Dynamic Projection Angle Selection for X-ray Inspection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing non-destructive testing methods, such as X-ray computed tomography and 2D X-ray radiography, face challenges in speed and accuracy, particularly in inline industrial applications, where long acquisition times and high computational costs hinder near real-time defect identification and classification.
Innovation Solution
A method and system that utilize a limited number of projection images by simulating and comparing them to a 3D model of the item, determining optimal viewing angles and orientations to detect defects, leveraging CAD data and machine learning algorithms for efficient defect detection without requiring tomographic reconstruction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If hundreds to thousands of equiangular X-ray projections are acquired for CT-based quality control, then volumetric information and measurement precision are improved, but acquisition time and productivity deteriorate
Solution Approach 1:
The patent pre-calculates optimal projection angles based on CAD models and defect detection requirements before actual inspection. This preliminary action identifies the minimal set of angles needed to detect specific defect types, eliminating the need to acquire hundreds of equiangular projections and thus reducing acquisition time while maintaining detection capability
Solution Approach 2:
Instead of acquiring complete 360-degree equiangular projections, the patent acquires only the specific projection angles that are most informative for detecting particular defect types. This partial action approach obtains sufficient volumetric information for quality control without the excessive number of projections required by traditional CT methods
2Reliability
If many real images are acquired to image potential defects with good visibility, then defect detection reliability is improved, but acquisition time and productivity worsen
Solution Approach 1:
The system performs preliminary analysis using CAD models to predict which projection angles will reveal specific defect types. This pre-planning ensures that the acquired images are targeted and informative, achieving reliable defect detection with fewer images rather than acquiring many images through trial and error
Solution Approach 2:
The patent uses iterative optimization where initial projection images are analyzed, and the system feedback-adjusts the selection of subsequent projection angles based on detected features and regions of interest. This feedback mechanism ensures reliable defect detection while minimizing the total number of images required
3Measurement precision
If feature vectors for each pixel of high-resolution radiographic images are compared, then defect detection precision is improved, but computational cost and processing time worsen
Solution Approach 1:
The patent extracts and compares only specific feature vectors that are most relevant for defect detection, such as those corresponding to regions of interest or defect-prone areas, rather than processing all pixel feature vectors in high-resolution images. This selective extraction maintains defect detection precision while significantly reducing computational processing time
Solution Approach 2:
The system applies different processing strategies to different regions of the image, focusing computational resources on regions with higher probability of containing defects. This local quality approach ensures high defect detection precision in critical areas while reducing overall computational burden
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 enables fast and accurate non-destructive 3D inspection with reduced computational costs, allowing for efficient defect detection and classification in industrial processes, even in real-time, by optimizing the acquisition of projection images based on predefined regions of interest and prior knowledge.
Implementation Method 1
X-ray computed tomography (CT) can be used, as known in the art, for non-destructive testing and/or quality control
Implementation Method 2
acquiring a projection image of the item using a radiation imaging system
Data Source
AI summary
A method is provided for inspection of an item comprising acquiring a projection image of the item using a radiation imaging system and obtaining a plurality of simulated projection images of the item or a component thereof, based on a simulation of a numerical three-dimensional model. A relative orientation of the item with respect to the imaging system is determined by comparing the projection image to the plurality of simulated images, and at least one angle of rotation is determined by taking into account a viewing angle and the relative orientation. The method further comprises moving the item and/or the imaging system in accordance with the at least one angle of rotation and acquiring a further projection image of the item.