DISTRIBUTED DECISION MAKING ARCHITECTURE FOR EMBEDDED PROGNOSTICS

• US 20100042366A1
• Filed: 08/15/2008
• Published: 02/18/2010
• Est. Priority Date: 08/15/2008
• Status: Abandoned Application

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Hadden, George D., Magnuson, Randy, Felke, Timothy J., Colclough, John C., Kolbet, David M.
• Application Number:
  US12/192,665
• Publication Number:
  US 20100042366A1
• Time in Patent Office: Days
• US Class Current: 702/182
• 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
• CPC Class Codes: G06F 11/008 Reliability or availability analysis
• CPC Class Codes: G06F 11/3013 where the computing system is an embedded system, i.e. a combination of hardware and software dedicated to perform a certain function in mobile devices, printers, automotive or aircraft systems testing or monitoring of control systems or parts thereof G05B23/02
• CPC Class Codes: G06F 11/3072 where the reporting involves data filtering, e.g. pattern matching, time or event triggered, adaptive or policy-based reporting

Abstract

A distributed decision making architecture for embedded prognostics in a platform is provided. An estimation system determines at least one performance characteristic of at least one device in the platform. A supervisory system is in communication with, and superior to, the estimation system. The supervisory system calculates a prediction of remaining useful life (RUL) of the at least one device in the platform. The supervisory system is adapted for collecting the at least one performance characteristic from the estimation system to generate a performance estimate, and implementing at least one data-driven equation to match the at least one performance estimate against of at least one known degradation condition to generate the prediction of remaining useful life of the at least one device.

Claims

1. A distributed decision making architecture for embedded prognostics in a platform, comprising:

an estimation system for determining at least one performance characteristic of at least one device in the platform; and

a supervisory system, in communication with and superior to, the estimation system for calculating a prediction of remaining useful life (RUL) of the at least one device in the platform, wherein the supervisory system is adapted for;

collecting the at least one performance characteristic from the estimation system to generate a performance estimate, and

implementing at least one data-driven equation to match the at least one performance estimate against at least one known degradation condition to generate the prediction of remaining useful life of the at least one device.

2. The architecture of claim 1, wherein the supervisory system is further adapted for publishing the prediction of remaining useful life of the device to a prognostic monitor.

3. The architecture of claim 1, wherein the estimation system is adapted for collecting a plurality of signal values from the at least one device.

4. The architecture of claim 1, wherein the estimation system is embedded in a platform of a vehicle.

5. The architecture of claim 1, further including a classifier in communication with the supervisory system, wherein the supervisory system is further adapted for:

generating at least one degradation signature, the at least one degradation signature representing a mapping of the performance estimate against the at least one known degradation condition, and

providing the at least one degradation signature to the classifier.

6. A system for predicting a remaining useful life (RUL) of at least one device embedded in a platform, comprising:

an estimator module having at least one input for collecting a plurality of signal values from the device and an output providing a determination of at least one performance estimate based on the plurality of signal values; and

a supervisory module, in communication with and superior to, the estimator module, the supervisory module receiving the at least one performance estimate from the estimator module, wherein at least one data-driven equation is implemented to match the at least one performance characteristic against at least one known degradation condition to generate the prediction of remaining useful life of the at least one device.

7. The system of claim 6, wherein the supervisory module is further adapted for publishing the prediction of remaining useful life to a prognostic monitor.

8. The system of claim 6, wherein the plurality of signal values are collected in real time.

9. The system of claim 6 wherein the estimator module is a subcomponent of a vehicle platform.

10. The system of claim 9, wherein the estimator module is embedded in a line replaceable unit (LRU) of the vehicle.

11. The system of claim 6, wherein the prediction of remaining useful life of the at least one device is indicated by a degradation signature.

12. A method for calculating a prediction of remaining useful life (RUL) of at least one device embedded in a platform, comprising:

collecting a plurality of input signal values from the at least one device;

determining at least one performance characteristic based on the plurality of input signal values in at least one estimator system;

generating at least one performance estimate from the at least one performance characteristic;

forwarding the at least one performance estimate to a supervisory system; and

implementing at least one data-driven equation in the supervisory system to match the at least one performance estimate against at least one known degradation condition to generate the prediction of remaining useful life of the at least one device.

13. The method of claim 12, further including publishing the prediction of remaining useful life to a prognostic monitor.

14. The method of claim 12, further including embedding the at least one estimator system in a line-replaceable unit (LRU) of a vehicle.

15. The method of claim 12, further including embedding the at least one estimator system in a platform of a vehicle.

16. The method of claim 12, further including generating at least one degradation signature, the at least one degradation signature representing a mapping of the performance characteristic with the at least one known degradation condition.

18. The computer program product of claim 15, further including a seventh executable portion for publishing the prediction of remaining useful life to a prognostic monitor.

19. The computer program product of claim 15, further including a seventh executable portion for generating at least one degradation signature, the at least one degradation signature representing a mapping of the performance estimate with the at least one known degradation condition.

20. The computer program product of claim 15, wherein the first executable portion is stored in a line-replaceable unit (LRU) of a vehicle.

17. A computer program product for calculating a prediction of remaining useful life (RUL) of at least one device embedded in a platform, the computer program product comprising a computer-readable storage medium having computer-readable program portions stored therein, the computer-readable program code portions comprising:

a first executable portion for collecting a plurality of input signal values from the at least one device;

a second executable portion for determining at least one performance characteristic based on the plurality of input signal values in at least one estimator system;

a third executable portion for forwarding the at least one performance characteristic to a supervisory system;

a fourth executable portion for generating at least one performance estimate from the at least one performance characteristic;

a fifth executable portion for forwarding the at least one performance estimate to a supervisory system; and

a sixth executable portion for implementing at least one data-driven equation in the supervisory system to match the at least one performance estimate against at least one known degradation condition to generate the prediction of remaining useful life of the at least one device.