Study on Identification Method Based on XGBoost Model for Aluminum Alloy Using Laser-Induced Breakdown Spectroscopy
LI Chen-yang1, 2, 3, CHEN Xiong-fei1, 2, 3, ZHANG Yong4, WANG Ya-wen1, 2, 3, TIAN Zhong-chao4, WANG Shi-gong4, ZHAO Zhen-yang4, LIU Ying1, 2, 3，LIU Peng-yu1, 2, 3*
1. National Analysis and Testing Center of Nonferrous Metals and Electronic Materials, GRINM Group Corporation Limited, Beijing 100088, China
2. China United Test & Certification Co., Ltd., Beijing 101400, China
3. General Research Institute for Nonferrous Metals, Beijing 100088, China
4. Shandong Dongyi Photoelectric Instruments Co., Ltd., Yantai 264670, China
Abstract：As an important metal material, aluminum alloy is widely used in various fields, but a large amount of aluminum alloy waste is difficult to sort and recycle. The recycling of aluminum alloy resources is a booster for China’s industrial green and sustainable development. How to quickly and easily identify and classify aluminum alloy waste has become a prerequisite for re-utilization. Laser-induced breakdown spectroscopy (LIBS) is an analytical technique that has developed rapidly in recent years. It has the advantages of fast, full-element analysis, real-time, in-situ, and long-distance detection. It has been widely used in plastics, soil, meat, steel, etc. For recognition research, most of them use the PLS-DA, SIMCA, ANN, SVM, Random Forest and other algorithms to build models. XGBoost algorithm has the advantages of regularization, parallel processing, built-in cross-validation, and high algorithm flexibility. Its model structure is relatively simple; it has a small amount of calculation and superior accuracy. It has become extremely popular in machine learning in recent years. Based on 600 sets of spectral data of six aluminum alloy samples, model extracts spectral features through machine learning to determine the classification. The processed spectral data is randomly divided into a training set, and a test set, and the XGBoost algorithm based on Decision Tree is used for automatic classification and sorting An algorithm model is constructed through the training set and its classification features are extracted; the test set is used to check the stability and usability of the model to qrevent over-fitting. The model obtained by XGBoost under fixed parameters has certain self-adaptability, is less affected by the data set, and the overall accuracy rate can reach 96.67%. Its classification characteristics are consistent with the known element content information, which proves that the characteristic spectral line data based on big data can provide a reference for classification identification；the importance of spectral line features can be ranked according to the feature score generated by XGBoost. Experimental results show that LIBS can be used for rapid identification of different types of aluminum alloys, and provides a new technology for the classification and recovery of waste metals.
Key words：Aluminum alloy; LIBS; Recognition; XGBoost; Decision Tree
李晨阳，陈雄飞，张 勇，王亚文，田中朝，王世功，赵珍阳，刘 英，刘鹏宇. 基于XGBoost的铝合金LIBS光谱分类识别方法[J]. 光谱学与光谱分析, 2021, 41(02): 624-628.
LI Chen-yang, CHEN Xiong-fei, ZHANG Yong, WANG Ya-wen, TIAN Zhong-chao, WANG Shi-gong, ZHAO Zhen-yang, LIU Ying，LIU Peng-yu. Study on Identification Method Based on XGBoost Model for Aluminum Alloy Using Laser-Induced Breakdown Spectroscopy. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(02): 624-628.
[1] Koyanaka，Kobayashi K，Yamamoto，et al. Resourses Conservation and Recycling，2013，75：63.
[2] Aderval S Luna，Fabiano B Gonzaga，Werickson F C da Rocha. Spectrochimica Acta Part B: Atomic Spectroscopy，2018，139：20.
[3] Rosalba Gaudiusoa，Ebo Ewusi-Annana，Noureddine Melikechi，et al. Spectrochimica Acta Part B: Atomic Spectroscopy，2018，146：106.
[4] Ke Liu，Di Tian，Xinxin Deng，et al. Journal of Analytical Atomic Spectrometry，2019，34：1665.
[5] Prasanthi Inakollu，Thomas Philip，Awadhesh K. Rai，et al. Spectrochimica Acta Part B: Atomic Spectroscopy，2009，64：99.
[6] Liang L，Zhang T，Wang K，et al. Applied Optics，2014，53（4）：544.
[7] Xu L，Liang L，Zhang T，et al. Analytical Methods，2014，6（20）：8374.
[8] Campanella B，Grifoni E，Legnaioli S，et al. Spectrochimica Acta Part B: Atomic Spectroscopy，2017，134：52.
[9] Robert P Sherodan，Wei Ming Wang，Andy Liaw，et al. Journal of Chemical Information and Modeling，2016，56(12)：2353.
[10] Chen T，Guestrin C. XGBoost: A Scalable Tree Boosting System. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM，2016. 785.
[11] Jin Zhang，Daniel Mucs，Ulf Norinder，et al. Journal of Chemical Information and Modeling，2019，59(10)：4150.
[12] Aman Agarwal，Liu Y A，Christopher McDowell. Industrial & Engineering Chemistry Research，2019，58(36)：16719.
[13] ZHANG Xiao，LUO A-li（张 枭，罗阿理）. Spectroscopy and Spectral Analysis（光谱学与光谱分析），2019，39（10）：3292.
