Air Traffic Control Support System Using Predictive Flight Plan Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current air traffic control systems are inefficient in quickly grasping flight plans, leading to increased frequency of traffic flow control and higher delays and workload for controllers due to rising aviation demand.
Innovation Solution
An air traffic control support system that uses learning means to generate a prediction model based on past flight plans and affecting information, enabling quick prediction of future flight plans and traffic volumes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If traditional flight plan processing methods are used, then controllers can monitor and control flights, but the system cannot quickly grasp flight plans leading to increased traffic flow control frequency and longer delay times
Solution Approach 1:
The system performs preliminary actions by predicting flight plans before they are officially presented by airlines. The prediction unit generates predicted flight plans based on historical data and patterns, allowing the air traffic management system to prepare traffic flow control measures in advance, thereby reducing delays when actual flight plans are submitted
Solution Approach 2:
The system segments the flight plan processing into multiple components: prediction of flight plans, calculation of traffic volumes based on predicted plans, and comparison with actual presented plans. This segmentation allows parallel processing and faster overall response time in grasping and responding to flight plans
2Productivity
If traditional flight plan processing methods are used, then controllers can perform air traffic control, but the frequency of traffic flow control increases due to inability to quickly grasp flight plans
Solution Approach 1:
The system performs self-service by automatically predicting flight plans and calculating traffic volumes without requiring manual intervention from controllers. The prediction unit and traffic volume calculation unit operate autonomously, reducing controller workload while improving the efficiency and frequency of traffic flow control operations
Solution Approach 2:
The system implements feedback by comparing predicted flight plans with actual presented flight plans, and using this information to continuously improve prediction accuracy. This feedback mechanism enables the system to learn from past performance and become more efficient over time, reducing unnecessary traffic flow control operations
3Reliability
If more traffic flow control is performed to manage increased aviation demand, then airspace capacity can be maintained, but delay time and controller workload increase
Solution Approach 1:
The system performs preliminary traffic flow control by predicting flight plans and calculating traffic volumes before flights are actually assigned. This allows air traffic management to proactively manage airspace capacity and implement control measures in advance, preventing delays rather than reacting to them after they occur
Data Source
AI summary
An air traffic control support system for more quickly grasping a flight plan in air traffic control is provided. An air traffic control support system 3 includes a learning unit 100 and a prediction unit 200. The learning unit 100 generates a prediction model, based on learning data including a past flight plan and information that affected formulation of the past flight plan. The prediction unit 200 predicts a flight plan, based on information that affects formulation of the flight plan and a prediction model.