Diagnostic system and method

• US 6,868,319 B2
• Filed: 02/26/2003
• Issued: 03/15/2005
• Est. Priority Date: 02/05/2001
• Status: Expired due to Term

• Current Assignee: The Boeing Co.
• Original Assignee: The Boeing Co.
• Inventors: Dildy, Glenn A., Chew, Susan Chan, Nelson, Scott L., Rein-Weston, Karl J., Kipersztok, Oscar
• Primary Examiner(s): Nguyen, Tan Q.
• Assistant Examiner(s): Tran, Dalena
• Application Number:
  US10/375,814
• Publication Number:
  US 20030167111A1
• Time in Patent Office: 748 Days
• Field of Search: 701/29, 701/30, 701/31, 701/34, 701/32, 701/35, 701/33, 701/16, 714/25, 714/26, 714/799, 702/184, 702/185
• US Class Current: 701/29
• CPC Class Codes: G05B 23/0278 Qualitative, e.g. if-then rules; Fuzzy logic; Lookup tables; Symptomatic search; FMEA

Abstract

A diagnostic system and method are provided that include an interface for receiving input relating to observed symptoms indicative of one or more failed components, a processing element for correlating the input relating to the observed symptoms with at least one suspect component that is capable of causing the observed symptoms upon failure, and a display for presenting information relating to the suspect components. The processing element correlates the input relating to the observed symptoms with the suspect components in accordance with a diagnostic model constructed based upon systemic information, experiential information and factual information. The processing element generally presents the suspect components in a listing prioritized based upon the relative likelihood that the respective suspect components caused the observed symptoms. Additionally, the processing element can present a prioritized listing of tests that can be conducted to refine the identification and prioritization of the suspect components.

Claims

1. A method for constructing a diagnostic model for correlating at least one observed symptom with at least one suspect component that is capable of causing the at least one observed symptom upon failure, the method comprising:

obtaining systemic information relating to the components and input-output relationships of the components;

obtaining experiential information relating to direct relationships between component failures and the observed symptoms;

obtaining factual information relating to component reliability;

constructing the diagnostic model comprising a plurality of nodes and a plurality of arcs that interconnect the nodes in a manner defined by the systemic information and the experiential information, wherein the plurality of nodes include nodes representing the components and the observed symptoms, wherein each node has at least two states, and wherein constructing the diagnostic model comprises assigning a probability to each state of a node based upon at least one of the systemic information, the experiential information and the factual information; and

associating additional information with at least one component that is selected from the group consisting of component availability, time to repair the component, cost to repair the component, time to replace the component and cost to replace the component.

2. A method of troubleshooting a system experiencing a fault, the method comprising:

providing input relating to observed symptoms indicative of a failed component;

providing a diagnostic model constructed based upon systemic information relating to the components and input-output relationships of the components, experiential information relating to direct relationships between component failures and the observed symptoms, and factual information relating to component reliability, wherein providing a diagnostic model comprises providing a diagnostic model comprising a plurality of nodes and a plurality of arcs that interconnect the nodes in a manner defined by at least one of the systemic information, the experiential information and the factual information, wherein the plurality of nodes include nodes representing the components and the observed symptoms, wherein at least some nodes have at least two states with each state having an associated probability based upon at least one of the systemic information, the experiential information and the factual information;

executing the diagnostic model, wherein executing the diagnostic model correlates the input relating to the observed symptoms with at least one suspect component;

identifying the suspect component that caused the fault based at least in part upon the correlation of the input relating to the observed symptoms with the at least one suspect component; and

determining remedial action to be taken with respect to the identified component.

3. A method according to claim 2 wherein determining the remedial action comprises determining whether the identified component is to be fixed prior to further operation of the system or whether fixing the identified component is capable of being deferred.

4. A method according to claim 3 wherein determining the remedial action further comprises:

linking to a database comprising a minimum equipment list;

determining if the identified component is included in the minimum equipment list; and

if the identified component is not included in the minimum equipment list, fixing the identified component prior to further operation of the system.

5. A method according to claim 2 wherein determining the remedial action comprises:

linking to a database comprising an inventory of components; and

determining if the identified component is in inventory.

6. A method according to claim 2 wherein determining the remedial action comprises:

linking to a database comprising schematic images of the at least one suspect component; and

reviewing a schematic image of the at least one suspect component.

7. A method according to claim 2 wherein determining the remedial action comprises:

linking to a database comprising textual data describing the at least one suspect component; and

reviewing the textual data describing the at least one suspect component.

8. A method according to claim 2 wherein execution of the diagnostic model correlates the input relating to the observed symptoms with a plurality of suspect components, prioritizes the plurality of suspect components based upon a relative likelihood that the respective suspect components caused the observed symptoms, and identifies at least one test to be performed in order to refine the prioritization of the plurality of suspect components.

9. A method according to claim 8 further comprising:

performing at least one of the identified tests; and

re-executing the diagnostic model based upon the outcome of the at least one test in order to reprioritize the plurality of suspect components.

10. A method according to claim 2 further comprising providing data relating to remedial actions undertaken with respect to the identified component in order to create a summary log of the observed symptoms, the at least one suspect component and the remedial actions.

11. A method of troubleshooting a system experiencing a fault, the method comprising:

providing input relating to observed symptoms indicative of a failed component;

providing a diagnostic model comprising a plurality of nodes and a plurality of arcs that interconnect the nodes in a manner defined by at least one of systemic information, experiential information and factual information, wherein the plurality of nodes include nodes representing the components and the observed symptoms, wherein at least some nodes have at least two states with each state having an associated probability based upon at least one of the systemic information, the experiential information and the factual information;

executing the diagnostic model to correlate the input relating to the observed symptoms with a plurality of suspect components that are each capable of causing the observed symptoms upon failure, wherein execution of the diagnostic model also prioritizes the plurality of suspect components based upon a relative likelihood that the respective suspect components caused the observed symptoms, and wherein execution of the diagnostic model further identifies at least one test to be performed in order to refine the prioritization of the plurality of suspect components;

identifying the suspect component that caused the fault based at least in part upon the correlation of the input relating to the observed symptoms with the at least one suspect component; and

determining remedial action to be taken with respect to the identified component.

12. A method according to claim 11 wherein determining the remedial action comprises determining whether the identified component is to be fixed prior to farther operation of the system or whether fixing the identified component is capable of being deferred.

13. A method according to claim 12 wherein determining the remedial action further comprises:

linking to a database comprising a minimum equipment list;

determining if the identified component is included in the minimum equipment list; and

if the identified component is not included in the minimum equipment list, fixing the identified component prior to further operation of the system.

14. A method according to claim 11 wherein determining the remedial action comprises:

linking to a database comprising an inventory of components; and

determining if the identified component is in inventory.

15. A method according to claim 11 wherein determining the remedial action comprises:

linking to a database comprising schematic images of the at least one suspect component; and

reviewing a schematic image of the at least one suspect component.

16. A method according to claim 11 wherein determining the remedial action comprises:

linking to a database comprising textual data describing the at least one suspect component; and

reviewing the textual data describing the at least one suspect component.

17. A method according to claim 11 further comprising:

performing at least one of the identified tests; and

re-executing the diagnostic model based upon the outcome of the at least one test in order to reprioritize the plurality of suspect components.

18. A method according to claim 11 further comprising providing data relating to remedial actions undertaken with respect to the identified component in order to create a summary log of the observed symptoms, the at least one suspect component and the remedial actions.