Prediction of functional availability of complex system

• US 8,195,595 B2
• Filed: 06/30/2008
• Issued: 06/05/2012
• Est. Priority Date: 06/30/2008
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Felke, Timothy J., Hadden, George D., Kolbet, David M., Magnuson, Randy
• Primary Examiner(s): Gaffin, Jeffrey A
• Assistant Examiner(s): BUSS, BENJAMIN J
• Application Number:
  US12/165,440
• Publication Number:
  US 20090327202A1
• Time in Patent Office: 1,436 Days
• Field of Search: 706/1, 706/2, 706/52, 706/900, 706/903, 700/1, 700/28
• US Class Current: 706/52
• CPC Class Codes: G06N 5/046 Forward inferencing; Production systems
• CPC Class Codes: G06N 7/02 using fuzzy logic computing arrangements based on biological models G06N3/00; computing arrangements using knowledge-based models G06N5/00
• CPC Class Codes: Y10S 706/90 Fuzzy logic

Abstract

A method, system, and computer program product for predicting the functional availability of a complex system is provided. Parameters of the complex system are converted from a plurality of binary values to at least one prognostic vector. At least a portion of a binary input expression is converted into an equivalent fuzzy output expression, the fuzzy output expression operable on the at least one prognostic vector.

Claims

1. A method for predicting the functional availability of a vehicle having a plurality of subsystems, comprising:

generating, by each of the plurality of subsystems, a plurality of binary values corresponding to the functional availability of the respective subsystem;

converting, by a plurality of prognostic generation modules each coupled to one of the plurality of subsystems, parameters for their respective subsystem from the plurality of binary values to a plurality of prognostic vectors, each corresponding to one of the plurality of subsystems;

converting, by an availability prediction module, at least a portion of a Boolean availability expression into an equivalent fuzzy output expression, the fuzzy output expression operable on the plurality of prognostic vectors; and

predicting, by the availability prediction module, the functional availability of the vehicle based upon the plurality of prognostic vectors and the fuzzy output expression.

2. The method of claim 1, further including operating the fuzzy output expression on the plurality of prognostic vectors to generate a fused prognostic vector.

3. The method of claim 1, wherein converting parameters for their respective subsystem from the plurality of binary values to a plurality of prognostic vectors includes encoding both of a current status of the parameters and a predicted status of the parameters at a specified future time interval.

4. The method of claim 1, wherein converting at least a portion of the Boolean availability expression into an equivalent fuzzy output expression includes implementing at least one expression transform taking a phrase from the Boolean availability expression and converting the phrase to a function in the fuzzy output expression.

5. The method of claim 4, further including repeating the implementing at least one expression transform taking a phrase from the Boolean availability expression and the converting the phrase to a function in the fuzzy output expression until each portion of the Boolean availability expression has been converted.

6. The method of claim 4, wherein converting at least a portion of the Boolean availability expression into an equivalent fuzzy output expression includes implementing a plurality of mappings between a Boolean form represented in the Boolean availability expression into a statistical form represented in the fuzzy output expression.

7. The method of claim 6, wherein implementing a plurality of mappings between a Boolean form represented in the Boolean availability expression into a statistical form represented in the fuzzy output expression includes implementing at least one of:

[Not (a)] mapped to [1-a],

[And (a,b)] mapped to [min(a,b)], and

[Or (a,b)] mapped to [max(a,b)],

where a and b are vectors containing a current status of the parameters and a predicted status of the parameters at a specified future time interval expressed in a ratio between 0 representing a not available status and 1 representing certainly available status.

8. A system for predicting the functional availability of a vehicle having a plurality of subsystems, comprising:

a plurality of prognostic vector generators, each prognostic vector generator coupled to one of the plurality of subsystems, adapted for converting binary values corresponding to parameters of each subsystem to at least one prognostic vector;

a fuzzy converter, in communication with the plurality of prognostic vector generators, adapted for converting at least a portion of a Boolean availability expression into an equivalent fuzzy output expression, the fuzzy output expression operable on the at least one prognostic vector; and

an availability prediction module in communication with the fuzzy converter and the plurality of prognostic vector generators, configured to predict the functional availability of the vehicle based upon the at least one prognostic vectors and the fuzzy output expression.

9. The system of claim 8, wherein the fuzzy prediction evaluator is further configured to operate the fuzzy output expression on the at least one prognostic vector to generate a fused prognostic vector.

10. The system of claim 8, wherein the prognostic vector generator is further adapted for encoding both of a current status of the parameters and a predicted status of the parameters at a specified future time interval.

11. The system of claim 8, wherein the fuzzy converter is further adapted for implementing at least one expression transform taking a phrase from the Boolean availability expression and converting the phrase to a function in the fuzzy output expression.

12. The system of claim 11, wherein the fuzzy converter is further adapted for repeating the implementing at least one expression transform taking a phrase from the Boolean availability expression and the converting the phrase to a function in the fuzzy output expression until each portion of Boolean availability expression has been converted.

13. The system of claim 11, wherein the fuzzy converter is further adapted for implementing a plurality of mappings between a Boolean form represented in the Boolean availability expression into a statistical form represented in the fuzzy output expression.

14. The system of claim 13, wherein the fuzzy converter is further adapted for implementing at least one of:

[Not (a)] mapped to [1-a],

[And (a,b)] mapped to [min(a,b)], and

[Or (a,b)] mapped to [max(a,b)],

where a and b are vectors containing a current status of the parameters and a predicted status of the parameters at a specified future time interval expressed in a ratio between 0 representing a not available status and 1 representing certainly available status.

15. A computer program product for predicting the functional availability of a complex system, the complex system including a plurality of subsystems, the computer program product comprising a computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:

a first executable portion for converting parameters generated by each of the plurality of subsystems from a plurality of binary values to at least one prognostic vector;

a second executable portion for converting at least a portion of a Boolean availability expression into an equivalent fuzzy output expression, the fuzzy output expression operable on the at least one prognostic vector; and

a third executable portion predicting the functional availability of the complex system based upon the at least one prognostic vector and the fuzzy output expression.

16. The computer program product of claim 15, wherein the third executable portion is further configured for operating the fuzzy output expression on the at least one prognostic vector to generate a fused prognostic vector.

17. The computer program product of claim 15, wherein the first executable portion for converting parameters of the complex system from a plurality of binary values to at least one prognostic vector includes a third executable portion for encoding both of a current status of the parameters and a predicted status of the parameters at a specified future time interval.

18. The computer program product of claim 15, wherein the second executable portion for converting at least a portion of a Boolean availability expression into an equivalent fuzzy output expression includes a third executable portion for implementing at least one expression transform taking a phrase from the Boolean availability expression and converting the phrase to a function in the fuzzy output expression.

19. The computer program product of claim 18, further including a fourth executable portion for repeating the implementing at least one expression transform taking a phrase from the Boolean availability expression and the converting the phrase to a function in the fuzzy output expression until each portion of the Boolean availability expression has been converted.

20. The computer program product of claim 18, wherein second executable portion for converting at least a portion of a Boolean availability expression into an equivalent fuzzy output expression includes a fourth executable portion for implementing a plurality of mappings between a Boolean form represented in the Boolean availability expression into a statistical form represented in the fuzzy output expression.

21. The computer program product of claim 20, wherein the fourth executable portion for implementing a plurality of mappings between a Boolean form represented in the Boolean availability expression into a statistical form represented in the fuzzy output expression includes a fifth executable portion for implementing at least one of:

[Not (a)] mapped to [1-a],

[And (a,b)] mapped to [min(a,b)], and

[Or (a,b)] mapped to [max(a,b)],

where a and b are vectors containing a current status of the parameters and a predicted status of the parameters at a specified future time interval expressed in a ratio between 0 representing a not available status and 1 representing certainly available status.