LIBS Metal Sorting System Using Spectral Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current metal sorting technologies, such as those using near-infrared rays, visible light, and X-rays, face limitations in accurately and efficiently sorting metals due to complex material compositions and multidimensional correlations, leading to low usability and accuracy in waste resource recycling.
Innovation Solution
A metal sorting system utilizing laser-induced breakdown spectroscopy (LIBS) with a method involving LIBS library information, multiple cluster classification, first and second regression component analyses, and weighted sum calculations to discriminate metal types, enhancing accuracy through correlation analysis of metal component distributions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional electromagnetic sensors (near-infrared, visible light, X-ray) are used for metal sorting, then the sorting process can be performed, but the accuracy and usability are low due to complex material compositions and multidimensional correlations
Solution Approach 1:
The patent replaces traditional electromagnetic sensor-based sorting systems with a laser-induced breakdown spectroscopy (LIBS) system. This substitution uses laser physics and plasma spectroscopy mechanisms instead of conventional electromagnetic fields, enabling precise identification of metal compositions through spectral analysis of elemental signatures, thereby resolving the accuracy limitation while maintaining system feasibility
Solution Approach 2:
The patent transforms the sorting approach by changing the detection parameter from electromagnetic interaction (traditional sensors) to laser-induced plasma emission (LIBS). By using laser wavelength, pulse duration, and spectral intensity as control parameters, the system achieves high-precision metal identification based on unique spectral fingerprints of different elements and alloys
2Measurement precision
If simple sorting methods are used, then the device complexity is low, but the sorting accuracy is insufficient for metals with complex compositions and multidimensional correlations
Solution Approach 1:
The patent implements preliminary action by pre-establishing a comprehensive spectral library containing reference data for various metal compositions and alloy types. This pre-processing of spectral information enables the system to quickly compare and identify unknown samples through pattern matching, achieving both high accuracy for complex compositions and efficient processing speed
Solution Approach 2:
The patent creates spectral copies of metal compositions by generating and storing reference spectral signatures for different metals and alloys in a database. These spectral copies serve as templates for rapid comparison and identification, allowing the system to accurately distinguish complex metal compositions without requiring complex real-time analysis algorithms
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 system achieves precise metal sorting by analyzing spectral data and estimating element concentrations, improving accuracy and efficiency in distinguishing metal types, thereby optimizing the recycling process.
Implementation Method 1
analyzing a metal component distribution for various metals using LIBS library information
Implementation Method 2
irradiating the metal sample with a laser
Data Source
AI summary
Disclosed is an operating method of a metal sorting system using laser induced breakdown spectroscopy (LIBS), which may include: analyzing a metal component distribution for various metals using LIBS library information; setting multiple clusters according to the metal component distribution; performing first regression component analysis with respect to spectral data of a metal sample; calculating a probability that the spectral data will belong to each of the set multiple clusters using the first regress component analysis result; performing second regression component analysis with respect to the spectral data which belong to each cluster; and discriminating a type of metal sample by a weighted sum of the calculated probability and the second regression component analysis result.