# US 11,907,913 B2 · Maintaining an aircraft with automated acquisition of replacement aircraft parts

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,907,913 B2
- Document ID: US11907913B2
- Status: Granted
- Kind: B2
- Application number: 17/376,805
- Filed: 2021-07-15
- Published: 2022-02-17
- Granted: 2024-02-20
- Earliest claimed: 2020-08-13
- Assignees: The Boeing Company
- Applicants: The Boeing Company
- Inventors: Rahul C. Thakkar; Leontios Christodoulou; Surya Pandrangi
- Web page: https://patentgrep.com/patent/US11907913B2

## CPC

- G06Q 10/20: Administration of product repair or maintenance
- B64F 5/40: Maintaining or repairing aircraft
- G06F 16/2379: {Updates performed during online database operations; commit processing}
- G06N 20/00: Machine learning
- G06N 20/20: Ensemble learning
- G06Q 10/06315: {Needs-based resource requirements planning or analysis}
- G06Q 10/087: Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06Q 10/08726: {for replenishment processing, procedures, or recommendations using forecasting or optimisation}
- G06Q 10/10: Office automation; Time management
- G06Q 30/0633: {Managing shopping lists, e.g. compiling or processing purchase lists (shipping orders G06Q10/083; order filling G06Q10/087)}
- G07C 5/085: {using electronic data carriers}
- G06Q 10/0877: {by inventory control or reporting using inventory tracking or counting}
- G07C 5/008: {communicating information to a remotely located station (transmission systems for measured values G08C)}
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- B64F: GROUND OR AIRCRAFT-CARRIER-DECK INSTALLATIONS SPECIALLY ADAPTED FOR USE IN CONNECTION WITH AIRCRAFT; DESIGNING, MANUFACTURING, ASSEMBLING, CLEANING, MAINTAINING OR REPAIRING AIRCRAFT, NOT OTHERWISE PROVIDED FOR; HANDLING, TRANSPORTING, TESTING OR INSPECTING AIRCRAFT COMPONENTS, NOT OTHERWISE PROVIDED FOR
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G07C: TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE

## Abstract

A method is provided for maintaining an aircraft of a type of aircraft. The method includes accessing time series of observations of variables that describe in-service operation of the aircraft, maintenance of the aircraft, and weather and/or terrain in an environment of the aircraft during in-service operation and maintenance. The method includes determining a behavior model that is trained to predict demand for replacement aircraft parts from a training set across a plurality of aircraft of the type of aircraft. The behavior model is implemented as a directed acyclic graph of machine learning models that are connected to one another. The time series are applied to the behavior model to predict the demand for the replacement aircraft parts, a plan is created for acquisition of the replacement aircraft parts and maintenance of the aircraft based on the demand as predicted, and the plan is executed.

## Claims

### Claim 1

A system for maintaining an aircraft from a plurality of aircraft of a type of aircraft that includes a plurality of aircraft parts, the system comprising:
at least one source of data including at least one series of observations related to the aircraft; and
an electronic device in communication with the at least one source of data, the electronic device including:
a memory configured to store computer-readable program code; and
processing circuitry configured to access the memory, and execute the computer-readable program code to cause the electronic device to at least:
access a first time series of observations of first variables that describe in-service operation of the aircraft, including for a plurality of flights of the aircraft, flight plans, and geographic locations, operational context and status of the aircraft;
access a second time series of observations of second variables that describe maintenance of the aircraft, including a maintenance history of the aircraft, historical orders of replacement aircraft parts for respective aircraft parts of the plurality of aircraft parts, and historical time to replace the respective aircraft parts with the replacement aircraft parts;
access a third time series of observations of third variables that describe at least one of weather or terrain in an environment of the aircraft during the in-service operation and the maintenance of the aircraft;
determine a behavior model of the type of aircraft that is trained to predict demand for the replacement aircraft parts from a training set of observations of the first variables, the second variables and the third variables across the plurality of aircraft of the type of aircraft, the behavior model implemented as a directed acyclic graph of machine learning models that are connected to one another, an output of a first of the machine learning models fed as input to a second of the machine learning models;
apply the first time series, the second time series and, the third time series to the behavior model to predict the demand for the replacement aircraft parts;
create a plan for acquisition of the replacement aircraft parts, and maintenance of the aircraft in which the respective aircraft parts are replaced with the replacement aircraft parts, based on the demand as predicted; and
execute the plan to maintain the aircraft.

### Claim 2 (depends on 1)

The system of claim 1, wherein the operational context of the aircraft for a flight of the aircraft is defined by one or more of the first variables that characterize a situation of the aircraft during the flight, including a type of the flight as a solo flight or a coordinated flight with multiple aircraft, and when the flight is the coordinated flight, a position of the aircraft in a formation of the multiple aircraft.

### Claim 3 (depends on 1)

The system of claim 1, wherein the operational context of the aircraft for a flight of the aircraft is defined by one or more of the first variables that characterize a situation of the aircraft during the flight, including a use of flight controls to operate the aircraft during the flight, and a use of aircraft systems driven by the use of the flight controls.

### Claim 4 (depends on 1)

The system of claim 1, wherein the processing circuitry is configured to execute the computer-readable program code to cause the electronic device to further at least:
store the first time series, the second time series and the third time series in one or more data stores continuously and contemporaneous with the in-service operation and the maintenance of the aircraft, the one or more data stores including one or more of a time-series data warehouse, an object storage system, a document storage system, a distributed file system, a disk file system, a distributed data storage, or a database management system, and
wherein the first time series, the second time series, and the third time series are accessed from the one or more data stores.

### Claim 5 (depends on 4)

The system of claim 4, wherein the electronic device caused to store one or more of the first time series, the second time series, or the third time series includes the electronic device caused to at least:
digitize printed documents to produce corresponding electronic documents;
extract data from the corresponding electronic documents; and
format the data into observations of one or more of the first time series, the second time series, or the third time series.

### Claim 6 (depends on 1)

The system of claim 1, wherein the behavior model is determined from the training set of the observations of the first variables, the second variables, and the third variables across the plurality of aircraft of the type of aircraft, and further across a plurality of types of aircraft.

### Claim 7 (depends on 1)

The system of claim 1, wherein the electronic device caused to create the plan includes the electronic device caused to at least:
determine the replacement aircraft part is an out-of-stock part or an out-of-production part; and
identify the replacement aircraft part as a make-to-order part; and
identify a manufacturer for the replacement aircraft part,
wherein the electronic device caused to execute the plan includes the electronic device caused to place an automated order for the replacement aircraft part from the manufacturer.

### Claim 8 (depends on 1)

The system of claim 1, wherein the electronic device caused to execute the plan includes the electronic device caused to at least:
collect additional observations of the first variables, the second variables, and the third variables; and
feed the additional observations of the first variables, the second variables, and the third variables back to the training set to further train the behavior model.

### Claim 9

A system for automated acquisition of a replacement aircraft part to replace an aircraft part of an aircraft, the system comprising:
at least one source of data including at least one series of observations related to the aircraft; and
an electronic device in communication with the at least one source of data, the electronic device including:
a memory configured to store computer-readable program code; and
processing circuitry configured to access the memory, and execute the computer-readable program code to cause the electronic device to at least:
determine a demand for the replacement aircraft part based on the at least one series of observations related to the aircraft;
determine the replacement aircraft part is an out-of-stock part or an out-of-production part;
determine the replacement aircraft part is manufacturable as a make-to-order part in compliance with regulations to which the aircraft is subject, and that is certifiable for use on the aircraft;
identify a plurality of manufacturers authorized to manufacture and certify the replacement aircraft part;
submit a request for proposal for the replacement aircraft part to the plurality of manufacturers;
receive responses to the request for proposal from the plurality of manufacturers;
identify a manufacturer for the replacement aircraft part based on the responses; and
place an automated order for the replacement aircraft part from the manufacturer.

### Claim 10 (depends on 9)

The system of claim 9, wherein the aircraft is from a plurality of aircraft of a type of aircraft, and the electronic device caused to at least:
access a first time series of observations of first variables that describe in-service operation of the aircraft, a second time series of observations of second variables that describe maintenance of the aircraft, and a third time series of observations of third variables that describe at least one of weather or terrain in an environment of the aircraft during the in-service operation and the maintenance of the aircraft;
determine a behavior model of the type of aircraft that is trained to predict the demand for the replacement aircraft part from a training set of observations of the first variables, the second variables and the third variables across the plurality of aircraft of the type of aircraft, the behavior model implemented as a directed acyclic graph of machine learning models that are connected to one another, an output of a first of the machine learning models fed as input to a second of the machine learning models; and
apply the first time series, the second time series, and the third time series to the behavior model to predict the demand for the replacement aircraft part.

### Claim 11

A method of maintaining an aircraft from a plurality of aircraft of a type of aircraft that includes a plurality of aircraft parts, the method comprising:
receiving, via processing circuitry of an electronic device, at least one series of observations related to the aircraft from at least one source of data in communication with the electronic device;
accessing, via the processing circuitry of the electronic device, a first time series of observations of first variables that describe in-service operation of the aircraft, including for a plurality of flights of the aircraft, flight plans, and geographic locations, operational context and status of the aircraft;
accessing, via the processing circuitry of the electronic device, a second time series of observations of second variables that describe maintenance of the aircraft, including a maintenance history of the aircraft, historical orders of replacement aircraft parts for respective aircraft parts of the plurality of aircraft parts, and historical time to replace the respective aircraft parts with the replacement aircraft parts;
accessing, via the processing circuitry of the electronic device, a third time series of observations of third variables that describe at least one of weather or terrain in an environment of the aircraft during the in-service operation and the maintenance of the aircraft;
determining, via the processing circuitry of the electronic device, a behavior model of the type of aircraft that is trained to predict demand for the replacement aircraft parts from a training set of observations the first variables, the second variables, and the third variables across the plurality of aircraft of the type of aircraft, the behavior model implemented as a directed acyclic graph of machine learning models that are connected to one another, an output of a first of the machine learning models fed to as input to a second of the machine learning models;
applying, via the processing circuitry of the electronic device, the first time series, the second time series and the third time series to the behavior model to predict the demand for the replacement aircraft parts;
creating, via the processing circuitry of the electronic device, a plan for acquisition of the replacement aircraft parts, and maintenance of the aircraft in which the respective aircraft parts are replaced with the replacement aircraft parts, based on the demand as predicted; and
executing the plan, created via the processing circuitry of the electronic device, to maintain the aircraft.

### Claim 12 (depends on 11)

The method of claim 11, wherein the operational context of the aircraft for a flight of the aircraft is defined by one or more of the first variables that characterize a situation of the aircraft during the flight, including a type of the flight as a solo flight or a coordinated flight with multiple aircraft, and when the flight is the coordinated flight, a position of the aircraft in a formation of the multiple aircraft.

### Claim 13 (depends on 11)

The method of claim 11, wherein the operational context of the aircraft for a flight of the aircraft is defined by one or more of the first variables that characterize a situation of the aircraft during the flight, including a use of flight controls to operate the aircraft during the flight, and a use of aircraft systems driven by the use of the flight controls.

### Claim 14 (depends on 11)

The method of claim 11 further comprising:
storing, via the processing circuitry of the electronic device, the first time series, the second time series and the third time series in one or more data stores continuously and contemporaneous with the in-service operation and the maintenance of the aircraft, the one or more data stores including one or more of a time-series data warehouse, an object storage system, a document storage system, a distributed file system, a disk file system, a distributed data storage, or a database management system, and
wherein the first time series, the second time series, and the third time series are accessed from the one or more data stores.

### Claim 15 (depends on 14)

The method of claim 14, wherein storing one or more of the first time series, the second time series, or the third time series includes:
digitizing printed documents to produce corresponding electronic documents;
extracting data from the corresponding electronic documents; and
formatting the data into observations of one or more of the first time series, the second time series, or the third time series.

### Claim 16 (depends on 11)

The method of claim 11, wherein the behavior model is determined from the training set of the observations of the first variables, the second variables, and the third variables across the plurality of aircraft of the type of aircraft, and further across a plurality of types of aircraft.

### Claim 17 (depends on 11)

The method of claim 11, wherein creating the plan for acquisition of the replacement aircraft parts:
determining the replacement aircraft part is an out-of-stock part or an out-of-production part; and
identifying the replacement aircraft part as a make-to-order part; and
identifying a manufacturer for the identified replacement aircraft part,
wherein executing the plan includes placing an automated order for the identified replacement aircraft part from the identified manufacturer.

### Claim 18 (depends on 11)

The method of claim 11, wherein executing the plan includes:
collecting additional observations of the first variables, the second variables and the third variables; and
feeding the additional observations of the first variables, the second variables and the third variables back to the training set to further train the behavior model.

### Claim 19

A method of automated acquisition of a replacement aircraft part to replace an aircraft part of an aircraft, the method implemented by a computer and comprising:
receiving, via processing circuitry of an electronic device, at least one series of observations related to the aircraft; and
determining, via the processing circuitry of the electronic device, a demand for the replacement aircraft part based upon the at least one series of observations received by the processing circuitry of the electronic device;
determining, via the processing circuitry of the electronic device, the replacement aircraft part is an out-of-stock part or an out-of-production part;
determining, via the processing circuitry of the electronic device, the replacement aircraft part is manufacturable as a make-to-order part in compliance with regulations to which the aircraft is subject, and that is certifiable for use on the aircraft;
identifying, via the processing circuitry of the electronic device, a plurality of manufacturers authorized to manufacture and certify the replacement aircraft part;
submitting, via the processing circuitry of the electronic device, a request for proposal for the replacement aircraft part to the plurality of manufacturers;
receiving, via the processing circuitry of the electronic device, responses to the request for proposal from the plurality of manufacturers;
identifying, via the processing circuitry of the electronic device, a manufacturer for the replacement aircraft part based on the responses;
placing, via the processing circuitry of the electronic device, an automated order for the replacement aircraft part from the manufacturer;
receiving, via the processing circuitry of the electronic device, the replacement aircraft part from the manufacturer, the replacement aircraft part manufactured in compliance with the regulations and certified; and
replacing the aircraft part on the aircraft with the replacement aircraft part received from the manufacturer.

### Claim 20 (depends on 19)

The method of claim 19, wherein the aircraft is from a plurality of aircraft of a type of aircraft, and determining the demand for the replacement aircraft part includes:
accessing, via the processing circuitry of the electronic device, a first time series of observations of first variables that describe in-service operation of the aircraft, a second time series of observations of second variables that describe maintenance of the aircraft, and a third time series of observations of third variables that describe at least one of weather or terrain in an environment of the aircraft during the in-service operation and the maintenance of the aircraft;
determining, via the processing circuitry of the electronic device, a behavior model of the type of aircraft that is trained to predict the demand for the replacement aircraft part from a training set of observations the first variables, the second variables, and the third variables across the plurality of aircraft of the type of aircraft, the behavior model implemented as a directed acyclic graph of machine learning models that are connected to one another, an output of a first of the machine learning models fed as input to a second of the machine learning models; and
applying, via the processing circuitry of the electronic device, the first time series, the second time series and the third time series to the behavior model to predict the demand for the replacement aircraft part.