Aircraft Engine Monitoring Using Flight-Specific Reference Models

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for monitoring aircraft engine state are not robust to changes in the flight envelope, as they rely on global models that may not cover the entire operating range, leading to difficulties in detecting changes in the transfer function, especially when data is scarce or noisy, and can result in false alarms.

Innovation Solution

A device and method that utilize individual flight models learned from data acquired during each flight, linking engine input, environmental, and output variables, allowing for the calculation of estimates and errors associated with these models, using reference values to detect changes in the transfer function without relying on parametric or global models.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If a global model is used to monitor engine state, then the monitoring system is simpler to implement, but it cannot detect changes in the transfer function when data is scarce or noisy

Engineering Contradiction:
Improvemonitoring system complexityVSAvoidtransfer function detection reliability
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The patent divides the monitoring approach into two segments: using individual flight models for each flight to capture local transfer function characteristics, and using reference models for comparison. This segmentation allows detection of transfer function changes without requiring a complex global model covering the entire operating range.

Inventive Principle:
Principle #1Segmentation

2Measurement precision

If individual flight models are created for each flight, then detection accuracy improves, but computational complexity increases

Engineering Contradiction:
Improvetransfer function change detection accuracyVSAvoidmodel calculation complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies local quality by creating individual flight models that are specific to each flight's operating conditions. Each model is tailored to the local characteristics of that flight, improving detection accuracy for transfer function changes in that specific context without requiring a universally complex global model.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent performs preliminary calculations by pre-processing flight data and creating individual flight models before the actual monitoring comparison. This preliminary action organizes the computational work in advance, making the real-time detection process more efficient despite the complexity of individual model creation.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If reference values from a prescribed set are used for comparison, then false alarms are reduced, but the system cannot adapt to flights outside the reference domain

Engineering Contradiction:
Improvefalse alarm reductionVSAvoidflight domain coverage
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent implements dynamics by allowing the system to adapt when reference values are unavailable. Individual flight models can be created for new flight conditions, and the reference set can be expanded dynamically. This makes the system both reliable for known flights and adaptable to new operating domains.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP4042007B1Apparatus, method and computer program for monitoring an aircraft engine
Publication Date: 2025.01.01 SAFRAN SA
  • EP4042007B1 patent drawingFigure 1
  • EP4042007B1 patent drawingFigure 2
  • EP4042007B1 patent drawingFigure 3

AI summary

The invention relates to an apparatus for monitoring over time the state of an aircraft propulsion engine, characterised by a module (ACQ) for capturing flight (Vi) data (DVi) from the engine, the data comprising input values ​​(E1i) during the flight (Vi), environmental variable values ​​(ENV1i) of the engine and output values ​​(S1i), a learning module (APPR) for computing, from the data (DVi), an individual model (fi) of the flight (Vi), a module (MUT) which uses the models (fi) to compute values ​​(S2i=fi(ER, ENVR)) of the output variables, which values are obtained by applying the model (fi) to input reference values ​​(ER) of the engine (M) and to environmental (ENV) variable reference values (ENVR) of the engine (M) and an error (εi) associated with the model (fi), the reference values ​​(ER, ENVR, SR) belonging to a prescribed set of identical reference data (DR) for the models (fi).