Aircraft Flightpath Optimization via Probabilistic Trajectory Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing flightpath optimization methods are resource-intensive and inefficient in generating optimized trajectories that balance various parameters such as altitude, speed, and heading, making it challenging to quickly determine the most efficient flightpath for aircraft.
Innovation Solution
A method and system that generate a set of waypoints with adjustable parameters, perform probabilistic or exhaustive assessments to identify elite trajectories with high efficiency metrics, and adjust mobile waypoints to determine an optimal flightpath, reducing processing resources and enabling faster generation of optimized flightpaths.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If exhaustive assessment of all unique trajectories is performed to identify optimal flightpath, then manufacturing precision (optimization accuracy) is improved, but productivity (processing speed) deteriorates
Solution Approach 1:
The patent segments the exhaustive trajectory assessment into two phases: (1) probabilistic sampling phase that generates an initial elite set of trajectories, and (2) refined assessment phase that performs exhaustive evaluation only on the elite set. This segmentation reduces the computational burden from assessing all possible trajectories to assessing only the most promising subset, thereby improving processing speed while maintaining optimization accuracy.
Solution Approach 2:
The patent applies partial action by performing exhaustive assessment only on a portion of the total trajectories - specifically, only on the elite set that represents the upper range of efficiency metrics. The majority of trajectories are evaluated using probabilistic sampling, which requires fewer computational resources. This partial exhaustive approach maintains accuracy for the most important trajectories while improving overall processing speed.
2Productivity
If probabilistic assessment is used to reduce processing resources, then productivity (processing speed) is improved, but manufacturing precision (optimization accuracy) deteriorates
Solution Approach 1:
The patent implements feedback by using the results of probabilistic assessment to identify an elite set of trajectories, then feeding this elite set into a refined exhaustive assessment phase. The feedback loop ensures that the probabilistic sampling is guided toward the most promising trajectories, improving the likelihood of finding the true optimal path. This two-stage feedback approach maintains optimization accuracy while achieving faster processing.
Solution Approach 2:
The patent performs preliminary probabilistic assessment to pre-identify an elite set of trajectories before conducting the refined exhaustive assessment. This preliminary action filters out clearly suboptimal trajectories early in the process, so that the computationally intensive exhaustive assessment is applied only to trajectories that have a high probability of being optimal. This preliminary filtering improves both processing speed and maintains accuracy.
3Manufacturing precision
If multiple parameters (altitude, speed, heading) are optimized simultaneously, then manufacturing precision (optimization accuracy) is improved, but device complexity (computational complexity) deteriorates
Solution Approach 1:
The patent segments the multi-parameter optimization problem by representing it as a series of waypoint adjustments along trajectories. Each trajectory is evaluated based on multiple parameters (altitude, speed, heading) simultaneously, but the search space is organized around discrete waypoints rather than continuous parameter spaces. This segmentation reduces computational complexity while maintaining the ability to optimize all parameters together.
Solution Approach 2:
The patent manages computational complexity by changing the representation of parameters from continuous values to discrete waypoint-based specifications. Instead of optimizing altitude, speed, and heading as continuous variables throughout the entire flight path, the system defines specific waypoints with target parameters and allows the trajectory to be adjusted by selecting among predefined parameter options at each waypoint. This parameter discretization reduces the computational burden of multi-parameter optimization.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Embodiments provide for vertical flight path optimization by generating a plurality of waypoints with allowable parameters for a flightpath at which a course, including elements for heading, altitude, and speed, of an aircraft is adjustable; calculating a number of unique trajectories available based on the plurality of waypoints; when the number of unique trajectories is greater than a threshold number of trajectories, performing a probabilistic assessment of the unique trajectories to identify an elite set of trajectories that include those trajectories with efficiency metrics within an upper range of a set of assessed trajectories; identifying mobile waypoints in trajectories of the elite set of trajectories; performing a global optimal path assessment, wherein positions of mobile waypoints are adjusted within an associated trajectory to identify an optimal trajectory for the aircraft on the flightpath; and providing the optimal trajectory to the aircraft to follow the flightpath according to the optimal trajectory.