Quantitative analysis of uranium and thorium in niobium-tantalum ore by laser-induced breakdown spectroscopy combined with random forest
PENG Lingling1, XIE Shaorong2, MENG Xiangting1, JIAO Baobao1, LIU Lin3, LIU Xiaoliang*1,3
1. Joint Laboratory for Nuclear Technology Application Innovation,East China University of Technology,Nanchang 330013,China; 2. Experimental Testing Brigade of Jiangxi Provincial Geological Bureau,Nanchang 330013,China; 3. Key Laboratory of Advanced Nuclear Energy Design and Safety,Ministry of Education,Hengyang 421001,China
Abstract：The analysis and determination of radioactive elements including uranium (U) and thorium (Th) in niobium-tantalum ores is a key step in the exploitation process of niobium-tantalum ore, and it has important significance for the radiation safety assessment and environmental protection. In this study, the quantitative analysis of radioactive U and Th in niobium-tantalum ore was investigated in the laboratory based on laser-induced breakdown spectroscopy (LIBS) combined with random forest (RF) algorithm. The contents of U and Th in eleven niobium-tantalum ore samples were determined using the traditional high purity germanium (HPGe) γ spectrometer, which were used as the reference values for LIBS. Nine of the samples were set as the training set for RF modeling, while the remaining two samples were used as the test set for model validation. The LIBS spectra after full spectral area normalization and the corresponding contents were used as the dataset for the RF algorithm. Firstly, the number of decision trees parameter of RF was optimized through five-fold cross-validation. Then, the influence of wavelength feature selection of LIBS spectra on the prediction results was explored by setting the importance score threshold. The results showed that, by combining the wavelength feature selection and optimizing the decision tree parameters, the root mean square error of calibration (RMSEC) of U and Th in the training set was 48 μg/g and 313 μg/g, respectively. For the prediction of U and Th contents in 2# and 6# samples, the root mean square error of validation (RMSEV) of test set was 141 μg/g and 209 μg/g for U, and 750 μg/g and 914 μg/g for Th, respectively. The relative standard deviations (RSD) of multiple measurement results for both elements were both within 7%. Moreover, the average value of multiple measurements was compared with the measurements by the γ spectrometer, and the relative error (RE) of prediction for two elements was within 8%. These results indicated that the combination of LIBS technology with the RF algorithm could effectively achieve the quantitative analysis of radioactive U and Th in niobium-tantalum ores, which provided a reference for the accurate mining and evaluation of niobium-tantalum ores.
[1] 何海洋,何敏,李建武.我国铌矿资源供需形势分析[J].中国矿业,2018,27(11):1-5. HE Haiyang,HE Min,LI Jianwu.Analysis of the niobium resources supply and demand pattern in China[J].China Mining Magazine,2018,27(11):1-5. [2] 黎洁,谢贤,吕晋芳,等.铌矿资源概述及选矿技术研究进展[J].金属矿山,2021(2):120-126. LI Jie,XIE Xian,LÜ Jinfang,et al.Overview of niobium resources and research progress in mineral processing technology[J].Metal Mine,2021(2):120-126. [3] Winefordner J D,Gornushkin I B,Correll T,et al.Comparing several atomic spectrometric methods to the super stars:special emphasis on laser induced breakdown spectrometry,LIBS, a future super star[J].Journal of Analytical Atomic Spectrometry,2004,19:1061-1083. [4] 段晓晨,薛玉兰,刘钢耀. ICP-AES法测定铁矿石及炉渣中镧、铈、镨、钕、钐[J].包钢科技,2023,49(1):93-98. DUAN Xiaochen,XUE Yulan,LIU Gangyao.Determination of lanthanum,cerium,praseodymium,neodymium and samarium in iron ore and slags with inductively coupled plasma-atomic emission spectrometry(ICP-AES)[J].Science and Technology of Baotou Steel,2023,49(1):93-98. [5] 姚明星,郭晓瑞,毛香菊,等.微波消解-电感耦合等离子体质谱法测定铁精矿中稀土元素分量和总量[J].冶金分析,2024,44(2):10-17. YAO Mingxing,GUO Xiaorui,MAO Xiangju,et al.Determination of total amount of rare earth elements and its component in iron concentrate by inductively coupled plasma mass spectrometry with microwave digestion[J].Metallurgical Analysis,2024,44(2):10-17. [6] 李先和,万双,刘子健,等.X射线荧光光谱法测定铜精矿中10种元素[J].冶金分析,2016,36(6):55-59. LI Xianhe,WAN Shuang,LIU Zijian,et al.Determination of ten elements in copper concentrate by X-ray fluorescence spectrometry[J].Metallurgical Analysis,2016,36(6):55-59. [7] 潘从元,吴克富,高海军,等.激光诱导击穿光谱在铜精矿成分在线检测中的应用[J].冶金分析,2023,43(1):8-15. PAN Congyuan,WU Kefu,GAO Haijun,et al.Application of laser-induced breakdown spectroscopy on on-line detection of copper concentrate composition[J].Metal-lurgical Analysis,2023,43(1):8-15. [8] 邱苏玲,李安,王宪双,等.基于激光诱导击穿光谱的矿石中铁含量的高准确度定量分析[J].中国激光,2021, 48(16):201-210. QIU Suling,LI An,WANG Xianshuang,et al.High-accuracy quantitatively analysis of iron content in mineral based on laser-induced breakdown spectroscopy[J].Chinese Journal of Lasers,2021,48(16):201-210. [9] Peter L,Sturm V,Noll R.Liquid steel analysis with laser-induced breakdown spectrometry in the vacuum ultraviolet[J].Applied Optics,2003,42(30):6199-6204. [10] Gookseon J,Hohyun K,Hyunkeun L,et al.Effects of feature engineering on the robustness of laser-induced breakdown spectroscopy for industrial steel classification[J].Spectrochimica Acta Part B:Atomic Spectroscopy,2024,212:106857. [11] Death D,Cunningham A,Pollard L.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. [12] Samira S,Nessrine M,Ismail E,et al.Laser-induced breakdown spectroscopy analysis of palladium in rock ore[J].Spectrochimica Acta Part B:Atomic Spectroscopy,2022,196:106523. [13] 杨国晶.基于LIBS技术的土壤重金属元素污染快速检测与治理方法研究[J].环境科学与管理,2023,48(4):108-113. YANG Guojing.Rapid detection and treatment of soil heavy metal pollution based on LIBS technology[J].Environmental Science and Management,2023,48(4):108-113. [14] MICHEL A P M,SONNICHSEN F.Laser induced breakdown spectroscopy for heavy metal detection in a sand matrix[J].Spectrochimica Acta Part B:Atomic Spectroscopy,2016,125:177-183. [15] 陈君玺,陈莎,杨燕婷,等.激光诱导击穿光谱结合多变量回归法对石灰岩中主量元素的定量分析[J].冶金分析,2021,41(1):13-23. CHEN Junxi,CHEN Sha,YANG Yanting,et al.Quantification of major elements in limestones using laser-induced breakdown spectroscopy combined with multivariate regression approaches[J].Metallurgical Analysis,2021,41(1):13-23. [16] 鄢嘉懿,王艺陶,李燕.基于激光诱导击穿光谱(LIBS)的煤灰熔点快速检测[J].中国无机分析化学,2024,14(2):191-196. YAN Jiayi,WANG Yitao,LI Yan.Rapid detection of coal ash melting point based on laser-induced breakdown spectrum[J].Chinese Journal of Inorganic Analytical Chemistry,2024,14(2):191-196. [17] 刘曙,金悦,苏飘,等.变量重要性-反向传播人工神经网络辅助激光诱导击穿光谱测定铁矿石中硅、铝、钙和镁含量[J].光谱学与光谱分析,2023,43(10):3132-3142. LIU Shu,JIN Yue,SU Piao,et al.Determination of calcium,magnesium,aluminium and silicon content in iron ore using laser-induced breakdown spectroscopy assisted by variable importance-back propagation artificial neural networks[J].Spectroscopy and Spectral Analysis,2023,43(10):3132-3142. [18] 刘一江,闫春华,李茂刚,等.激光诱导击穿光谱(LIBS)结合机器学习算法快速测定石油焦中微量元素[J].中国无机分析化学,2024,14(2):197-204. LIU Yijiang,YAN Chunhua,LI Maogang,et al.Rapid determination of trace elements in petroleum coke by laser-induced breakdown spectroscopy combined with machine learning algorithms[J].Chinese Journal of Inorganic Analytical Chemistry,2024,14(2):197-204. [19] 苏云鹏,贺春景,李昂泽,等.基于共焦LIBS技术结合机器学习的矿石分类识别方法[J].光谱学与光谱分析,2023,43(3):692-697. SU Yunpeng,HE Chunjing,LI Angze,et al.Ore classification and recognition based on confocal LIBS combined with machine learning[J].Spectroscopy and Spectral Analysis,2023,43(3):692-697. [20] 李茂刚,梁晶,闫春华,等.基于激光诱导击穿光谱技术结合随机森林算法快速定量分析土壤中重金属元素[J].分析化学,2021,49(8):1410-1418. LI Maogang,LIANG Jing,YAN Chunhua,et al.Rapid quantitative analysis of heavy metals in soil by laser induced breakdown spectroscopy combined with random forest algorithm[J].Chinese Journal of Analytical Chemistry, 2021,49(8):1410-1418. [21] 周嘉俊,李茂刚,张天龙,等.激光诱导击穿光谱结合随机森林的稀土矿石中钪元素定量分析[J].中国激光,2024,51(2):179-187. ZHOU Jiajun,LI Maogang,ZHANG Tianlong,et al.Quantitative analysis of Sc in rare-earth ores via laser-induced breakdown spectroscopy combined with random forest[J].Chinese Journal of Lasers,2024,51(2):179-187. [22] 舒开强,许应铜,高智星,等.激光诱导击穿光谱对U的定量分析[J].中国无机分析化学,2024,14(2):139-144. SHU Kaiqiang,XU Yingtong,GAO Zhixing,et al.Quantitative analysis of U by laser-induced breakdown spectroscopy[J].Chinese Journal of Inorganic Analytical Chemistry,2024,14(2):139-144. [23] 杨彦伟,张丽丽,郝晓剑,等.机器学习结合激光诱导击穿光谱技术铁矿石分类方法[J].红外与激光工程,2021,50(5):273-280. YANG Yanwei,ZHANG Lili,HAO Xiaojian,et al.Classification of iron ore based on machine learning and laser induced breakdown spectroscopy[J].Infrared and Laser Engineering,2021,50(5):273-280. [24] 刘小亮,王澜,彭玲玲,等.飞秒激光诱导击穿光谱技术对石墨中钍的定量分析[J].中国光学,2023,16(1):103-112. LIU Xiaoliang,WAN Lan,PENG Lingling,et al.Quantitative analysis of thorium in graphite using femtosecond laser-induced breakdown spectroscopy[J].Chinese Optics,2023,16(1):103-112. [25] Breiman L.Random forests[J].Machine Learning,2001,45(1):5-32.
