Numerical Analysis of X-ray and SEM Images for Anomaly Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for inspecting explosive pellets used in downhole operations face challenges in detecting manufacturing faults and design anomalies due to limitations in human-eye discernible grey-scale images from scanning electron microscopes and X-ray scanning technologies, making it difficult to ensure consistent performance and density distribution.
Innovation Solution
The use of numerical analysis on X-ray, SEM, or CT scan images to assign numeric values to pixels, allowing for the identification of anomalies such as voids, fissures, and density gradients that are not visible to the naked eye, using a processing system with a processor and memory to compare these values to reference data for anomaly detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If grey-scale images from scanning electron microscopes or X-ray scanning technology are used for inspection, then the inspection can be performed, but the ability to detect subtle anomalies is insufficient because the images contain details not discernable to the human eye
Solution Approach 1:
The patent transforms the inspection approach by changing the parameter of image analysis from visual grey-scale interpretation to quantitative numerical analysis. By converting pixel intensity values into numerical data and analyzing statistical parameters (mean, standard deviation, skewness, kurtosis), the system detects subtle anomalies that are imperceptible in standard grey-scale images, thereby improving measurement precision without losing information.
2Measurement precision
If numerical analysis of pixel values is performed to detect subtle anomalies, then anomaly detection capability is improved, but the complexity of the inspection system increases
Solution Approach 1:
The patent replaces the mechanical/visual inspection system with an automated computational system. Instead of relying on human visual analysis of grey-scale images, the system uses computer-based numerical analysis of pixel values, calculating statistical parameters automatically. This substitution increases detection capability while managing complexity through automation rather than manual processes.
Solution Approach 2:
The patent introduces numerical data as an intermediary between the raw image data and the anomaly detection process. By converting pixel intensity values into numerical parameters (mean, standard deviation, skewness, kurtosis) and comparing these against reference values, the system creates a bridge that enables precise anomaly detection while maintaining system manageability through structured data processing.
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 the detection of subtle anomalies in explosive pellets, improving the control over manufacturing and design processes, leading to better-performing and more stable pellet designs, and can be applied to other objects like printed circuit boards or semiconductor materials.
Implementation Method 1
X-ray scanning technology
Implementation Method 2
scanning electron microscopes
Implementation Method 3
X-ray computed tomography
Data Source
AI summary
A non-destructive inspection method that comprises obtaining one or more images corresponding to an X-ray, scanning electron microscope, or CT scan of an object, assigning numeric values to pixels of the images, comparing the numeric values to reference numeric values, and identifying an anomaly in the object based on the comparison. A non-destructive inspection system that comprises at least one processor, a memory in communication with the processor and storing instructions that causes the processor to obtain an image corresponding to an X-ray, scanning electron microscope, or CT scan of an object, assign numeric values to pixels of the image, compare the assigned numeric values to reference numeric values, and identify an anomaly in the object based on the comparison.