EFFICIENT HEALTH MANAGEMENT, DIAGNOSIS AND PROGNOSIS OF A MACHINE

• US 20130268241A1
• Filed: 04/10/2013
• Published: 10/10/2013
• Est. Priority Date: 04/10/2012
• Status: Active Grant

• Current Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Original Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Inventors: Das, Sreerupa, Patel, Amar, McNamara, Steven, Todd, Jonathan
• Granted Patent: US 9,734,001 B2
• Time in Patent Office: Days
• US Class Current: 702/185
• CPC Class Codes: G01M 99/005 Testing of complete machines, e.g. washing-machines or mobile phones testing of machine parts G01M13/00; testing of electric apparatus or components G01R31/50
• CPC Class Codes: G05B 23/024 Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
• CPC Class Codes: G05B 23/0254 based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks
• CPC Class Codes: G06F 11/00 Error detection; Error correction; Monitoring error detection, correction or monitoring in information storage based on relative movement between record carrier and transducer G11B20/18; monitoring, i.e. supervising the progress of recording or reproducing G11B27/36; in static stores G11C29/00

Abstract

Mechanisms for generating an analysis result about a machine are provided. A device generates a first health management (HM) analysis result regarding a machine based on real-time first sensor information received during a first period of time and on a first version HM analytic model. The device provides, to an off-board device, a plurality of sensor information comprising the real-time first sensor information and that is generated during the first period of time. The device receives a second version HM analytic model that is based at least in part on the plurality of sensor information and fault information that identifies actual faults that have occurred on the machine. The device generates a second HM analysis result regarding the machine based on real-time second sensor information received during a second period of time and on the second version HM analytic model.

Claims

1. A method for generating an analysis result about a machine, comprising:

generating, by a device, a first health management (HM) analysis result regarding the machine based on real-time first sensor information received during a first period of time and on a first version HM analytic model;

providing, to an off-board device, a plurality of sensor information comprising the real-time first sensor information and that is generated during the first period of time;

receiving, by the device, a second version HM analytic model that is based at least in part on the plurality of sensor information and on fault information that identifies actual faults of the machine; and

generating a second HM analysis result regarding the machine based on real-time second sensor information received during a second period of time and on the second version HM analytic model.

2. The method of claim 1, wherein the first HM analysis result comprises a first diagnostic analysis result, the first version HM analytic model comprises a first version diagnostic analytic model, the second version HM analytic model comprises a second version diagnostic analytic model, and the second HM analysis result comprises a second diagnostic analysis result, further comprising:

generating a first prognostic analysis result regarding the machine based on the real-time first sensor information during the first period of time and on a first version prognostic analytic model;

receiving a second version prognostic analytic model that is based at least in part on the plurality of sensor information and on the fault information that identifies the actual faults of the machine; and

generating a second prognostic analysis result regarding the machine based on the real-time second sensor information during the second period of time and on the second version prognostic analytic model.

3. The method of claim 2, further comprising:

replacing the first version diagnostic analytic model with the second version diagnostic analytic model on the device prior to generating the second diagnostic analysis result.

4. The method of claim 3, wherein the first diagnostic analysis result is generated by a diagnostic engine that executes on the device, and the first prognostic analysis result is generated by a prognostic engine that executes on the device, and wherein replacing the first version diagnostic analytic model with the second version diagnostic analytic model on the device further comprises replacing the first version diagnostic analytic model with the second version diagnostic analytic model on the device without interruption to the prognostic engine.

5. The method of claim 4, further comprising replacing the first version prognostic analytic model with the second version prognostic analytic model on the device prior to generating the second prognostic analysis result without interruption to the diagnostic engine.

6. The method of claim 4, wherein replacing the first version diagnostic analytic model with the second version diagnostic analytic model comprises replacing the first version diagnostic analytic model with the second version diagnostic analytic model without interruption to the diagnostic engine.

7. The method of claim 1, wherein the plurality of sensor information identifies characteristics of components of the machine during the first period of time.

8. The method of claim 1, wherein the real-time first sensor information identifies at least one of a status of a battery, a fluid level, an engine oil characteristic, an engine RPM, a coolant characteristic, a transmission characteristic, an ambient characteristic, a fuel pump characteristic, and an alternator characteristic.

9. The method of claim 1, wherein the first HM analysis result comprises data predicting a future fault of a component of the machine, and a probability of the future fault.

10. The method of claim 9, wherein the second version HM analytic model comprises a Gaussian mixture model.

11. The method of claim 1, wherein the first HM analysis result comprises data identifying a current fault of the machine and a probability that the current fault is associated with a particular component.

12. A device for generating an analysis result about a machine, comprising:

a communications interface configured to communicate with an off-board device;

a control system comprising a processor coupled to the communications interface and configured to;

generate a first health management (HM) analysis result regarding the machine based on real-time first sensor information received during a first period of time and on a first version HM analytic model;

provide, to the off-board device, a plurality of sensor information comprising the real-time first sensor information and being generated during the first period of time;

receive a second version HM analytic model that is based at least in part on the plurality of sensor information; and

generate a second HM analysis result regarding the machine based on real-time second sensor information received during a second period of time and on the second version HM analytic model.

13. The device of claim 12, wherein the first HM analysis result comprises a first diagnostic analysis result, the first version HM analytic model comprises a first version diagnostic analytic model, the second version HM analytic model comprises a second version diagnostic analytic model, and the second HM analysis result comprises a second diagnostic analysis result, and wherein the processor is further configured to:

generate a first prognostic analysis result regarding the machine based on the real-time first sensor information during the first period of time and on a first version prognostic analytic model;

receive a second version prognostic analytic model that is based at least in part on the plurality of sensor information; and

generate a second prognostic analysis result regarding the machine based on the real-time second sensor information during the second period of time and on the second version prognostic analytic model.

14. The device of claim 13, wherein the processor is further configured to:

replace the first version diagnostic analytic model with the second version diagnostic analytic model on the device prior to generating the second diagnostic analysis result.

15. The device of claim 14, wherein the control system further comprises:

a diagnostic engine that is configured to generate the first diagnostic analysis result and the second diagnostic analysis result based on the first version diagnostic analytic model and the second version diagnostic analytic model respectively;

a prognostic engine that is configured to generate the first prognostic analysis result and the second prognostic analysis result based on the first version prognostic analytic model and the second version prognostic analytic model respectively; and

wherein the control system is configured to;

replace the first version diagnostic analytic model with the second version diagnostic analytic model without interruption to the prognostic engine.

16. The device of claim 15, wherein the control system is further configured to replace the first version prognostic analytic model with the second version prognostic analytic model without interruption to the diagnostic engine.

17. The device of claim 15, wherein the control system is further configured to replace the first version diagnostic analytic model with the second version diagnostic analytic model without interruption to the diagnostic engine.

18. The device of claim 12, wherein the real-time first sensor information identifies at least one of a status of a battery, a fluid level, an engine oil characteristic, an engine RPM, a coolant characteristic, a transmission characteristic, a fuel pump characteristic, and an alternator characteristic.

19. A device comprising:

a communications interface configured to communicate with a health management (HM) device associated with a machine; and

a control system comprising a processor and coupled to the communications interface and configured to;

receive, from the HM device, a plurality of sensor information that identifies real-time characteristics associated with a plurality of components of the machine over a first period of time;

update, based on the plurality of sensor information and fault information that identifies actual faults that have occurred on the machine, a first version HM analytic model that correlates sensor information with conditions of the machine, to generate a second version HM analytic model; and

provide the second version HM analytic model to the HM device for use during a second period of time.

20. The device of claim 19, wherein the control system is further configured to:

receive the fault information from the HM device.

21. A method comprising:

receiving, from a health management (HM) device, a plurality of sensor information that identifies real-time characteristics associated with a plurality of components of a machine over a first period of time;

updating, based on the plurality of sensor information and fault information that identifies actual faults that have occurred on the machine, a first version HM analytic model that correlates sensor information with conditions of the machine, to generate a second version HM analytic model; and

providing the second version HM analytic model to the HM device for use during a second period of time.