Aircraft Flight Regime Detection Using Smoothed Maneuver Classification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for detecting flight regimes in aircraft face challenges in accurately analyzing the diverse durations of maneuvers, leading to reduced precision and dependency on feature extraction techniques that can compromise accuracy.

Innovation Solution

The method involves smoothing and registration of primary quantity samples using kernel nearest neighbor smoothing and shift registration, followed by training a fuzzy C-means classifier on processed data to identify flight regimes, reducing the impact of temporal shifts and improving detection accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If advanced data processing techniques are used to analyze temporal trends of primary quantities, then maneuver detection capability is improved, but device complexity increases

Engineering Contradiction:
Improvemaneuver detection accuracyVSAvoiddata processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the continuous temporal trends of primary quantities into discrete maneuver episodes by identifying start and end points based on threshold criteria. This segmentation transforms the complex continuous analysis problem into manageable discrete segments, reducing processing complexity while maintaining detection accuracy

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent extracts key maneuver characteristics (such as duration, intensity, and type) from the temporal trends of primary quantities by applying filtering and feature extraction techniques. This extraction isolates the essential maneuver information from the raw data, improving detection accuracy without requiring analysis of the entire complex dataset

Inventive Principle:
Principle #2Taking out (Extraction)

2Measurement precision

If temporal trends of primary quantities are analyzed to detect maneuvers, then flight regime detection capability is improved, but measurement precision deteriorates due to different maneuver durations

Engineering Contradiction:
Improveflight regime detection accuracyVSAvoidmaneuver duration variability
Core Design Contradiction:
Measurement precisionVSDuration of action of moving object

Solution Approach 1:

The patent employs dynamic threshold criteria for identifying maneuver start and end points, allowing the detection parameters to adapt to different maneuver durations. This dynamic approach enables accurate detection of both short and long maneuvers by adjusting the threshold criteria based on the observed temporal characteristics, thereby maintaining measurement precision across varying maneuver durations

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent changes the analysis parameters (such as time windows, sampling rates, and threshold values) based on the detected maneuver duration characteristics. By adapting these parameters to match the specific duration of each maneuver type, the system maintains high detection accuracy whether analyzing brief or extended maneuver sequences

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4163750B1Method and system for detecting flight regimes of an aircraft, on the basis of measurements acquired during an aircraft flight
Publication Date: 2024.01.31 LEONARDO SPA
  • EP4163750B1 patent drawingFigure 1A~2
  • EP4163750B1 patent drawingFigure 1B
  • EP4163750B1 patent drawingFigure 3

AI summary

Method implemented by computer for detecting flight regimes of an aircraft (1) equipped with a monitoring system (2) that acquires samples of quantities relative to the flight including: acquiring (202) an unknown matrix (TFDMx) including, for each quantity, a corresponding series of samples (sx1[n] - sxNQ[n]); performing (204) smoothing operations of each series of samples, so as to generate a corresponding series of smoothed samples (sx'1[n]-sx'NQ[n]) and determining a corresponding approximating function (Fxi(t)) defined by a respective series of coefficients (Cxk,i) and by a plurality of base functions (ϕk(t)), the smoothed series of samples forming a smoothed unknown matrix (TFDMx'); on the basis of the base functions, applying (206) 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 (208) a flight regime in which the aircraft operated, on the basis of the estimates generated by the classifier.