Study on quantitative analysis method of silicon in sinter based on neural network and laser-induced breakdown spectroscopy
CHEN Yujuan1,2,3, DING Yu*1,2,3, ZHU Shaonong1,2,3, DENG Fan1,2,3, CHEN Feifan1,2,3
1. Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology,Nanjing University of Information Science & Technology,Nanjing 210044,China; 2. Jiangsu Engineering Research Center on Meteorological Energy Using and Control,Nanjing University of Information Science & Technology,Nanjing 210044,China; 3. Jiangsu Key Laboratory of Big Data Analysis Technology,Nanjing University of Information Science & Technology,Nanjing 210044,China
Abstract:The content of silica in the sinter had an important influence on the output of slag and energy consumption in smelting.Therefore,it was of great research significance to explore a quick and accurate analysis method of the content of silicon in the sinter.30 actual samples of sinter ore was analyzed quickly by laser-induced breakdown spectroscopy (LIBS).After the spectral signals in the range of 190-300 nm was collected,a standard curve of the characteristic line (Si 288.16 nm) was established to analyze the relationship between the intensity and the element concentration.Then two neural network prediction models were constructed to analyze their prediction performance with different numbers of features as input.The experimental results showed that the standard curve method had poor prediction performance and the correlation coefficient was 0.230 9.The neural network prediction model built with 55 features had overfitting phenomenon and could not meet the detection needs.The neural network prediction model built with 5 features was optimum among the three models.For the test set,the correlation coefficient was 0.886 3,the root mean square error was 0.209 0,and the relative error was 1.42%.In addition,as the number of features decreased,the average training time of the model decreased from 11.9 s to 0.3 s.LIBS technology combined with neural network method could effectively analyze the content of silicon in sintered ore,and provide data support for real-time adjustment of ingredients in the metallurgical process.
张芳,李荣,罗果萍,等.包钢低硅烧结矿的冶金性能[J].钢铁研究学报,2013,25(2):4-8.ZHANG Fang,LI Rong,LUO Guoping,et al.Metallurgical property of low silicon sinter in Baotou iron and steel(Group)[J].Journal of Iron and Steel Research,2013,25(2):4-8.
[2]
唐凌剑,于青,李庆美,等.缩短烧结矿碱度检测滞后的研究[J].烧结球团,2016,41(4):7-10.TANG Lingjian,YU Qing,LI Qingmei,et al.Study on shortening the detection lagging of sinter basicity[J].Sintering and Pelletizing,2016,41(4):7-10.
[3]
DIDIER Bonvin,RAVI Yellepeddi.X 射线荧光光谱法和X 射线衍射技术在钢铁工业中的最新进展:化学分析与相分析的结合[J].冶金分析,2009,29(12):1-6.DIDIER Bonvin,RAVI Yellepeddi.Latest developments in X-ray fluorescence spectrometry and X-ray diffraction technology for iron and steel industry:integrated chemical and phase analysis[J].Metallurgical Analysis,2009,29(12):1-6.
[4]
Ene A,Pantelica A.Study of transfer of minor elements during ironmaking by neutron activation analysis[J].Radiochimica Acta,2010,98(1):53-57.
[5]
Ding Y,Zhang W,Zhao X,et al.A hybrid random forest method fusing wavelet transform and variable importance for the quantitative analysis of K in potassic salt ore using laser-induced breakdown spectroscopy[J].Journal of Analytical Atomic Spectrometry,2020,35(6):1131-1138.
[6]
Lin Q,Yin P,Duan Y,et al.Quantitative multiple-element simultaneous analysis of seaweed fertilizer by laser-induced breakdown spectroscopy[J].Optics Express,2020,28(10):14198-14208.
[7]
Pathak A K,Kumar R,Singh V K,et al.Assessment of LIBS for spectrochemical analysis:A review[J].Applied Spectroscopy Reviews,2012,47(1):14-40.
[8]
Qi J,Zhang T,Tang H,et al.Rapid classification of archaeological ceramics via laser-induced breakdown spectroscopy coupled with random forest[J].Spectrochimica Acta Part B:Atomic Spectroscopy,2018,149:288-293.
[9]
Yang G,Han X,Wang C,et al.The basicity analysis of sintered ore using laser-induced breakdown spectroscopy (LIBS) combined with random forest regression (RFR)[J].Analytical Methods,2017,9(36):5365-5370.
[10]
Deng X,Yang G,Zhang H,et al.Accurate quantification of alkalinity of sintered ore by random forest model based on PCA and variable importance (PCA-VI-RF) [J].Applied Optics,2020,59(7):2042-2049.
[11]
Wang P,Li N,Yan C,et al.Rapid quantitative analysis of the acidity of iron ore by the laser-induced breakdown spectroscopy (LIBS) technique coupled with variable importance measures-random forests (VIM-RF)[J].Analytical Methods,2019,11(27):3419-3428.
[12]
Ding Y,Yan F,Yang G,et al.Quantitative analysis of sinters using laser-induced breakdown spectroscopy (LIBS) coupled with kernel-based extreme learning machine (K-ELM)[J].Analytical Methods,2018,10(9):1074-1079.
[13]
Lopez-Moreno C,Amponsah-Manager K,Smith B W,et al.Quantitative analysis of low-alloy steel by microchip laser induced breakdown spectroscopy[J].Journal of Analytical Atomic Spectrometry,2005,20(6):552-556.
[14]
Freedman A,Iannarilli F J,Wormhoudt J C.Aluminum alloy analysis using microchip-laser induced breakdown spectroscopy[J].Spectrochimica Acta Part B:Atomic Spectroscopy,2005,60(7):1076-1082.