Borescope Damage Assessment Using Reference Marker Mapping

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current automated inspection techniques, such as borescopes, face challenges in standardized viewing angles and oblique image capture, leading to inaccuracies in damage assessment of components like gas turbine engines, particularly combustor panels, due to lack of automated analysis and data archiving, and human-machine-interactive systems for absolute metrology and trending.

Innovation Solution

A semi-automated damage detection and assessment system that processes images and videos from borescopes using deep learning and image transformation algorithms to correct viewing angles, quantify damage with absolute metrology, and archive data for trending and lifing analysis, enabling accurate damage assessment and prediction across a fleet of equipment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If borescopes are manually inserted and positioned to inspect components, then the inspection can reach difficult-to-access locations, but the viewing angles vary between inspections and are often oblique, leading to measurement inaccuracies

Engineering Contradiction:

Improveability to reach difficult locationsVSAvoiddamage quantification accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system transforms images captured at various angles and depths into a standardized reference coordinate system by adjusting geometric parameters. Image transformation algorithms recalculate pixel coordinates based on reference markers, converting oblique views into accurate metric measurements regardless of the original viewing angle.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

Reference markers serve as intermediaries between the captured images and the final measurement system. These markers provide a common coordinate framework that allows images taken from different positions and angles to be accurately registered and measured in a standardized reference system.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Productivity

If automated image analysis is implemented, then inspection efficiency increases, but standardized viewing angles and absolute metrology are difficult to achieve

Engineering Contradiction:

Improveinspection efficiencyVSAvoidabsolute metrology capability

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

Reference markers are positioned and registered before the actual damage inspection occurs. This preliminary setup establishes the coordinate transformation relationships needed for subsequent automated measurements, enabling efficient processing of damage images while maintaining absolute metrology accuracy.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system replaces manual measurement processes with automated image processing algorithms. Computer vision techniques automatically detect reference markers, calculate transformation parameters, and measure damage dimensions, eliminating the need for manual angle standardization while maintaining measurement precision.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Area of stationary object

If multiple images are captured from different positions, then complete coverage of the component is achieved, but data archiving and trending across inspections becomes complex

Engineering Contradiction:

Improvecomponent coverageVSAvoiddata archiving system

Core Design Contradiction:

Area of stationary objectVSDevice complexity

Solution Approach 1:

The inspection data is segmented into structured components: reference marker positions, transformation parameters, damage locations, and measurement results. This segmentation allows each element to be stored and processed independently, simplifying the archiving system while maintaining the ability to reconstruct complete component views and track changes over time.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentEP3514525B1Interactive semi-automated borescope video analysis and damage assessment system and method of use

Publication Date: 2022.08.03 RTX CORP

Figure 1
Figure 2
Figure 3

AI summary

A method of assessing damage to a component includes displaying a sensor image of the component in a first viewing pane, displaying a reference image of the component, which is a graphical depiction of the component with accurate dimensions, in a second viewing pane, placing a plurality of first identification markers on the sensor image of the component in the first viewing pane to correspond to a matching location with a second identification marker on the component in the reference image, identifying a region of damage on the component in the sensor image, mapping the region of damage to the component in the reference image using the plurality of first and second identification markers, and calculating a size of the region of damage.