Systems and methods for predicting flight data

Patent metadata

Field	Value
Publication number	US-12027057-B2
Application number	US-202017014334-A
Country	US
Kind code	B2
Filing date	Sep 8, 2020
Priority date	Nov 15, 2019
Publication date	Jul 2, 2024
Grant date	Jul 2, 2024

Abstract

A device for flight data prediction includes a memory, a communication interface, and one or more processors. The memory is configured to store a departure airport map. The communication interface is configured to receive location data for a plurality of aircraft expected to arrive at or depart from a departure airport during a particular time range. The one or more processors are configured to predict, based on the location data and the departure airport map, a taxi duration or a fuel usage of a first aircraft of the plurality of aircraft. The one or more processors are also configured to generate an output based on the taxi duration or the fuel usage.

First claim

What is claimed is:

1. A device for flight data prediction comprising:
a memory configured to store a departure airport map and an arrival airport map;
a communication interface configured to receive location data for a plurality of aircraft expected to arrive at or depart from a departure airport during a particular time range and flight plans of a second plurality of aircraft expected to arrive at or depart from an arrival airport during a second particular time range, the arrival airport distinct from the departure airport; and
one or more processors configured to:
predict, based on the location data and the departure airport map, a taxi duration and a first taxi fuel usage of a first aircraft of the plurality of aircraft using a data model that is trained based on historical data associated with the departure airport, wherein the historical data includes historical taxi durations at the departure airport;
predict a second taxi fuel usage based on the flight plans and the arrival airport map;
generate a combined fuel usage based on the first taxi fuel usage and the second taxi fuel usage;
generate an output based on the combined fuel usage;
detect a first detected taxi duration of the first aircraft; and
train the data model based on the first detected taxi duration and the location data.

2. The device of claim 1 , wherein the taxi duration or the first taxi fuel usage is based on weather conditions at the departure airport, second flight plans of the plurality of aircraft, aircraft performance of the first aircraft, aircraft specifications of the first aircraft, runway directions of the departure airport, or a combination thereof.

3. The device of claim 1 , wherein the location data is received from an automatic dependent surveillance broadcast system, an airport surface detection equipment model X system, or both, and wherein the departure airport map is received from an aerodrome mapping database.

4. The device of claim 1 , wherein the taxi duration or the first taxi fuel usage is based on aircraft performance data that indicates a detected fuel usage during a taxi between a gate and a runway at a particular airport for a prior flight by the first aircraft.

5. The device of claim 1 , wherein the data model includes a neural network, a random forest, a gradient boosted decision tree, a machine learning model, a statistical model, or a combination thereof.

6. The device of claim 1 , wherein the data model is trained based on the departure airport map, and wherein the historical data indicates second location data of a third plurality of aircraft that was expected to arrive at or depart from the departure airport, historical weather conditions at the departure airport, historical weather forecasts, historical flight plans of the third plurality of aircraft, a second detected taxi duration of a second aircraft of the third plurality of aircraft, historical aircraft performance of the second aircraft, aircraft specifications of the second aircraft, or a combination thereof.

7. The device of claim 1 , wherein the one or more processors are further configured to:
detect a second detected taxi duration of the first aircraft; and
train a second data model based on the second detected taxi duration and the flight plans.

8. The device of claim 1 , wherein the memory is further configured to store aircraft performance data of the first aircraft, and wherein the first taxi fuel usage is based on the taxi duration and the aircraft performance data.

9. The device of claim 1 , wherein the output indicates an amount of fuel to load on the first aircraft to accommodate the taxi duration.

10. The device of claim 1 , wherein the communication interface is further configured to send the output to an electronic flight bag device, wherein at least one of the memory, the one or more processors, or the communication interface is integrated into a server.

11. The device of claim 1 , wherein at least one of the memory, the one or more processors, or the communication interface is integrated into an electronic flight bag device, wherein the communication interface is configured to receive the data model.

12. The device of claim 1 , wherein at least one of the memory, the one or more processors, or the communication interface is integrated into an electronic flight bag device or a server.

13. The device of claim 1 , wherein the combined fuel usage is based on a third fuel usage associated with a flight duration.

14. A method of flight data prediction, the method comprising:
receiving, at a device, flight plans for a plurality of aircraft expected to arrive at or depart from an arrival airport during a particular time range and location data for a second plurality of aircraft expected to arrive at or depart from a departure airport during a second particular time range, the departure airport distinct from the arrival airport;
predicting, based on the flight plans and an arrival airport map, a taxi duration and a first taxi fuel usage of a first aircraft of the plurality of aircraft using a data model that is trained based on historical data associated with the arrival airport, wherein the historical data includes historical taxi durations at the arrival airport;
predicting a second taxi fuel usage based on the location data and a departure airport map;
generating a combined fuel usage based on the first taxi fuel usage and the second taxi fuel usage;
generating, at the device, an output based on the combined fuel usage;
detecting a first detected taxi duration of the first aircraft; and
training the data model based on the first detected taxi duration and the flight plans.

15. The method of claim 14 , wherein the taxi duration or the first taxi fuel usage is predicted based on a weather forecast of the arrival airport, aircraft performance of the first aircraft, aircraft specifications of the first aircraft, expected runway directions of the arrival airport, a parking stand area of the arrival airport, or a combination thereof.

16. The method of claim 14 , further comprising:
detecting a second detected taxi duration of the first aircraft; and
training a second data model based on the second detected taxi duration and the location data.

17. The method of claim 14 , wherein the historical data indicates second flight plans of a third plurality of aircraft, and a second detected taxi duration of a second aircraft of the third plurality of aircraft, and wherein the third plurality of aircraft was expected to arrive at or depart from the arrival airport during a first time range that is prior to the particular time range.

18. The method of claim 14 , wherein the data model includes a neural network, a random forest, a gradient boosted decision tree, a machine learning model, a statistical model, or a combination thereof.

19. The method of claim 14 , wherein the output indicates an amount of fuel to load on the first aircraft to accommodate the taxi duration.

20. A computer-readable storage hardware device storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
receiving flight plans for a plurality of aircraft expected to arrive at or depart from a departure airport during a particular time range and second flight plans of a second plurality of aircraft expected to arrive at or depart from an arrival airport during a second particular time range, the arrival airport distinct from the departure airport; and
predicting, based on the flight plans and

Assignees

• Boeing Co

Inventors

• Frontera Guillermo
• Lopez Leones Javier
• Pena Ortiz Nicolas
• Costas Pablo

Classifications

• G08G5/723

  from the aircraft · CPC title

• G08G5/76

  for monitoring atmospheric conditions · CPC title

• G08G5/30

  Flight plan management · CPC title

• G08G5/21

  located onboard the aircraft · CPC title

• G08G5/54 Primary

  for approach or landing · CPC title