Method of and system for prediction of the state of health of an apparatus

• US 20060131381A1
• Filed: 11/29/2005
• Published: 06/22/2006
• Est. Priority Date: 12/17/2004
• Status: Active Grant

• Current Assignee: NCR Corporation
• Original Assignee: NCR Corporation
• Inventors: Forrest, Simon J., Timmis, Jon, Ayara, Modupe, Lemos, Rogerio de
• Granted Patent: US 7,815,103 B2
• Time in Patent Office: Days
• US Class Current: 235/376
• CPC Class Codes: G05B 23/0229 knowledge based, e.g. expert systems; genetic algorithms
• CPC Class Codes: G07D 11/235 for monitoring or indicating operating conditions; for detecting malfunctions
• CPC Class Codes: G07F 19/20 Automatic teller machines [ATMs]
• CPC Class Codes: G07F 19/201 Accessories of ATMs
• CPC Class Codes: G07F 19/207 Surveillance aspects at ATMs

Abstract

A method is describe of predicting the probable future condition of one or more components within an apparatus comprising a plurality of sensors arranged to monitor the operation of components of the apparatus and a control means arranged to receive said information from said plurality of sensors. The method comprises receiving said sensor information; analyzing the information to ascertain sensor patterns from said sensor information; comparing said sensor patterns with detectors, which are predefined patterns, indicative of the future condition of said one or more components within the apparatus; and classifying said sensor patterns as being indicative of future failure of a component or not based upon a comparison of sensor patterns with said detectors.

Claims

1. A method of predicting the probable future condition of one or more components within an apparatus comprising a plurality of sensors arranged to monitor the operation of components of the apparatus and a control means arranged to receive said information from said plurality of sensors, the method comprising:

a) receiving said sensor information;

b) analyzing said information to ascertain sensor patterns from said sensor information

c) comparing said sensor patterns with detectors, which are predefined patterns, indicative of the future condition of said one or more components within the apparatus; and

d) classifying said sensor patterns as being indicative of future failure of a component or not based upon a comparison of sensor patterns with said detectors.

2. A method as claimed in claim 1, wherein the detectors are created/determined prior to the operation of the apparatus.

3. A method as claimed in claim 2, wherein the detectors are created from off-line analysis of logs of previous sensor information.

4. A method as claimed in claim 1, wherein detectors include information from two or more sensors received over a period of time.

5. A method as claimed in claim 1, wherein detectors are given a weighting determined by their rate of previous success in correctly predicting the failure of a component within/associated with the apparatus.

6. A method as claimed in claim 1, wherein a newly created detector is used more frequently if it proves to be successful in correctly predicting the failure of a component within/associated with the apparatus.

7. A method as claimed in claim 1, wherein detectors are continually evaluated during operation of the apparatus to optimize the selection of detectors for the apparatus.

8. A method as claimed in claim 7, wherein a new or candidate detector is only fully utilized as a detector, in that warnings created by it are forwarded to the operator of the apparatus, when it has proven to successfully predict the future state of health/condition of said one or more components to a pre-determined level of acceptability.

9. A method as claimed in claim 1, wherein the apparatus is one of a plurality of apparatuses within a network, further comprising a network control centre;

and the detectors are classified as either apparatus specific detectors or network detectors.

10. A method as claimed in claim 9, wherein apparatus specific detectors which have proven to be successful in determining state of health of an individual apparatus can be passed to the network control centre where they are reclassified as network detectors.

11. A method as claimed in claim 9, wherein newly presented network detectors undergo a network level evaluation prior to their dispersal to other apparatuses within the system.

12. A system for predicting the probable future condition of one or more components within an apparatus, the system comprising a plurality of sensors arranged to monitor the operation of components of the apparatus and a control means arranged to:

a) receive said information from said plurality of sensors;

b) analyze said information to ascertain sensor patterns from said sensor information;

c) compare said sensor patterns with detectors, which are predefined patterns, indicative of the future condition of said one or more components within the apparatus; and

d) classify said sensor patterns as being indicative of future failure of a component or not based upon a comparison of sensor patterns with said detectors.

13. A system as claimed in claim 12, wherein the detectors are created/determined and loaded into the control means prior to the operation of the apparatus.

14. A system as claimed in claim 12, wherein said detectors include information from two or more sensors received over a period of time.

15. A system as claimed in claim 12, wherein the control means gives detectors a weighting determined by their rate of previous success in correctly predicting the failure of a component within/associated with the apparatus.

16. A system as claimed in claim 12, wherein detectors are continually evaluated during operation of the apparatus to optimize the selection of detectors for the apparatus.

17. A system as claimed in claim 16, arranged to fully utilize a new or candidate detector as a detector, in that warnings created by it are forwarded to the operator of the apparatus, only when it has proven to successfully predict the future state of health/condition of said one or more components to a pre-determined level of acceptability.

18. A system as claimed in claim 12, wherein the apparatus is one of a plurality of apparatuses within a network, further comprising a network control centre;

and the detectors are classified as either apparatus specific detectors or network detectors.

19. A system as claimed in claim 12, wherein apparatus specific detectors which have proven to be successful in determining state of health of an individual apparatus can be passed to the network control centre where they are reclassified as network detectors.

20. A system as claimed in claim 19, wherein newly presented network detectors undergo a network level evaluation prior to their dispersal to other apparatuses within the system.

21. A computer program for predicting the probable future status of one or more components within an apparatus comprising a plurality of sensors arranged to monitor the operation of components of the apparatus and a control means arranged to receive said information from said plurality of sensors, the program being adapted to:

a) receive said sensor information;

b) analyze said information to ascertain sensor patterns from said sensor information;

c) compare said sensor patterns with detectors, which are predefined patterns, indicative of the future condition of said one or more components within the apparatus; and

d) classify said sensor patterns as being indicative of future failure of a component or not based upon a comparison of sensor patterns with said detectors.

22. A program as claimed in claim 21, wherein the detectors are created/determined prior to the operation of the apparatus.

23. A program as claimed in claim 21, wherein the detectors are created from off-line analysis of logs of previous sensor information.

24. A program as claimed in claim 21, wherein detectors include information from two or more sensors received over a period of time.

25. A program as claimed in claim 21, wherein detectors are given a weighting determined by their rate of previous success in correctly predicting the failure of a component within/associated with the apparatus.

26. A program as claimed in claim 21, wherein a newly created detector is used more frequently if it proves to be successful in correctly predicting the failure of a component within/associated with the apparatus.

27. A program as claimed in claim 21, wherein detectors are continually evaluated during operation of the apparatus to optimize the selection of detectors for the apparatus.

28. A program as claimed in claim 27, wherein a new or candidate detector is only fully utilized as a detector, in that warnings created by it are forwarded to the operator of the apparatus, when it has proven to successfully predict the future state of health/condition of said one or more components to a pre-determined level of acceptability.

29. A program as claimed in claim 21, wherein the apparatus is one of a plurality of apparatuses within a network, further comprising a network control centre;

and the detectors are classified as either apparatus specific detectors or network detectors.

30. A program as claimed in claim 29, wherein newly presented network detectors undergo a network level evaluation prior to their dispersal to other apparatuses within the system.