Application of laser-induced breakdown spectroscopy assisted by principal component analysis and extreme learning machine in the classification recognition of aluminum alloy
PAN Li-jian, CHEN Wei-fang*, CUI Rong-fang, LI Miao-miao
College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210001, China
Abstract：The quantity of waste products rapidly increases with the development of society in our country. A large number of waste aluminum is also generated. Aluminum is a kind of good renewable resources. However, the traditional separation technology cannot realize the sophisticated classification of waste aluminum according to the respective brand grades. As a result, many high-quality aluminum resources are used after downgrading, leading to a huge waste. The application of laser-induced breakdown spectroscopy (LIBS) assisted by principal component analysis (PCA) and extreme learning machine (ELM) algorithm in the classification recognition of aluminum alloy was investigated. Four brands of aluminum alloy in two series were selected as the experimental samples. Total 420 groups of spectral data were obtained by excitation of sample using LIBS technology. The original spectral data were pretreated. Then 21 spectral lines of five elements (Mg, Mn, Cu, Fe and Si) with main difference in aluminum alloy were selected to constitute 420×21 spectral data matrix. The spectral data were further treated by dimensionality reduction using PCA method. The input variable of model was decreased from 21 to 8. Then 120 groups of spectral data were selected as the training set to establish classification model of aluminum alloy based on ELM. The rest 300 groups of data were selected as the testing set. Under the condition that the content difference of main non-aluminum elements (Mg, Mn, Cu, Fe and Si) was only 0.0021%-3.68%, it was found that the average recognition accuracy rate of classification model based on PCA-ELM was up to 98.01%. The standard deviation was 0.82%. The modeling time was 0.081s. The results showed that the classification model based on PCA-ELM exhibited very high efficiency and stability. Its combination with LIBS technique could be applied for the rapid classification fields in industry. The proposed study provided a reference for the sophisticated classification industry.
潘立剑, 陈蔚芳, 崔榕芳, 李苗苗. 主成分分析结合极限学习机辅助激光诱导击穿光谱用于铝合金分类识别[J]. 冶金分析, 2020, 40(1): 1-6.
PAN Li-jian, CHEN Wei-fang, CUI Rong-fang, LI Miao-miao. Application of laser-induced breakdown spectroscopy assisted by principal component analysis and extreme learning machine in the classification recognition of aluminum alloy. , 2020, 40(1): 1-6.
高安江,王刚,曲信磊,等.废铝再生预处理过程中的杂质分离和分类分选技术研究[J].再生资源与循环经济,2015,8(2):33-36.GAO An-jiang,WANG Gang,QU Xin-lei,et al.The research on impurities separating and sorting technology in the pretreatment process of the aluminum scrap recycling[J].Recyclable Resources and Circular Economy,2015,8(2):33-36.
[2]
黄莫一杰,任贤魏.浅谈再生铝回收及利用技术[J].铝加工,2015(6):51-57.HUANG Mo-yi-jie,REN Xian-wei.On recycling and utilization technology for secondary aluminum[J].Aluminium Fabrication,2015(6):51-57.
[3]
范超,龙思远,李聪,等.废铝分类分离技术的研究进展[J].轻金属,2012(7):61-64.FAN Chao,LONG Si-yuan,LI Cong,et al.The status and development of separating and sorting technology on aluminium scrap[J].Light Metals,2012(7):61-64.
[4]
邱海鸥,郑洪涛,汤志勇.岩石矿物分析[J].分析试验室,2014,33(11):1349-1364.QIU Hai-ou,ZHENG Hong-tao,TANG Zhi-yong.Analysis of rocks and minerals[J].Chinese Journal of Analysis Laboratory,2014,33(11):1349-1364.
[5]
赵书瑞,赵志巍,王华丽,等.激光频率对激光诱导等离子体特性的影响[J].冶金分析,2017,37(6):9-13.ZHAO Shu-rui,ZHAO Zhi-wei,WANG Hua-li,et al.Effect of laser frequency on the laser-induced plasma characteristics[J].Metallurgical Analysis,2017,37(6):9-13.
[6]
Andrade D F,Fortunato F M,Pereira-Filho E R.Calibration strategies for determination of the In content in discarded liquid crystal displays (LCD) from mobile phones using laser-induced breakdown spectroscopy (LIBS)[J]. Analytica Chimica Acta,2019(2):42-49.
[7]
Ruiz F J,Ripoll L,Hidalgo M,et al.Dispersive micro solid-phase extraction (DμSPE) with graphene oxide as adsorbent for sensitive elemental analysis of aqueous samples by laser induced breakdown spectroscopy (LIBS)[J].Talanta,2019,191:162-170.
[8]
Kotzagianni M,Kakkava E,Couris S.Laser-induced breakdown spectroscopy (LIBS) for the measurement of spatial structures and fuel distribution in flames[J].Applied Spectroscopy,2016,70(4):627-634.
[9]
胡勇,范增伟,李超,等.激光诱导击穿光谱结合极限学习机的矿物识别分析研究[J].光谱学与光谱分析,2016,36(S1):471-472.HU Yong,FAN Zeng-wei,LI Chao,et al.Mineral identification analysis of laser-induced breakdown spectrosc-opy combined with extreme learning machine[J].Spectroscopy and Spectral Analysis,2016,36(S1):471-472.
[10]
Dastjerdi M V,Mousavi S J,Soltanolkotabi M,et al.Identification and sorting of PVC polymer in recycling process by laser-induced breakdown spectroscopy (LIBS) combined with support vector machine (SVM) model[J].Iranian Journal of Science and Technology,Transactions A:Science,2018,42(2):959-965.
[11]
朱毅宁,杨平,杨新艳,等.支持向量机结合主成分分析辅助激光诱导击穿光谱技术识别鲜肉品种[J].分析化学,2017,45(3):336-341.ZHU Yi-ning,YANG Ping,YANG Xin-yan,et al.Classification of fresh meat species using laser-induced breakdown spectroscopy with support vector machine and principal component analysis[J].Chinese Journal of Analytical Chemistry,2017,45(3):336-341.
[12]
余琦,马晓红,王锐,等.基于LIBS技术和主成分分析的快速分类方法研究[J].光谱学与光谱分析,2014,34(11):3095-3099.YU Qi,MA Xiao-hong,WANG Rui,et al.Research on fast classification based on LIBS technology and principle component analyses[J].Spectroscopy and Spectral Analysis,2014,34(11):3095-3099.
[13]
韩小孩,张耀辉,孙福军,等.基于主成分分析的指标权重确定方法[J].四川兵工学报,2012,33(10):124-126.HAN Xiao-hai,ZHANG Yao-hui,SUN Fu-jun,et al.Method for determining index weight based on principal component analysis[J].Journal of Ordnance Equipment Engineering,2012,33(10):124-126.
[14]
Huang G B,Li M B,Chen L,et al.Incremental extreme learning machine with fully complex hidden nodes[J].Neurocomputing,2008,71(4-6):576-583.
