Aircraft Flight Regime Detection Using Smoothed Time-Shifted Signals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting flight regimes in aircraft face challenges in accurately distinguishing between maneuvers of varying durations due to their dependency on feature extraction and sensitivity to temporal trends, leading to reduced detection accuracy.
Innovation Solution
The method involves smoothing and registering primary quantity samples using kernel nearest neighbor smoothing and shift registration to generate processed training data, which is then used to train a fuzzy C-means classifier for precise flight regime detection, independent of supervised training and sensitive to temporal shifts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If feature extraction methods are used to detect flight regimes, then the detection process can handle varying maneuver durations, but the detection accuracy is reduced due to sensitivity to temporal shifts and trends
Solution Approach 1:
The patent replaces traditional mechanical feature extraction methods with a deep learning-based neural network system. The neural network automatically learns temporal patterns and features from raw sensor data, eliminating the need for manual feature engineering and reducing sensitivity to temporal shifts. This substitution of the detection mechanism resolves the contradiction by maintaining adaptability to varying maneuver durations while improving detection accuracy through automated feature learning.
Solution Approach 2:
The patent transforms the input data parameters by applying temporal differentiation and other preprocessing operations to the raw sensor signals before feeding them to the neural network. This parameter transformation enhances the network's ability to detect maneuver boundaries by emphasizing relevant temporal patterns while suppressing noise and trends, thereby improving detection accuracy without sacrificing adaptability to different maneuver durations.
2Measurement precision
If advanced data processing techniques are applied to analyze temporal trends, then maneuver detection capability is improved, but the system complexity increases
Solution Approach 1:
The patent replaces complex manual data processing techniques with an automated neural network system. The neural network performs temporal pattern recognition, feature extraction, and maneuver classification in an integrated manner, eliminating the need for multiple separate processing stages. This automation reduces system complexity while maintaining or improving maneuver detection capability.
Solution Approach 2:
The neural network system is self-training and self-optimizing, automatically learning the optimal features and patterns from training data without requiring manual intervention for feature engineering or parameter tuning. This self-service capability reduces the complexity of system configuration and maintenance while enhancing detection performance.
Data Source
AI summary
Method implemented by computer for detecting flight regimes of an aircraft equipped with a monitoring system that acquires samples of quantities relative to the flight including: acquiring an unknown matrix including, for each quantity, a corresponding series of samples; performing smoothing operations of each series of samples, so as to generate a corresponding series of smoothed samples and determining a corresponding approximating function defined by a respective series of coefficients and by a plurality of base functions, the smoothed series of samples forming a smoothed unknown matrix; on the basis of the base functions, applying to the smoothed unknown matrix and to the corresponding sets of coefficients a classifier trained to generate, for each flight regime among a plurality of flight regimes, a corresponding estimate of the probability that the smoothed unknown matrix and the corresponding sets of coefficients belong to a cluster relative to the flight regime; identifying a flight regime in which the aircraft operated, on the basis of the estimates generated by the classifier.