REPORTING AND PRIORITIZING FAULTS FOR AIRCRAFT DOWNTIME REDUCTION

• US 20190087789A1
• Filed: 09/21/2017
• Published: 03/21/2019
• Est. Priority Date: 06/09/2017
• Status: Active Grant

• Current Assignee: Kidde Technologies, Inc. (Raytheon Technologies Corporation d/b/a RTX)
• Original Assignee: KIDD Technology
• Inventors: Barkat, Mohammad Adil, Karan, Vivek, Nandakumar, Pradeep Kumar
• Granted Patent: US 10,643,187 B2
• Time in Patent Office: Days
• CPC Class Codes: B64D 2045/0085 Devices for aircraft health monitoring, e.g. monitoring flutter or vibration
• CPC Class Codes: B64F 5/40 Maintaining or repairing aircraft
• CPC Class Codes: B64F 5/60 Testing or inspecting aircraft components or systems
• CPC Class Codes: G06F 7/08 Sorting, i.e. grouping record carriers in numerical or other ordered sequence according to the classification of at least some of the information they carry by merging two or more sets of carriers in ordered sequence G06F7/16
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 10/06316 Sequencing of tasks or work
• CPC Class Codes: G06Q 10/20 Administration of product repair or maintenance
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C
• CPC Class Codes: G07C 5/0808 Diagnosing performance data testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005
• CPC Class Codes: G07C 5/0841 Registering performance data recording measured values G01D; information storage G11B

Abstract

Disclosed is a computer-implemented method for maintenance planning for an aircraft. The method includes retrieving, via a processor, a data transmission comprising a plurality of component faults from an aircraft processor while the aircraft is in flight. The processor executes, using a prediction engine, a predictive fault list based on the component faults. The predictive fault list includes a plurality of weighted predictions of authentic component faults and nuisance component faults. The processor prioritizes the weighted predictions of authentic component faults, and generates a maintenance checklist prioritized based on the weighted prediction of authentic component faults. The processor then outputs the prioritized maintenance checklist on an operatively connected maintenance planning device.

Claims

1. A computer-implemented method for maintenance planning for an aircraft, the method comprising:

retrieving, via a processor, a data transmission comprising a plurality of component faults from an aircraft processor while the aircraft is in flight;

constructing, via the processor executing a prediction engine, a predictive fault list based on the component faults, the predictive fault list having a plurality of weighted predictions of authentic component faults and nuisance component faults;

prioritizing, via the processor, the weighted predictions of authentic component faults;

generating, via the processor, a maintenance checklist prioritized based on the weighted prediction of authentic component faults; and

outputting, via an output processor, the prioritized maintenance checklist on an operatively connected maintenance planning device.

2. The computer-implemented method of claim 1, further comprising obtaining, via the processor, a prediction accuracy report indicative of an accuracy for each of the weighted predictions of authentic component faults and nuisance component faults;

generating, via the processor, an accuracy table indicative of a relative accuracy for each of the weighted predictions; and

configuring, via the processor, the prediction engine based on the accuracy table.

3. The computer-implemented method of claim 1, wherein constructing the predictive fault list comprises:

retrieving, via the processor, a part failure history for each sensor indicated in the plurality of component faults from the aircraft processor while the aircraft is in flight; and

evaluating, based on the part failure history, for each sensor associated with a particular sensor fault in the plurality of component faults from the aircraft processor, a relationship between

     1) an aircraft flight path,

     2) the particular sensor fault, and

     3) a prediction hit or miss rate for the sensor associated with the sensor fault.

4. The computer-implemented method of claim 3, further comprising predicting, for each of the plurality of component faults, the weighted prediction of authentic component faults based on the relationship between the aircraft flight path, the sensor fault, and the prediction hit or miss rate for the sensor associated with the sensor fault.

5. The computer-implemented method of claim 4, wherein the aircraft flight path comprises a predetermined flight leg unique to the aircraft flight path.

6. The computer-implemented method of claim 5, wherein the aircraft flight path comprises one or more of a flight parameters including but not limited to flight vector, an engine speed, and an altitude.

7. A system for aircraft maintenance planning comprising:

a processor configured to;

retrieve a data transmission comprising a plurality of component faults from an aircraft processor while the aircraft is in flight;

construct, via a prediction engine, a predictive fault list based on the component faults, the predictive fault list having a plurality of weighted predictions of authentic component faults and nuisance component faults;

prioritize, via the prediction engine, the weighted predictions of authentic component faults;

generate a maintenance checklist prioritized based on the weighted prediction of authentic component faults; and

output the prioritized maintenance checklist on an operatively connected maintenance planning device.

8. The system of claim 7, wherein constructing the predictive fault list comprises:

retrieving, via the processor, a part failure history for each sensor indicated in the plurality of component faults from the aircraft processor while the aircraft is in flight; and

evaluating, based on the part failure history, for each sensor associated with a particular sensor fault in the plurality of component faults from the aircraft processor, a relationship between

     1) an aircraft flight path,

     2) the particular sensor fault, and

     3) a prediction hit or miss rate for the sensor associated with the sensor fault.

9. The system of claim 8, further comprising predicting, for each of the plurality of component faults, the weighted prediction of authentic component faults based on the relationship between the aircraft flight path, the sensor fault, and the prediction hit or miss rate for the sensor associated with the sensor fault.

10. The system of claim 9, wherein the aircraft flight path comprises a predetermined flight leg unique to the aircraft flight path.

11. The system of claim 10, wherein the aircraft flight path comprises one or more of a flight data including but not limited to flight vector, an engine speed, and an altitude.

12. A non-transitory computer readable medium comprising a computer program product configured to, when executed on a processor, perform a method for aircraft maintenance planning comprising:

retrieving, via the processor, a data transmission comprising a plurality of component faults from an aircraft processor while the aircraft is in flight;

constructing, via the processor executing a prediction engine, a predictive fault list based on the component faults, the predictive fault list having a plurality of weighted predictions of authentic component faults and nuisance component faults;

prioritizing, via the processor, the weighted predictions of authentic component faults;

generating, via the processor, a maintenance checklist prioritized based on the weighted prediction of authentic component faults; and

outputting, via an output processor, the prioritized maintenance checklist on an operatively connected maintenance planning device.

13. The non-transitory computer readable medium of claim 12, further comprising obtaining, via the processor, a prediction accuracy report indicative of an accuracy for each of the weighted predictions of authentic component faults and nuisance component faults;

generating, via the processor, an accuracy table indicative of a relative accuracy for each of the weighted predictions; and

configuring, via the processor, the prediction engine based on the accuracy table.

14. The non-transitory computer readable medium of claim 12, wherein constructing the predictive fault list comprises:

retrieving, via the processor, a part failure history for each sensor indicated in the plurality of component faults from the aircraft processor while the aircraft is in flight; and

evaluating, based on the part failure history, for each sensor associated with a particular sensor fault in the plurality of component faults from the aircraft processor, a relationship between

     1) an aircraft flight path,

     2) the particular sensor fault, and

     3) a prediction hit or miss rate for the sensor associated with the sensor fault.

15. The non-transitory computer readable medium of claim 12, further comprising predicting, for each of the plurality of component faults, the weighted prediction of authentic component faults based on the relationship between the aircraft flight path, the sensor fault, and the prediction hit or miss rate for the sensor associated with the sensor fault.

16. The non-transitory computer readable medium of claim 15, wherein the aircraft flight path comprises a predetermined flight leg unique to the aircraft flight path.

17. The non-transitory computer readable medium of claim 16, wherein the aircraft flight path comprises one or more of a flight vector, an engine speed, and an altitude.