Optical Granular Substance Sorter Using 3D Color Space Thresholding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional optical granule sorting machines require operator adjustment of sensitivity levels, which is cumbersome and unstable, leading to imprecise sorting and reduced yield due to the need for operator expertise in distinguishing between conforming and nonconforming granules.
Innovation Solution
An optical granule sorting machine utilizing three-dimensional color space information to automatically set thresholds by plotting wavelength components of R, G, and B light in a color space, calculating Mahalanobis and Euclidean distances to partition granule clusters, and fitting an inertia equivalent ellipse to set sensitivity levels, eliminating the need for operator decision-making.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If operator manually adjusts sensitivity level, then sorting precision can be improved, but operation complexity and time consumption increase
Solution Approach 1:
The system automatically determines sensitivity levels by analyzing color distribution characteristics of granules itself, without requiring operator intervention. The determination means calculates color space parameters and automatically sets thresholds based on the distribution patterns, making the system self-configuring and eliminating manual adjustment complexity
Solution Approach 2:
The system dynamically changes the sensitivity parameter (threshold value) based on the actual color distribution characteristics detected from the granules. By calculating parameters like average color values and standard deviations from the color distribution data, the system adapts the sensitivity level to match the specific batch of granules being sorted, improving precision without manual intervention
2Measurement precision
If operator frequently adjusts sensitivity level, then sorting accuracy can be optimized, but sorting stability deteriorates
Solution Approach 1:
The system continuously monitors the color distribution characteristics of incoming granules and uses this feedback to maintain optimal sensitivity levels. By calculating real-time statistics from the color distribution data and comparing against established patterns, the system automatically maintains consistent sorting accuracy without requiring repeated operator adjustments, thereby stabilizing the sorting process
Solution Approach 2:
The automatic determination mechanism continuously self-adjusts based on detected color distribution patterns, eliminating the need for operator re-adjustment. This self-maintaining capability ensures sorting stability by keeping the sensitivity level optimally adapted to the current granule batch without human intervention that would cause fluctuations
3Measurement precision
If sensitivity level is set too high, then foreign substance removal improves, but conforming granule loss increases
Solution Approach 1:
The system applies different threshold criteria to different regions of the color distribution space. By analyzing the local density and clustering characteristics of color values, it sets region-specific thresholds that are sensitive enough to detect foreign substances in their respective color ranges while maintaining tolerance for natural variations in conforming granules, thus reducing false positives and granule loss
Solution Approach 2:
The system dynamically adjusts the sensitivity parameter based on the detected color distribution characteristics of the specific granule batch. By calculating parameters such as the standard deviation of color values and the density of color clusters, it optimizes the threshold to perfectly distinguish foreign substances from conforming granules, maximizing foreign substance removal while minimizing conforming granule loss
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
The machine achieves precise sorting by simplifying signal processing and eliminating the need for operator expertise, ensuring accurate separation of conforming and nonconforming granules with improved yield and stability.
Implementation Method 1
an optical detection section that detects light transmitted through the granules or reflected from the granules
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Determination means includes a three-dimensional color distribution data creation section that creates data on wavelength components of R light, G light, and B light from granules in a three-dimensional color space, a Mahalanobis distance interface creation section that partitions the data into a conforming granule cluster area and a nonconforming granule cluster area, a Euclidean distance interface creation section that determines a position of center of gravity of the conforming granule cluster area and a position of center of gravity of the nonconforming granule cluster area to set an interface that allows the positions of center of gravity to lie at a longest distance from each other, a two-dimensional data conversion section that converts into two-dimensional color distribution data by using a line of intersection between the interfaces, and a threshold setting section that creates a closed area by fitting an inertia equivalent ellipse to the nonconforming granule cluster area on the two-dimensional color distribution data and sets a threshold in the closed area.