Prognostic diagnostic capability tracking system

• US 8,001,423 B2
• Filed: 08/27/2009
• Issued: 08/16/2011
• Est. Priority Date: 09/26/2008
• Status: Active Grant

• Current Assignee: BAE Systems Information and Electronic Systems Integration Incorporated (BAE Systems Plc)
• Original Assignee: BAE Systems Information and Electronic Systems Integration Incorporated (BAE Systems Plc)
• Inventors: Spier, Carolyn, Mills, Daniel E.
• Primary Examiner(s): Baderman, Scott
• Assistant Examiner(s): PATEL, KAMINI B
• Application Number:
  US12/548,683
• Publication Number:
  US 20100083056A1
• Time in Patent Office: 719 Days
• Field of Search: 714/26
• US Class Current: 714/26
• CPC Class Codes: G05B 23/0275 Fault isolation and identification, e.g. classify fault; estimate cause or root of failure
• CPC Class Codes: G06F 11/0727 in a storage system, e.g. in a DASD or network based storage system drivers for digital recording or reproducing units G06F3/06; circuits for error detection or correction within digital recording or reproducing units G11B20/18; for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS], H04L67/1097
• CPC Class Codes: G06F 11/0739 in a data processing system embedded in automotive or aircraft systems
• CPC Class Codes: G06F 11/079 Root cause analysis, i.e. error or fault diagnosis in a hardware test environment G06F11/22; in a software test environment G06F11/36

Abstract

A universal on-board system is provided for automatic fault detection and on-the-spot repair instructions that includes a module adapted to be coupled to a wide variety of platforms and Line Replaceable Units.

Claims

1. A universal on platform system for automatic detection of platform faults and for providing repair or replacement instructions based on the determination of the cause of a fault, comprising:

a module embedded in said platform for sensing platform faults and for providing accurate evaluation of the state of said platform, said module being embedded in said platform and evaluating each likely cause of failure of the detected fault; and

,

a display for displaying repair and/or replace instructions corresponding to the cause of the fault detected by said module, whereby the unique cause of a fault is determined and detailed targeted repair/replace instructions are provided to address the cause of the fault, said maintenance operation function employing a second set of reasoning algorithms capable of determining at a high level the unique cause of a detected fault, said second set of reasoning algorithms being provided with one or more models of said platform, the information being analyzed by said second set of reasoning algorithms being taken from a suspect list of suspected causes for the detected fault, said module providing a fault isolation test function for specifying tests useful in determining the cause of a detected fault, said fault isolation test function being invoked responsive to the inability of said second set of reasoning algorithms to ascertain a single cause for said fault and a consequent single remove and replace operation.

2. The system of claim 1, wherein said module is reconfigured to accept signals from said platform and for performing health monitoring and maintenance operation of functions based on the utilization of reasoners.

3. The system of claim 2, wherein the reasoners associated with said health monitoring function include a set of reasoning algorithms that access one or more models of said platform to determine that a fault has occurred in said platform, and for outputting the existence of said fault and the cause thereof to said display.

4. The system of claim 3, wherein said set of reasoning algorithms includes low-level reasoning algorithms.

5. The system of claim 4, wherein said low-level reasoning algorithms output a suspect list of suspected causes for the detected fault.

6. The system of claim 2, wherein said reasoners include a dynamic reasoner.

7. The system of claim 2, wherein said reasoners are taken from the group of reasoners consisting of abductive reasoners, Bayesian reasoners, neural reasoners, fault dictionary reasoners, physics-based reasoners and rules-based reasoners.

8. The system of claim 2, wherein said fault monitoring function is performed during the performance of the mission of said platform.

9. The system of claim 2, wherein said maintenance operation function is performed when said platform is not required to perform its mission.

10. The system of claim 1, wherein said second set of reasoning algorithms outputs an ambiguity list indicating failure to isolate a single replaceable component of said platform for repairing a detected fault due to a failure to find a single cause for a detected fault, and wherein said fault isolation test function supplies the name of the next test to be executed to provide information to isolate the cause of said detected fault.

11. The system of claim 10, wherein if said ambiguity group has only one cause for a detected fault, then said module outputs remove and replace instructions to said display.

12. The system of claim 1, wherein said module includes a rules engine, a data manager, an executive program and a report manager, the function of said data manager, executive program and report manager being under control of said rules engine to configure said data manager, executive program and report manager in accordance with the platform into which said module is embedded, thereby to reconfigure said module to the platform in which said module is embedded.

13. The system of claim 1, wherein said module utilizes a dynamic reasoning algorithm including an abductive reasoner coupled to a Bayesian mechanism to calculate the probability or criticality of the result of the hypothesis associated with said abductive reasoner.

14. The system of claim 1, wherein said module outputs prognostics for predicting future failures of said platform.

15. The system of claim 1, wherein the output of said module includes information relating to an immediately-replaceable source of said detected fault or upon the unavailability of an immediately-replaceable source, the output of a suspect list of causes of said fault.