Aircraft Engine Fault Diagnosis Through Flight Data Permutations

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The analysis of flight data collected during aircraft engine flight tests is complex and time-consuming, requiring improvements for efficient diagnosis.

Innovation Solution

A method and system utilizing a graph-based representation to model mathematical relationships between engine and aircraft parameters, generating output data from flight data, comparing permutations to detect faults, and outputting signals indicative of discrepancies.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional flight data analysis methods are used, then comprehensive diagnosis can be achieved, but the process is complex and time-consuming

Engineering Contradiction:

Improvediagnosis accuracyVSAvoidanalysis time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent segments the complex flight data analysis into multiple permutations of graph-based representations. Each permutation represents a different way of modeling mathematical relationships between parameters, allowing the system to divide the overall diagnosis task into manageable computational units that can be processed efficiently and compared to identify faults.

Inventive Principle:

Principle #1Segmentation

2Reliability

If traditional flight data analysis methods are used, then comprehensive diagnosis can be achieved, but the process is complex

Engineering Contradiction:

Improvediagnosis accuracyVSAvoidanalysis complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent introduces graph-based representations as an intermediary layer between raw flight data and fault diagnosis. These graphs model mathematical relationships between parameters and serve as a mediator that transforms complex data relationships into structured permutations, simplifying the analysis process while maintaining diagnostic comprehensiveness.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Speed

If real-time diagnosis is implemented, then immediate fault detection is achieved, but computational requirements increase

Engineering Contradiction:

Improvediagnosis speedVSAvoidcomputational energy

Core Design Contradiction:

SpeedVSUse of energy by moving object

Solution Approach 1:

The patent applies partial action by generating a plurality of permutations of graph-based representations rather than analyzing all possible relationships. This selective approach allows real-time diagnosis by computing only the necessary permutations needed to detect faults, reducing computational energy requirements while maintaining diagnostic effectiveness.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS11615656B2Method and system for diagnosing an engine or an aircraft

Publication Date: 2023.03.28 PRATT & WHITNEY CANADA CORP

AI summary

Systems and methods for diagnosing an engine or an aircraft are described herein. Flight data of at least one of the engine and the aircraft is obtained. A graph-based representation modeling a mathematical relationship between parameters of at least one of the engine and the aircraft is obtained. The graph-based representation has a plurality of permutations. Output data for the plurality of permutations is generated based on the flight data. The output data for the plurality of permutations is compared and a fault is detected based on a discrepancy in the output data. A signal indicative of the fault is outputted in response to detecting the fault.