Thermal Spray Coating Image Analysis for Accurate Porosity Separation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image analysis techniques for thermal spray coatings struggle to accurately distinguish between oxide components and voids, leading to overcounting of porosity and difficulty in determining the percentage of porosity from closed pores and splat lines, which hinders quality control and adaptive control of thermal spray processes.
Innovation Solution
Advanced image processing techniques using a computing device to normalize images, apply an oxide filter to remove oxide components, and execute a shape detection module to differentiate between closed pores and splat lines, enabling accurate quantification of porosity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional image analysis techniques are used to quantify porosity, then the analysis process is simple, but the measurement precision is poor due to overcounting oxide components as voids
Solution Approach 1:
The image analysis process is segmented into distinct stages: oxide component identification and removal, followed by separate analysis of closed pores and splat lines. This segmentation allows each feature type to be quantified independently, improving measurement precision while managing complexity through structured processing steps.
Solution Approach 2:
Oxide components are extracted and removed from the image data before porosity analysis. By taking out the oxide components that would otherwise be misidentified as voids, the system achieves accurate porosity measurement without requiring complex differentiation algorithms for all feature types.
2Measurement precision
If simple pixel summing techniques are used, then the ease of operation is high, but the measurement precision is insufficient to distinguish between different porosity types
Solution Approach 1:
The porosity analysis is segmented into separate quantification steps for closed pores and splat lines after oxide removal. This allows precise differentiation between porosity types through structured analysis, maintaining operational clarity while achieving high measurement precision.
Solution Approach 2:
The analysis transitions from simple 2D pixel summing to multi-dimensional feature differentiation by analyzing shape, size, and spatial distribution characteristics of remaining features after oxide removal, enabling precise porosity type differentiation.
3Productivity
If manual image comparison by skilled operators is used, then the adaptability to different coating types is high, but the productivity is low due to time-consuming analysis
Solution Approach 1:
The system performs self-service automation by automatically identifying, removing oxide components, and quantifying porosity features without requiring skilled operator intervention. This automated self-service approach dramatically increases productivity while the structured algorithm design keeps system complexity manageable.
Solution Approach 2:
Manual visual comparison by operators is replaced with automated image processing algorithms that mechanically identify and quantify features. This substitution of mechanical manual analysis with automated computational processes increases productivity while maintaining accuracy through algorithmic precision.
Data Source
AI summary
A method includes receiving, by a computing device, a raw image indicative of a cross-section of a thermally-sprayed layer. The image includes a matrix of pixels, and each respective pixel in the matrix of pixels defines a luminance value. The method may further include determining, based on the luminance values, at least one pixel that corresponds to an oxide component in the layer and removing the at least one pixel that corresponds to the oxide component in the layer to generate a modified matrix of pixels. The method may further include generating an oxide-filtered image based on the modified matrix of pixels. The method may further include converting, by the computing device and based on the luminance values, the oxide-filtered image into a binary image and determining, by the computing device and based at least partially on the binary image, a porosity of the coating layer.