Aircraft Maneuver Detection Using Clustering Algorithms

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Health and usage monitoring systems (HUMS) in aircraft struggle to accurately quantify and record flight maneuvers due to static regime parameter definitions, leading to underestimated maneuver durations and overcounting of occurrences, which affects fatigue damage calculations and maintenance decisions.

Innovation Solution

A clustering algorithm is employed to post-process HUMS regime sequence data, mapping it into quantifiable composite worst-case (CWC) spectrum regimes, using persistence parameters calibrated with flight test and fleet data to reduce uncertainty and ensure conservative fatigue damage estimation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If static regime parameter definitions are used to identify maneuvers, then the system is simple to implement, but maneuver durations are underestimated and occurrence counts are overestimated

Engineering Contradiction:

Improvesimplicity of implementationVSAvoidaccuracy of maneuver duration and occurrence

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent transitions from static regime parameter definitions to dynamic clustering algorithms that adaptively group regime sequences. The clustering approach dynamically adjusts maneuver identification based on aggregated sensor data patterns, allowing the system to accurately capture maneuver durations and occurrences without being constrained by fixed parameter thresholds.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent applies preliminary aggregation of regime sequences before final maneuver identification. By pre-processing and grouping similar regime sequences using clustering algorithms, the system prepares optimized data structures that enable accurate maneuver quantification while reducing computational complexity during real-time operation.

Inventive Principle:

Principle #10Preliminary action

2Reliability

If comprehensive maneuver data is collected for fatigue damage calculations, then safety is improved, but data processing complexity increases

Engineering Contradiction:

Improvesafety through fatigue damage calculationVSAvoiddata processing complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces complex manual or rule-based maneuver identification processes with automated clustering algorithms. These algorithms automatically aggregate regime sequences, identify maneuver patterns, and calculate fatigue damage parameters, significantly reducing data processing complexity while maintaining comprehensive safety monitoring capabilities.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent transforms raw regime sequence data into meaningful maneuver parameters through clustering-based parameter aggregation. By changing the data representation from individual regime instances to clustered maneuver groups with aggregated statistics, the system enables efficient fatigue damage calculations while preserving comprehensive safety information.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS8744651B2Method of determining a maneuver performed by an aircraft

Publication Date: 2014.06.03 SIKORSKY AIRCRAFT CORP

AI summary

A method of determining a maneuver performed by an aircraft having sensors for monitoring motion data, the method including periodically sampling the sensors to electronically determine segments of motion data of the aircraft; aggregating sequences of the segments of the motion data; comparing the aggregated segments of motion data to models of particular maneuvers; and determining the maneuver performed by the aircraft.