相关向量机结合主成分分析应用于
LIBS 技术定量分析

doi:10.3969/j.issn.1007-5461.2023.03.009

量子电子学报 ›› 2023, Vol. 40 ›› Issue (3): 376-382.doi: 10.3969/j.issn.1007-5461.2023.03.009

Application of relevance vector machine combined with principal component analysis in quantitative analysis of LIBS

ZHANG Ranran, YING Luna, ZHOU Weidong *

( Key Laboratory of Researching Optical Information Detecting and Display Technology in Zhejiang Province, Zhejiang Normal University, Jinhua 321004, China )

Received:2021-04-29 Revised:2021-05-08 Published:2023-05-28 Online:2023-05-28

摘要/Abstract

摘要： 采用相关向量机 (RVM) 结合主成分分析 (PCA) 建立了激光诱导击穿光谱 (LIBS) 技术检测土壤中Cr元素含量的定量分析模型。配制了14个不同Cr元素浓度的土壤样品，选取其中10个作为训练样品集用于构建模型，另外4个作为测试样品集用于模型性能评估。结果表明，对于土壤中Cr元素含量的测量， PCA-RVM模型的预测精度明显优于RVM模型，整体预测均方根误差由RVM模型的8.00%减小到PCA-RVM模型的3.21%，预测精度提高了 59.9%。对测试样品集中全部4个待测样品， PCA-RVM模型多次重复预测结果的相对标准偏差相较于RVM模型都显著减小，且均小于1.89%，表明其预测结果具有更好的稳定性。

关键词: 光谱学, 激光诱导击穿光谱, 主成分分析, 相关向量机, 土壤

Abstract: A quantitative analysis model for detecting Cr in soil with laser induced breakdown spectroscopy (LIBS) was established by using correlation vector machine (RVM) combined with principal component analysis (PCA). Fourteen soil samples with different Cr concentrations were prepared, of which ten were selected as training samples for model construction, and the other four as test samples for model performance evaluation. The results show that the prediction accuracy of PCA-RVM model is significantly better than that of RVM model for the measurement of Cr content in soil. The root mean square error (RMSE) of the whole prediction is reduced from 8.00% of RVM model to 3.21% of PCARVM model, and the prediction accuracy is improved by 59.9%. Compared with RVM model, the relative standard deviation of repeated prediction results of PCA-RVM model for all four samples in the test sample set is significantly reduced and is less than 1.89%, indicating that the prediction results of PCARVM model have better stability.

Key words: spectroscopy, laser-induced breakdown spectroscopy, principal component analysis, relevance vector machine, soil

中图分类号:

O657.33

张冉冉 , 应璐娜 , 周卫东. 相关向量机结合主成分分析应用于 LIBS 技术定量分析[J]. 量子电子学报, 2023, 40(3): 376-382.

ZHANG Ranran, YING Luna, ZHOU Weidong . Application of relevance vector machine combined with principal component analysis in quantitative analysis of LIBS[J]. Chinese Journal of Quantum Electronics, 2023, 40(3): 376-382.

参考文献

[1]David A.Cremers,Rosemarie CChinni. Laser-Induced Breakdown Spectroscopy-Capabilities and Limitations[J].Applied Spectroscopy Reviews, 2009, 44(6):457-506
[2]Aberkane S M, Abdelhamid M, Mokdad F, et al.Sorting zamak alloys via chemometric analysis of their LIBS spectral[J].Analytical Methods, 2017, 9(24):3696-3703
[3]Ruan F Q, Qi J, Yan C H, et al.Quantitative detection of harmful elements in alloy steel by LIBS technique and sequential backward selection-random forest (SBS-RF)[J]. [J].J. Anal. l Atom. Spectro. , 2017, 32(11):2194-2199
[4]Wang Zhe; Yuan Ting-Bi; Hou, Zong-Yu et.al,Laser-induced breakdown spectroscopy in China[J].FRONTIERS OF PHYSICS, 2014, 9(4):419-438
[5]Kaleem Ahmad, Walid Tawfik, Wazirzada A.Farooq,et alAnalysis of alumina-based titanium carbide composites by laser-induced breakdown spectroscopy[J].Applied Physics A, 2014, 117(3):1315-1322
[6]Yu Youli, Zhou Weidong, Su Xuejiao.Detection of Cu in solution with double pulse laser-induced breakdown spectroscopy [J]. [J].Optics Communications,, 2014, 333(8):62-66
[7]Yuan Tingbi, Wang Zhe, Li Zheng.A partial least squares and wavelet-transform hybrid model to analyze carbon content in coal using laser-induced breakdown spectroscopy[J].[J]. Analytica Chimica ACTA，2014, 807: 29-35, 2014, 807(1):29-35
[8]Han, Dukki, Joe, Young Jin, Ryu, Jong-Sik, et al.Application of laser-induced breakdown spectroscopy to Arctic sediments in the Chukchi Sea[J]. [J].Spectrochimica Acta Part B:Atomic Spectroscopy, 2018, 146: 84-92, 2018, 146(2):84-92
[9]Herrera, K.K.,Tognoni,E,Gornushkin,I.B.,et al. Comparative study of two standard-free approaches in laser-induced breakdown spectroscopy as applied to the quantitative analysis of aluminum alloy standards under vacuum conditions[J].Journal of Analytical Atomic Spectrometry, 2009, 24(4):426-438
[10]Zhang B H, Jiang Y C, Zhang X Y, et al.Quantitative Analysis of Mn in Soil Samples Using LIBS[J].Spectroscopy and Spectral Analysis, 2015, 35(6):1715-1718
[11]Cama-Moncunill X, Markiewicz-Keszycka M, Cama-Moncunill R, et al.Sampling effects on the quantification of sodium content in infant formula using laser-induced breakdown spectroscopy (LIBS)[J].[J].International Dairy Journal, 2018, 85:49-55, 2018, 85(1):49-55
[12]Zhu Z H, Li J M, Guo Y Q, et al.Accuracy improvement of boron by molecular emission with a genetic algorithm and partial least squares regression model in laser-induced breakdown spectroscopy[J].Joural of Analytical Atomic Spectrometry, 2018, 33(2):205-209
[13]Li X W, Wang Z, Lui S L, et al.A partial least squares based spectrum normalization method for uncertainty reduction for laser-induced breakdown spectroscopy measurements. [J].Spectrochimica Acta Part:B Atomic Spectroscopy[J]. 2013, 88:180-185, 2013, 88(2):180-185
[14]Tomoko T, Blair T.Quantitative methods for compensation of matrix effects and self-absorption in Laser Induced Breakdown Spectroscopy signals of solids[J]. [J].Spectrochimica Acta Part:B Atomic Spectroscopy, 2017, 138:31-42, 2017, 138(1):31-42
[15]Zhang T L, Liang L, Wang K, et al.A novel approach for the quantitative analysis of multiple elements in steel based on laser-induced breakdown spectroscopy (LIBS) and random forest regression (RFR)[J].Journal of Analytical Atomic Spectrometry, 2014, 29(12):2323-2329
[16]Wu S, Zhang T L, Tang H S, et al.Quantitative analysis of nonmetal elements in steel using laser-induced breakdown spectroscopy combined with random forest[J].Analytical Methods, 2015, 7(6):2425-2432
[17]Yan C H, Qi J, Ma J X, et al.Determination of carbon and sulfur content in coal by laser induced breakdown spectroscopy combined with kernel-based extreme learning machine [J].[J].Chemometrics and Intelligent Laboratory Systems., 2017, 167:226-231, 2017, 167(3):226-231
[18]Yi C C, Lv Y, Xiao H, et al.Laser induced breakdown spectroscopy for quantitative analysis based on low-rank matrix approximations[J].Journal of Analytical Atomic Spectrometry, 2017, 32(11):2164-2172
[19]Gu Y H, Zhao N J, Ma M J, et al.Monitoring the Heavy Element of Cr in Agricultural Soils Using a Mobile Laser-Induced Breakdown Spectroscopy System with Support Vector Machine[J].Chinese Physics Letters, 2016, 33(8):085201--6
[20]Yang J H, Yi C C, Xu J W, ey al.A laser induced breakdown spectroscopy quantitative analysis method based on the robust least squares support vector machine regression model [J].[J].Journal of Analytical Atomic Spectrometry[J]. 2015, 30(7):1541-1551, 2015, 30(7):1541-1551
[21]Lin J Q, Lin X M, Guo Lianbo, et al.Identification accuracy improvement for steel species using a least squares support vector machine and laser-induced breakdown spectroscopy.[J].Journal of Analytical Atomic[J]. 2018, 33(9):1545-1551, 2018, 33(9):1545-1551
[22]Yang J H, Yi C C, Xu J W, et al.Laser-induced Breakdown spectroscopy quantitative analysis method via adaptive analytical line selection and relevance vector machine regression model[J]. [J].Spectrochimica Acta Part:B Atomic Spectroscopy,, 2015, 107(1):45-55
[23]Tipping M E.Sparse Bayesian learning and the relevance vector machine[J]. [J].J. Mach. Learn. Res.,, 2001, 1(2):211-244
[24]Wipf D P, Rao B D.Sparse Bayesian learning for basis selection[J]. [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,, 2004, 52(11):2153-2164
[25]Ji S, Xue Y, Carin L.Bayesian compressive sensing[J].[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,, 2008, 56(12):2346-2356
[26]Shi Q, Niu G H, Lin Q Y, et al.Quantitative analysis of sedimentary rocks using laser-induced breakdown spectroscopy:comparison of support vector regression and partial least squares regression chemometric methods[J].Journal of Analytical Atomic Spectrometry, 2015, 30(12):2384-2393
[27]Yang H X, Fu H B, Wang H D, et al.Laser-induced breakdown spectroscopy applied to the characterization of rock by support vector machine combined with principal component analysis[J].[J]. Chinese Physics B, 2016, 25(6):065201--6