Aircraft Descent Trajectory Prediction for Accurate Top of Descent
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current aircraft flight management systems often calculate the top of descent (TOD) based on standard terminal arrival routes and average wind speeds, leading to inefficient fuel usage due to deviations from planned routes caused by air traffic control instructions.
Innovation Solution
A method and system utilizing a trained machine learning prediction module to determine a predicted arrival route, landing runway, and descent flight trajectories based on historical flight data, weather data, and environmental factors, thereby providing more accurate and efficient descent planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If standard terminal arrival routes and average wind speeds are used to calculate top of descent, then the calculation process is simple, but fuel efficiency deteriorates due to deviations from planned routes
Solution Approach 1:
The system performs preliminary clustering analysis on historical flight data to identify probable descent trajectories and their associated distances before actual flight execution. This pre-computed information is then used to optimize the TOD calculation, allowing the system to account for route deviations and ATC instructions in advance, thereby improving fuel efficiency without requiring complex real-time calculations
Solution Approach 2:
The system dynamically adjusts the TOD calculation by selecting from multiple clustered trajectory options based on actual flight conditions. Instead of using a fixed standard route, the system adapts the descent path selection to match actual ATC instructions and flight conditions, optimizing fuel consumption while maintaining operational flexibility
2Loss of energy
If machine learning prediction modules are used to determine descent trajectories, then fuel efficiency improves, but device complexity increases
Solution Approach 1:
The machine learning system is divided into distinct functional modules: a clustering module that processes historical flight data to identify trajectory patterns, a filtering module that ranks trajectories by probability, and a TOD calculation module that uses the filtered results. This segmentation allows each module to perform a specific function efficiently, reducing overall system complexity while maintaining the fuel efficiency benefits of machine learning
Solution Approach 2:
The system uses historical flight data as a proxy for predicting future flight behavior. By clustering and analyzing past trajectories, the system creates a probabilistic model that copies successful descent patterns from history, avoiding the need for complex real-time physics simulations while achieving accurate fuel optimization
Data Source
AI summary
A method and system for improving the fuel efficiency of an aircraft flight, and a method for training a machine learning module to predict the most probable descent flight trajectories are disclosed. The machine learning module uses two stages of clustering and regression analysis to analyse historical flight data, so that the trained model can determine the most probable flight trajectory for the descent phase of a future/ongoing flight. This can then be used to determine an adjusted top of descent and output to the pilot of the future/ongoing flight, or used to control an associated autopilot system.