3D Component Defect Detection via Histogram Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Identifying internal defects in safety-critical or complex manufactured components is complex and computationally inefficient, especially when large defects are present, requiring individual testing to ensure manufacturing tolerances.
Innovation Solution
A method involving a volumetric scan to generate a 3D image of the component, creating a histogram of voxel values, comparing it to a template histogram using characteristics like peak frequencies and standard deviation, and employing machine learning to determine defects based on threshold differences.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If traditional individual testing or analysis methods are used to identify internal defects in manufactured components, then manufacturing precision and reliability are improved, but computational efficiency and productivity deteriorate
Solution Approach 1:
The patent extracts only the essential information needed for defect detection by generating histograms that summarize voxel value frequencies. Instead of analyzing every voxel individually in the 3D scan data, the method transforms the data into compact histogram representations that retain defect-related information while discarding redundant details, thereby improving computational efficiency without sacrificing detection accuracy
Solution Approach 2:
The patent transforms the raw voxel data into histogram parameters (frequency distributions of voxel values) for comparison. By changing the representation from individual voxel values to aggregated histogram characteristics, the method enables faster processing while maintaining the ability to detect defects through statistical comparison between component histograms and template histograms
2Reliability
If comprehensive individual testing of each component is performed to ensure manufacturing tolerances, then reliability is improved, but loss of time and productivity worsen
Solution Approach 1:
The patent creates template histograms from defect-free reference components and uses these templates to quickly assess production components. Instead of performing comprehensive analysis on every component, the method compares each component's histogram against the stored template, enabling rapid quality assurance that maintains reliability while significantly reducing inspection time
Solution Approach 2:
The patent performs preliminary analysis by creating template histograms from known good components before production testing begins. This pre-established reference data allows for rapid comparison and decision-making during actual component inspection, eliminating the need for time-consuming individual analysis of each production component while maintaining quality standards
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 efficiently identifies defects, including large ones, allowing for timely scrapping or remaking of components, reducing computational intensity and improving defect detection accuracy.
Implementation Method 1
The volumetric scan may comprise computational tomography (i.e., CT scan) using x-rays or gamma rays
Implementation Method 2
The volumetric scan may comprise computational tomography (i.e., CT scan) using x-rays or gamma rays
Data Source
AI summary
There is disclosed a method of identifying non-conformance of a manufactured component, the method comprising: performing a volumetric scan to generate a 3-dimensional (3D) image of a volume of space containing the component, the 3D image comprising a plurality of voxels, each voxel representing a sub-volume within the volume of space and assigned a voxel value relating to properties of the material in the sub-volume; generating a component histogram giving the frequency of each voxel value within the volume of space; and comparing the component histogram to a template histogram, and identifying differences between the component histogram and the template histogram, and based on the comparison, determining whether there is a defect in the component.