Premium
Identification of aluminum alloy by laser‐induced breakdown spectroscopy combined with machine algorithm
Author(s) -
Dai Yujia,
Zhao Shangyong,
Song Chao,
Gao Xun
Publication year - 2021
Publication title -
microwave and optical technology letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.304
H-Index - 76
eISSN - 1098-2760
pISSN - 0895-2477
DOI - 10.1002/mop.32810
Subject(s) - support vector machine , aluminium , laser induced breakdown spectroscopy , alloy , algorithm , principal component analysis , identification (biology) , least squares support vector machine , materials science , artificial intelligence , computer science , laser , metallurgy , optics , physics , botany , biology
Discarded aluminum alloys are a form of recyclable metal materials, and their classification and identification are highly important. In this work, laser‐induced breakdown spectroscopy (LIBS) technique combined with principal component analysis (PCA) and least‐squares support‐vector machine (LSSVM) algorithm were used to classify and identify five types of aluminum alloys. Exploratory analysis of five types of aluminum alloys by PCA was performed to achieve better segregation. The identification accuracy of the support‐vector machine (SVM) and LSSVM for aluminum alloy were 98.33% and 100%, respectively. The higher identification success rate was obtained using the LSSVM algorithm. Therefore, the LIBS technique combined with the PCA and LSSVM algorithms represents an efficient approach to identifying aluminum alloys.