Novelty detection systems, methods and computer program products for real-time diagnostics/prognostics in complex physical systems

• US 7,333,917 B2
• Filed: 08/09/2006
• Issued: 02/19/2008
• Est. Priority Date: 08/11/2005
• Status: Expired due to Fees

• Current Assignee: Intel Corporation, University of North Carolina At Chapel Hill (University of North Carolina System)
• Original Assignee: Saffron Technology, Inc. (Intel Corporation), University of North Carolina At Chapel Hill (University of North Carolina System)
• Inventors: Greis, Noel P., Olin, Jack G., Aparicio, Manuel IV
• Primary Examiner(s): Barlow; John
• Assistant Examiner(s): Taylor; Victor J.
• Application Number:
  US11/463,448
• Publication Number:
  US 20070038838A1
• Time in Patent Office: 559 Days
• Field of Search: 702/183, 702/184
• US Class Current: 702/183
• CPC Class Codes: G06F 11/008 Reliability or availability analysis

Abstract

Sensors are configured to repeatedly monitor variables of a physical system during its operation. A novelty detection system is responsive to the sensors and is configured to repeatedly observe into an associative memory, states of associations among the variables that are repeatedly monitored, during a learning phase. The novelty detection system is further configured to thereafter observe at least one state of associations among the variables that are sensed relative to the states of associations that are in the associative memory, to identify a novel state of associations among the variables. The novelty detection system may determine whether the novel state is indicative of normal operation or of a potential abnormal operation. Multiple layers of learning for real-time diagnostics/prognostics also may be provided.

Claims

1. A diagnostic/prognostic system for a physical system comprising:

a plurality of sensors that are configured to repeatedly monitor variables of the physical system during operation;

a first associative memory;

a novelty detection system that is responsive to the plurality of sensors and that is configured to repeatedly observe into the first associative memory, states of associations among the variables that are repeatedly monitored during a learning phase, that is further configured to thereafter imagine at least one state of associations among the variables that are monitored relative to the states of associations that are observed in the first associative memory, to identify a novel state of associations among the variables, and that is further configured to determine whether the novel state is indicative of normal operation or of a potential abnormal operation;

a second associative memory that includes therein associations of attributes of failure modes of the physical system; and

a failure mode learning system that is responsive to the novelty detection system and to the second associative memory and that is configured to imagine attributes of the novel state relative to the associations of attributes of failure modes of the physical system to identify and/or predict a potential failure mode of the physical system.

2. A diagnostic/prognostic system according to claim 1 wherein the failure mode learning system comprises:

a failure mode identification and diagnostics system; and

a trend learning and prognostics system.

3. A diagnostic/prognostic system according to claim 1 further comprising:

a third associative memory that includes therein associations of attributes of corrective actions and/or responses to failure modes of the physical system; and

an intervention learning system that is responsive to the failure mode learning system and to the third associative memory and that is configured to imagine attributes of the potential failure mode relative to the responses in the third associative memory to identify a potential corrective action and/or response to the potential failure mode.

4. A diagnostic/prognostic system according to claim 1 wherein the novelty detection system is further configured to observe the novel state that is indicative of normal operation into the first associative memory.

5. A diagnostic/prognostic system according to claim 1 wherein the novelty detection system is further configured to assign the variable values that are repeatedly monitored to bins, and wherein the novelty detection system is configured to repeatedly observe by repeatedly observing into the first associative memory, states of associations among the binned values during the learning phase.

6. A diagnostic/prognostic system according to claim 1 wherein the failure mode learning system is further configured to identify a new failure mode for the physical system.

7. A diagnostic/prognostic system according to claim 1 wherein the failure mode learning system is further configured to provide trend learning for prognostics.

8. A diagnostic/prognostic system according to claim 3 wherein the intervention learning system is further configured to apply the potential response to the physical system in real-time.

9. A diagnostic/prognostic system according to claim 3 wherein the novelty detection system, the failure mode learning system, the intervention learning system and the first, second and third associative memories operate on the physical system in real-time.

10. A computer program product, the computer program product comprising computer program code embodied in a computer-readable medium, the computer program code configured to provide the first associative memory, the second associative memory, the novelty detection system and/or the failure mode learning system of claim 1.

11. A diagnostic/prognostic method of a physical system the includes a plurality of sensors that are configured to repeatedly monitor variables of the physical system during operation, the diagnostic/prognostic method comprising:

repeatedly observing into a first associative memory, states of associations among the variables that are repeatedly monitored, during learning phase;

imagining at least one state of associations among the variables that are monitored relative to the states of associations that are observed in the first associative memory to identify a novel state of associations among the variables;

determining whether the novel state is indicative of normal operation or of a potential abnormal operation; and

imagining attributes of the novel state relative to associations of attributes of failure modes of the physical system in a second associative memory to identify and/or predict a potential failure mode for the physical system.

12. A diagnostic/prognostic method according to claim 11 further comprising:

imagining attributes of the potential failure relative to associations of attributes of responses to failure modes of the physical system in a third associative memory to identify a potential corrective action and/or response to the potential failure mode.

13. A diagnostic/prognostic method according to claim 11 wherein imagining attributes of the novel state relative to associations of attributes of failure modes of the physical system comprises determining failure trends and predictions relative to associations of time-based attributes of failure modes of the physical system.

14. A diagnostic/prognostic method according to claim 11 further comprising:

observing the novel state that is indicative of normal operation into the first associative memory.

15. A diagnostic/prognostic method according to claim 12 further comprising:

applying the potential response to the physical system in real-time.

16. A diagnostic/prognostic method according to claim 12 wherein identifying a potential response to the future failure potential is performed on the physical system in real-time.

17. A computer program product, the computer program product comprising computer program code embodied in a computer-readable medium, the computer program code configured to perform the method of claim 11.