected problem.

6. The computer-implemented method of claim 1, wherein the event data comprises an indication of at least one remedy that has been applied to resolve the at least one suspected problem.

7. The computer-implemented method of claim 1, wherein the corresponding health score for at least a portion of the plurality of candidate vehicles is generated based on at least one characteristic of the corresponding candidate vehicle.

8. The computer-implemented method of claim 7, wherein the at least one characteristic comprises an age of the corresponding candidate vehicle or a measurement of usage of the corresponding candidate vehicle.

9. The computer-implemented method of claim 1, wherein generating the corresponding health score for the at least one of the plurality of candidate vehicles comprises:

retrieving, from a database, a corresponding value for the corresponding event data for each one of the at least one of the plurality of candidates, the database comprising correlations between the corresponding event data and the corresponding values; and

generating the corresponding health score for the at least one of the plurality of candidate vehicles based on the corresponding value.

10. The computer-implemented method of claim 9, wherein the corresponding value comprises a corresponding log likelihood ratio (LLR) of a probability that the corresponding event data is present in vehicles that have had an operational failure within a specified time period to a probability that the corresponding event data is present in vehicles that have not had an operation failure within the specified time period.

11. The computer-implemented method of claim 10, further comprising:

receiving corresponding historical data for each one of a plurality of reference vehicles, the historical data comprising historical event data and failure data, the historical event data corresponding to at least one occurrence of the at least one suspected problem for the corresponding reference vehicle, and the failure data indicating whether or not the corresponding reference vehicle had an operational failure;

determining the corresponding LLR for the corresponding event data based on an analysis of the historical data; and

storing the corresponding LLR for the corresponding event data in the database.

12. The computer-implemented method of claim 11, wherein the analysis of the historical data comprises a determination of one or more correlations between the corresponding historical event data and the corresponding failure data.

13. The computer-implemented method of claim 1, further comprising:

generating a ranked list of the plurality of candidate vehicles based on their corresponding health scores; and

identifying a topmost portion or a bottommost portion of the plurality of candidate vehicles in the ranked list.

14. The computer-implemented method of claim 13, further comprising assigning the identified portion of the plurality of candidate vehicles to be used for the task.

15. The computer-implemented method of claim 1, further comprising identifying a portion of the plurality of candidate vehicles based on the corresponding health scores for the candidate vehicles of the identified portion satisfying a predetermined threshold.

16. The computer-implemented method of claim 15, further comprising assigning the identified portion of the plurality of candidate vehicles to be used for the task.

17. The computer-implemented method of claim 1, wherein the plurality of candidate vehicles comprises a plurality of locomotives.

18. A system comprising:

a machine having at least one module, the at least one module comprising at least one processor and being configured to perform operations comprising;

identifying a plurality of candidate vehicles for consideration for use for a task;

receiving corresponding event data for at least one of the plurality of candidate vehicles, the event data corresponding to at least one occurrence of at least one suspected problem for the corresponding candidate vehicle;

calculating a corresponding health score for each one of the plurality of candidate vehicles, the corresponding health score for the at least one of the plurality of candidate vehicles being generated based on the corresponding event data for the at least one of the plurality of candidate vehicles, the generated health scores indicating a likelihood of failure for their corresponding candidate vehicles; and

identifying a portion of the plurality of candidate vehicles based on their corresponding health scores.

19. The system of claim 18, wherein the event data comprises at least one of an identification of the at least one suspected problem, an indication of a severity level of the at least one suspected problem, a quantity of occurrences of the at least one suspected problem, a status of the at least one suspected problem, and an indication of at least one remedy that has been applied to resolve the at least one suspected problem.

20. A non-transitory machine-readable storage medium, tangibly embodying a set of instructions that, when executed by at least one processor, causes the at least one processor to perform operations comprising:

identifying a plurality of candidate vehicles for consideration for use for a task;

receiving corresponding event data for at least one of the plurality of candidate vehicles, the event data corresponding to at least one occurrence of at least one suspected problem for the corresponding candidate vehicle;

generating a corresponding health score for each one of the plurality of candidate vehicles, the corresponding health score for the at least one of the plurality of candidate vehicles being generated based on the corresponding event data for the at least one of the plurality of candidate vehicles, the generated health scores indicating a likelihood of failure for their corresponding candidate vehicles; and

generating a ranked list of the plurality of candidate vehicles based on their corresponding health scores.