Quantitative analysis of iron slurry based on laser induced breakdown spectroscopy combined with mutual information feature selection partial least squares method
1. Shenyang University of Chemical Technology, Shenyang 110142, China; 2. State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China; 3. Key Laboratory of Networked Control Systems, Chinese Academy of Sciences, Shenyang 110016, China; 4. Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China; 5. University of Chinese Academy of Sciences, Beijing 100049, China
Abstract：At present, the relative accurate method for the detection of iron slurry grade is the traditional chemical analysis. However, this method has long testing period and lagging problem. Moreover, it cannot realize the online detection. Laser induced breakdown spectroscopy (LIBS) has some advantages such as on line, in situ and rapidness,etc. Therefore,the grade of iron element in iron slurry tailings from iron ore beneficiation was analyzed by LIBS. Since the spectral data collected by LIBS contained a lot of useless redundant information for composition analysis, the modeling complexity was increased, leading to insufficient accuracy and poor generalization ability of the established model. Therefore, refer to the partial least squares (PLS) model, the PLS based on mutual information feature selection was proposed. The experimental results showed that the analytical accuracy of PLS model based on mutual information feature selection was significantly improved compared to the conventional PLS model. The determination coefficient (R2) of sample increased from 0.52 to 0.90. The mean absolute error (MAEP) of testing sample decreased from 2.87% to 1.38%. The mean absolute error (MAE) of total samples decreased from 1.0% to 0.60%.
[1] Wills B A,Hopkins D W.Mineral processing technology[M].3th ed.Elsevier,1985:376-379. [2] 王海军,王伊杰,李文超,等.全国矿产资源节约与综合利用报告(2019)[J].中国国土资源经济(Natural Resource Economics of China),2020,33(2):2. [3] 陈雨娟,丁宇,朱绍农,等.神经网络与激光诱导击穿光谱技术结合的烧结矿中硅元素定量分析方法探究[J].冶金分析,2021,41(1):24-29. CHEN Yujuan,DING Yu,ZHU Shaonong,et al.Study on quantitative analysis method of silicon in sinter based on neural network and laser-induced breakdown spectroscopy[J].Metallurgical Analysis,2021,41(1):24-29. [4] GUO Lianbo,ZHANG Deng,SUN Lanxiang,et al.Development in the application of laser-induced breakdown spectroscopy in recent years:A review[J].Frontiers of Physics,2021,16(2):22500. [5] 辛勇,李洋,蔡振荣,等.激光诱导击穿光谱液态金属成分在线分析仪在线监测熔融铝液中元素成分[J].冶金分析,2019,39(1):15-20. XIN Yong,LI Yang,CAI Zhenrong,et al.On-line monitoring of elemental composition in molten aluminum by laser-induced breakdown spectroscopy online analyzer for liquid metal composition[J].Metallurgical Analysis,2019,39(1):15-20. [6] Zaytsev S M,Popov A M,Chernykh E V.Comparison of single and multivariate calibration for determination of Si,Mn,Cr and Ni in high-alloyed stainless steels by laser-induced breakdown spectrometry[J].Journal of Analytical Atomic Spectrometry,2014,29(8):1417-1424. [7] Death D L,Cunningham A P,Pollard L J.Multi-element analysis of iron ore pellets by laser-induced breakdown spectroscopy and principal components regression[J].Spectrochimica Acta Part B Atomic Spectroscopy,2008,63(7):763-769. [8] Death D L,Cunningham A P,Pollard L J.Multi-element and mineralogical analysis of mineral ores using laser induced breakdown spectroscopy and chemometric analysis[J].Spectrochimica Acta Part B Atomic Spectroscopy,2009,64(10):1048-1058. [9] Yaroshchyk P,Death D L,Spencer S J.Comparison of principal components regression,partial least squares regression,multi-block partial least squares regression,and serial partial least squares regression algorithms for the analysis of Fe in iron ore using LIBS[J].Journal of Analytical Atomic Spectrometry,2012,27(1):92-98. [10] Yaroshchyk P,Death D L,Spencer S J.Quantitative measurements of loss on ignition in iron ore using laser-induced breakdown spectroscopy and partial least squares regression analysis[J].Applied Spectroscopy,2010,64(12):1335-1341. [11] Hao Z,Li C,Shen M,et al.Acidity measurement of iron ore powders using laser-induced breakdown spectroscopy with partial least squares regression[J].Optics Express,2015,23(6):7795-7801. [12] Khajehzadeh N,Haavisto O,Koresaar L.On-stream and quantitative mineral identification of tailing slurries using LIBS technique[J].Minerals Engineering,2016,98:101-109. [13] 邹孝恒,郝中骐,易荣兴,等.基于遗传算法和偏最小二乘法的土壤激光诱导击穿光谱定量分析研究[J].分析化学,2015(2):181-186. ZOU Xiaoheng,HAO Zhongqi,YI Rongxing,et al.Quantitative analysis of soil by laser-induced breakdown spectroscopy using genetic algorithm-partical least squares[J].Chinese Journal of Analytical Chemistry,2015(2):181-186. [14] 朱绍农,丁宇,陈雨娟,等.LIBS与变量选择PLS结合的含油土壤中Cu,Ni定量分析[J].光谱学与光谱分析,2020,40(12):3812-3817. ZHU Shaonong,DING Yu,CHEN Yujuan,et al.Quantitative analysis of Cu and Ni in oil-contaminated soil by LIBS combined with variable selection method and PLS[J].Spectroscopy and Spectral Analysis,2020,40(12):3812-3817. [15] 袁备,徐送宁,宁日波,等.基于主元提取神经网络LIBS光谱分析[J].沈阳理工大学学报,2018,37(6):86-91. YUAN Bei,XU Songning,NING Ribo,et al.Analysis of LIBS spectrum based on principal component extraction neural network[J].Journal of Shenyang Ligong University,2018,37(6):86-91. [16] Zhu X.Semi-supervised learning with graphs[D].Pittsburgh:Carnegic Mellon University,2005. [17] Darbellay G A.An estimator of the mutual information based on a criterion for independence[J].Computational Statistics & Data Analysis,1999,32:1-17. [18] Kraskov A,Stögbauer H,Grassberger P.Estimating mutual information[J].Physical Review. E,2004,69(6):066138. [19] HOU Jiajia,ZHANG Lei,ZHAO Yang,et al.Mechanisms and efficient elimination approaches of self-absorption in LIBS[J].Plasma Science and Technology,2019,21(3):129-143.
