18181511. METHOD AND SYSTEM FOR PREDICTING FUEL CONSUMPTION FOR A FLIGHT OF AN AIRCRAFT simplified abstract (The Boeing Company)

From WikiPatents
Jump to navigation Jump to search

METHOD AND SYSTEM FOR PREDICTING FUEL CONSUMPTION FOR A FLIGHT OF AN AIRCRAFT

Organization Name

The Boeing Company

Inventor(s)

Chaitanya Pavan Kumar Aripirala of Bangalore (IN)

Veeresh Kumar Masaru Narasimhulu of Bangalore (IN)

Satyendra Yadav of Lone Tree CO (US)

METHOD AND SYSTEM FOR PREDICTING FUEL CONSUMPTION FOR A FLIGHT OF AN AIRCRAFT - A simplified explanation of the abstract

This abstract first appeared for US patent application 18181511 titled 'METHOD AND SYSTEM FOR PREDICTING FUEL CONSUMPTION FOR A FLIGHT OF AN AIRCRAFT

Simplified Explanation:

This patent application describes a method and system for predicting fuel consumption of an aircraft using a centralized machine learning model that is trained with both public and proprietary data from aircraft owners.

  • The centralized machine learning model is built and trained using public data initially.
  • A version of this model is then sent to edge computing devices owned by aircraft entities, where they input their proprietary data for further training.
  • The model is trained with this proprietary data, and a neural network gain is determined based on a weighted average of gains from all edge devices.
  • This neural network gain is used to improve the accuracy of fuel consumption predictions without the centralized model ever directly accessing the proprietary data.

Key Features and Innovation:

  • Utilizes a centralized machine learning model for predicting fuel consumption of aircraft.
  • Incorporates proprietary data from aircraft entities through edge computing devices for further training.
  • Determines a neural network gain based on edge device contributions to enhance prediction accuracy.

Potential Applications:

  • Aviation industry for optimizing fuel consumption and flight planning.
  • Airlines for cost-saving measures and efficiency improvements.

Problems Solved:

  • Lack of accurate fuel consumption prediction methods for aircraft.
  • Difficulty in incorporating proprietary data from aircraft entities into predictive models.

Benefits:

  • More accurate fuel consumption predictions for better flight planning.
  • Cost savings for airlines through optimized fuel usage.

Commercial Applications:

Fuel consumption prediction technology can be used by airlines, aircraft manufacturers, and aviation authorities to improve operational efficiency and reduce costs in the aviation industry.

Questions about Fuel Consumption Prediction Technology:

1. How does this technology benefit the aviation industry? 2. What are the key features of the centralized machine learning model used in this patent application?


Original Abstract Submitted

A method and system for predicting a fuel consumption of an aircraft is disclosed. First, a centralized machine learning model is built and trained using available public data. A version of the centralized model is then sent to one or more edge computing devices controlled by entities that own aircraft, and they input their proprietary data into the version of the centralized model they receive. The received version of the centralized model is trained using the proprietary data and a neural network gain for the centralized machine learning model is determined based on a weighted average of edge neural network gains from the edge computing devices. This neural network gain is used to further train the centralized model to give a more accurate prediction of the fuel consumption without the centralized machine learning model actually ever receiving and being trained with the proprietary data of the airlines and other entities.

Retrieved from "http://wikipatents.org/index.php?title=18181511._METHOD_AND_SYSTEM_FOR_PREDICTING_FUEL_CONSUMPTION_FOR_A_FLIGHT_OF_AN_AIRCRAFT_simplified_abstract_(The_Boeing_Company)&oldid=231866"