Aeronautical Component Inspection Using Local Thermal Models

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing non-destructive testing methods for aeronautical parts with complex geometries and heterogeneous materials face challenges in automating the interpretation of thermal image anomalies due to spatial variations in thermal properties and complex geometries, leading to inefficiencies and inconsistencies in determining abnormality indices.

Innovation Solution

A method utilizing local models and micro-prediction areas within active infrared thermography, combined with incremental statistical learning, allows for automatic annotation of thermal image anomalies, reducing positional uncertainty and computational complexity.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If operator visual determination is used to determine abnormality index, then detection accuracy is maintained, but processing time increases significantly and automation is prevented

Engineering Contradiction:
Improveabnormality index determination accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system enables automatic determination of abnormality indices through statistical comparison algorithms that self-evaluate thermal image characteristics without requiring operator intervention. The method compares characteristic vectors automatically against reference models, allowing the system to serve itself in the detection process while maintaining consistent accuracy standards.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the manual visual assessment mechanism with an automated computational system. Statistical algorithms and computer vision techniques substitute for operator visual determination, enabling rapid processing of thermal images while maintaining measurement precision through mathematical comparison methods.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Extent of automation

If global statistical model is used for heterogeneous parts, then automation is achieved, but measurement precision decreases due to spatial variations in thermal properties

Engineering Contradiction:
Improveinterpretation automationVSAvoidabnormality index determination accuracy
Core Design Contradiction:
Extent of automationVSMeasurement precision

Solution Approach 1:

The patent divides the aeronautical part into multiple spatial zones, each with its own local statistical model. This segmentation allows the system to account for spatial variations in thermal properties while maintaining automation. Each zone's characteristics are evaluated independently against region-specific reference models, preserving measurement precision in heterogeneous materials.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The method implements local quality by creating zone-specific statistical models that reflect the unique thermal properties of different regions. Instead of applying a uniform global model, the system adapts the reference characteristics to each spatial zone, ensuring that abnormality determination is precise for locally heterogeneous materials while remaining fully automated.

Inventive Principle:
Principle #3Local quality

3Area of stationary object

If multiple unit acquisitions are performed to cover large parts, then complete inspection is achieved, but device complexity and processing time increase

Engineering Contradiction:
Improveinspection coverage areaVSAvoidacquisition system complexity
Core Design Contradiction:
Area of stationary objectVSDevice complexity

Solution Approach 1:

The patent merges multiple unit acquisition results into a unified abnormality assessment. By combining characteristic vectors from different spatial zones and integrating their statistical comparisons, the system achieves complete inspection coverage while managing complexity through standardized processing procedures that can be applied consistently across all zones.

Inventive Principle:
Principle #5Merging (Combining)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach accelerates the determination of abnormality indices by improving robustness and reducing processing time while maintaining high relevance, enabling efficient detection of defects in large, heterogeneous aeronautical parts.

Implementation Method 1

an instantaneous increase in the surface temperature of the part by several degrees in the case where the excitation source is a flash lamp

Methodology Applied
Scientific EffectThermal radiation: Thermal Radiation

Implementation Method 2

an infrared camera is used to observe the evolution of the temperature on the surface of the part

Methodology Applied
Scientific EffectInfrared radiation: Infrared Radiation

Data Source

PatentEP4118616B1Method and system for the non-destructive inspection of an aeronautical component
Publication Date: 2025.08.27 SAFRAN SA
  • EP4118616B1 patent drawingFigure 1~3
  • EP4118616B1 patent drawingFigure 4~5A
  • EP4118616B1 patent drawingFigure 5B~6

AI summary

A method for the non-destructive inspection of an aeronautical component comprising a step of obtaining a plurality of digital images of a unit area of the aeronautical component, a step of estimating a characteristic image (IMC) representative of the unit area, each pixel of the characteristic image (IMC) comprising a characteristic vector, a step of dividing the characteristic image (IMC) into a plurality of micro prediction zones (MZP), a step of comparing the characteristic vector of each pixel in each micro prediction zone (MZP) with a previously estimated local statistical model (MZP(ZU)-MOD) of the micro prediction zone (MZP), the local model (MZP(ZU)-MOD) of a micro prediction zone (MZP) being obtained by means of a learning algorithm from characteristic vectors of pixels in a micro learning zone of the annotated characteristic image which includes the micro prediction zone.