Automated X-Ray Image Alignment for Component Displacement Measurement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining the displacement of components within devices during operation are time-consuming and prone to variability due to manual superposition and operator interpretation, leading to inconsistent accuracy.
Innovation Solution
A method involving the processing of x-ray images through normalization, smoothing, and edge detection, followed by alignment and analysis to accurately determine component displacement, utilizing automated algorithms to enhance speed and consistency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual superposition of x-ray images is used, then operator can visualise component displacement, but analysis time is significant and accuracy varies between operators
Solution Approach 1:
The patent replaces the manual mechanical process of image superposition and visual measurement with an automated computer-based image processing system. The system uses algorithms to automatically align images, detect component boundaries, calculate displacements, and generate reports, eliminating the need for manual operator intervention while improving both speed and measurement consistency.
2Measurement precision
If multiple operators review images to increase accuracy through averaging, then measurement precision improves, but analysis time extends even further
Solution Approach 1:
The automated image processing system performs self-service by automatically executing the complete analysis workflow without requiring multiple operators. The system independently aligns images, detects features, calculates displacements, and validates results through algorithmic consistency checks, achieving high precision through automated repetition rather than human collaboration.
3Productivity
If automated algorithms are used for image processing, then analysis speed increases, but processing complexity increases
Solution Approach 1:
The patent segments the complex image processing task into distinct modular stages: pre-processing (noise reduction, contrast enhancement), image alignment (feature detection, transformation), component identification (boundary detection, segmentation), displacement calculation (coordinate transformation, measurement), and result validation. Each stage uses specialized algorithms that can be independently optimized and executed, managing overall complexity through structured decomposition.
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 method provides accurate and efficient determination of component displacement, reducing analysis time and minimizing variability, thereby improving the reliability of device performance assessment.
Implementation Method 1
X-ray images are a useful means of understanding detailed device behaviour during the design, operation and verification of devices such as gas turbine engines
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method of determining the displacement of a component within a device during operation of the device, the method comprising the steps of: obtaining a first x-ray image of the device while the device is in a first operation state; obtaining a second x-ray image of the device while the device is in a second operation state different to the first operation state; processing each of the first and the second image, wherein the processing comprises applying a filter obtained based on the noise of the image and a frequency characteristic of the image; superimposing the first and the second images to align a predetermined point in each of the first and the second images; and measuring the displacement of an edge associated with the component between the first and the second image to obtain the displacement of the component within the device during operation of the device.