US 10,324,004 B2Granted

Methods and devices for adaptive autonomous polynomial interpolation of time series data

AssigneeThe Boeing Company

InventorJohn M. Boggio

Life of this patent

Estimating the term…

Loading patent…

Abstract

A method of performing maintenance. Data is received from a plurality of physical sensors that measure parameters of parts of the platform, wherein a data point is missing from the data. A plurality of different polynomial interpolation values is calculated for the missing data point using a plurality of different polynomial interpolation formulas. A relative strength for each of the plurality of different polynomial interpolation values is calculated, wherein relative strengths are determined. A best polynomial interpolation value is selected based on a highest strength of the relative strengths. The best polynomial interpolation value is substituted for the data point that is missing from the data, wherein filled data is created. A status of the parts is determined based on the filled data, wherein an analysis is formed. Responsive to the analysis indicating that maintenance is due for a part in the parts, causing maintenance to be performed.

Claims41

Dependent claims

A method of performing maintenance on an aircraft, the method comprising:

programming a robot, comprising at least one of:
an inspection tool, and a maintenance tool, for receiving and executing a command;
receiving, in a processor during operation of the aircraft, from a first sensor that measures a first position of a first component located at a first part on the aircraft, a first incomplete input that comprises fluctuations of a first parameter that represents a performance of an aircraft system through a time series and comprises first blanks over the time series, such that the first blanks comprise a point in time that the processor receives, from a second sensor located at a second part of the aircraft, a second parameter for the aircraft system;
receiving, from the second sensor during the operation of the aircraft, a second incomplete input that comprises fluctuations of the second parameter that represents the performance of the aircraft system through the time series and comprises second blanks over the time series, such that the second blanks comprise a point in time that the processor receives the first parameter from the first sensor;
applying rules, responsive to a variation between parameters within the first incomplete input and between parameters within the second incomplete input, to the first incomplete input and the second incomplete input that self-generate a filled-in table that fills in the first blanks and the second blanks thus forming an accurate time series for the performance of the aircraft system, and thereby the rules producing, for each blank in the first blanks and for each blank in the second blanks:
a plurality of interpolative estimates for the first parameter during the first blanks and the second parameter during the second blanks;
using an order of interpolation, a confidence score for each interpolative estimate in the plurality of interpolative estimates;
and
using a strength of the confidence score for each interpolative estimate, a selection from the plurality of interpolative estimates that completes the filled-in table, such that the filled-in table comprises:
the selection, the first parameter, and the second parameter;
determining, using the filled-in table, a need for at least one of:
an inspection, and a maintenance action on the aircraft system;
and
generating, using the need, and transmitting the command to the robot.

11 more elements

A machine that determines a need for and executes at least one of:

an inspection, and a maintenance action, on an aircraft, such that the machine comprises:
a robot that comprises at least one of:
an inspection tool, and a maintenance tool, configured to receive and execute a command;
a processor;
a bus connected to the processor;
a memory connected to the bus, the memory storing computer usable program code configured to:
receive during an operation of the aircraft, from a first sensor located at a first part of the aircraft and configured to transmit a first parameter for an aircraft system, a first incomplete input that comprises fluctuations of the first parameter that represents a performance of the aircraft system through a time series and comprises first blanks over the time series, such that the first blanks comprise a point in time that the memory receives, from a second sensor located at a second part of the aircraft, a second parameter for the aircraft system;
receive, from the second sensor during the operation of the aircraft, a second incomplete input that comprises fluctuations of the second parameter that represents the performance of the aircraft system through the time series and comprises second blanks over the time series, such that the second blanks comprise a point in time that the memory receives the first parameter from the first sensor;
apply rules, responsive to a variation between parameters within the first incomplete input and between parameters within the second incomplete input, to the first incomplete input and the second incomplete input that self-generate a filled-in table that fills in the first blanks and the second blanks and comprises an accurate time series for the performance of the aircraft system, such that for each blank in the first blanks and for each blank in the second blanks, the rules produce:
interpolative estimates for the first parameter during the first blanks and the second parameter during the second blanks;
based upon an order of interpolation, a confidence score for each interpolative estimate in the plurality of interpolative estimates;
and
based upon a strength of the confidence score for each interpolative estimate, a selection from the plurality of interpolative estimates that completes the filled-in table, such that the filled-in table comprises:
the selection, the first parameter, and the second parameter;
based upon the filled-in table, determine the need for at least one of:
the inspection, and the maintenance action on the aircraft system;
and
based upon the need, generate and transmit the command to the robot.

15 more elements

A machine that determines a need for and executes at least one of:

an inspection, and a maintenance action, on an air conditioning system on an aircraft, such that the machine comprises:
a robot that comprises at least one of:
an inspection tool, and a maintenance tool, configured to receive and execute a command;
a processor;
a bus connected to the processor;
a memory connected to the bus, the memory storing a computer usable program code configured to:
receive during an operation of the aircraft, from a first sensor located at a first trim air valve on the aircraft and configured to transmit a position of the first trim air valve, a first incomplete input that comprises fluctuations of the position of the first trim air valve that represents a performance of the air conditioning system through a time series and comprises first blanks over the time series, such that the first blanks comprise a point in time that the memory receives, from a second sensor located at a second trim air valve on the aircraft, a position of the second trim air valve;
receive from the second sensor, during the operation of the aircraft, a second incomplete input that comprises fluctuations of the position of the second trim air valve that represents the performance of the air conditioning system through the time series and comprises second blanks over the time series, such that the second blanks comprise a point in time that the memory receives the position of the first trim air valve from the first sensor;
apply rules, responsive to a variation between parameters within the first incomplete input and between parameters within the second incomplete input, to the first incomplete input and the second incomplete input that self-generate a filled-in table that fills in the first blanks and the second blanks and comprises an accurate time series for the performance of the air conditioning system, such that for each blank in the first blanks and for each blank in the second blanks, the rules produce:
a plurality of interpolative estimates for the position of the first trim air valve during the first blanks and the position of the second trim air valve during the second blanks;
based upon an order of interpolation, a confidence score for each interpolative estimate in the plurality of interpolative estimates;
and
based upon a strength of the confidence score for each interpolative estimate, a selection from the plurality of interpolative estimates that completes the filled-in table, such that the filled-in table comprises:
the selection, the position of the first trim air valve, and the position of the second trim air valve;
based upon the filled-in table, determine the need for at least one of:
the inspection, and the maintenance action on the air conditioning system;
and
based upon the need, generate and transmit the command to the robot.

15 more elements

A method of performing maintenance on an aircraft, the method comprising:

a processor determining a need for and executing at least one of:
an inspection, and a maintenance action, on an air conditioning system on the aircraft;
programming a robot, comprising at least one of:
an inspection tool, and a maintenance tool, for receiving and executing a command;
receiving, during an operation of the aircraft, from a first sensor located at a first trim air valve on the aircraft and configured to transmit a position of the first trim air valve, a first incomplete input that comprises fluctuations of the position of the first trim air valve that represents a performance of the air conditioning system through a time series and comprises first blanks over the time series, such that the first blanks comprise a point in time that the processor receives, from a second sensor located at a second trim air valve on the aircraft, a position of the second trim air valve;
receiving from the second sensor, during the operation of the aircraft, a second incomplete input that comprises fluctuations of the position of the second trim air valve that represents the performance of the air conditioning system through the time series and comprises second blanks over the time series, such that the second blanks comprise a point in time that the processor receives the position of the first trim air valve from the first sensor;
applying rules, responsive to a variation between parameters within the first incomplete input and between parameters within the second incomplete input, to the first incomplete input and the second incomplete input that self-generate a filled-in table that fills in the first blanks and the second blanks and comprises an accurate time series for the performance of the air conditioning system, such that for each blank in the first blanks and for each blank in the second blanks, the rules produce:
a plurality of interpolative estimates for the position of the first trim air valve during the first blanks and the position of the second trim air valve during the second blanks;
using an order of interpolation, a confidence score for each interpolative estimate in the plurality of interpolative estimates;
and
using a strength of the confidence score for each interpolative estimate, a selection from the plurality of interpolative estimates that completes the filled-in table, such that the filled-in table comprises:
the selection, the position of the first trim air valve, and the position of the second trim air valve;
determining, using the filled-in table the need for at least one of:
the inspection, and the maintenance action on the air conditioning system;
and
generating, using the need, and transmitting the command to the robot.

13 more elements

Dependencies are inferred from the claim text.

Facts

Application: 14/687,854Filed 15 Apr 2015
Published: US 2016/0305848 A120 Oct 2016
Granted: 18 Jun 2019
Term ends: Not estimatedThe source records don’t support an estimate.

Classification14 codes

G01M 17/007
Testing of vehicles: wheeled or endless-tracked vehicles
G06F 17/17
Complex mathematical operations: function evaluation by approximation methods, e.g. inter- or extrapolation, smoothing, least mean square method
G06Q 10/0631
Operations research, analysis or management: resource planning, allocation, distributing or scheduling for enterprises or organisations
G06Q 10/20
Administration; Management: administration of product repair or maintenance