帮助 关于我们

返回检索结果

基于LIBS技术对岩石识别的数据降噪方法
Data Denoising Method for Rock Identification Based on LIBS Technology

查看参考文献20篇

王翀 1   张笑墨 1   朱香平 2,3 *   罗文峰 1   单娟 3  
文摘 利用激光诱导击穿光谱技术进行原岩分类与识别存在可重复性差,数据残差值高等问题,导致其分类识别准确率较低.针对此问题,提出了一种基于格拉布斯准则法的异常值判别方法,该方法可以有效替换残差值较大的数据,从而降低分类识别算法过拟合的概率.使用线性判别分析法、随机森林分类法、支持向量机三种分类识别算法对岩石的LIBS光谱进行识别.在数据降噪前,三种方法的识别准确率为:线性判别分析法79.6%、随机森林分类法75.2%、支持向量机94.5%,而数据降噪后的识别准确率为:线性判别分析法92%、随机森林分类法97%、支持向量机99.4%.
其他语种文摘 There have been confront with a low identification accuracy problem due to the poor repeatability and high data residual value of laser-induced breakdown spectrum.In order to solve such problems,an distinguishing method of abnormal value based on Grubbs criterion (3δ-Grubbs)was proposed.The method can effectively replace the data of large residual values to reduce the probability of over-fitting in the classification recognition algorithm.Finally,by using three classification recognition algorithms:linear discriminant analysis,random forest classification and support vector machine,we identified the LIBS spectrum of rocks.Before the data noise reduces,the recognition accuracy of the three methods were:linear discriminant analysis 79.6%,random forest classification 75.2%,support vector machine 94.5%.After data noise is reduced,the recognition accuracy of the three methods is as follows: linear discriminant analysis 92%,random forest classification 97%,support vector machine 99.4%.
来源 光子学报 ,2019,48(10):1030001 【核心库】
DOI 10.3788/gzxb20194810.1030001
关键词 激光诱导击穿光谱技术 ; 等离子体 ; 原岩识别 ; 主成分分析法 ; 降噪
地址

1. 西安邮电大学电子工程学院, 西安, 710121  

2. 中国科学院大学, 北京, 100049  

3. 中国科学院西安光学精密机械研究所, 瞬态光学与光子技术国家重点实验室, 西安, 710119

语种 中文
文献类型 研究性论文
ISSN 1004-4213
学科 物理学;地质学
基金 国家重点研发计划
文献收藏号 CSCD:6603905

参考文献 共 20 共1页

1.  罗文峰. 激光诱导击穿光谱技术的初步研究,2011 CSCD被引 3 次    
2.  Fortes F J. Laser-induced breakdown spectroscopy. Analytical Chemistry,2013,85(2):640-669 CSCD被引 41 次    
3.  Lucia F C D. Evaluation of femtosecond laser-induced breakdown spectroscopy for explosive residue detection. Optics Express,2009,17(2):419-425 CSCD被引 8 次    
4.  Tankova V. Investigation of archaeological metal artefacts by laser-induced breakdown spectroscopy(LIBS). Journal of Physics:Conference Series,2018,992:012003 CSCD被引 1 次    
5.  Vahid D M. Identification and sorting of PVC polymer in recycling process by laser-induced breakdown spectroscopy (LIBS)combined with support vector machine(SVM)model. Iranian Journal of Science and Technology Transaction A-Science,2016,42(2):959-965 CSCD被引 3 次    
6.  Lanza N L. Calibrating the ChemCam laser-induced breakdown spectroscopy instrument for carbonate minerals on Mars. Applied Optics,2010,49(13):C211-C217 CSCD被引 21 次    
7.  Ollila A M. Comparison of two partial least squares-discriminant analysis algorithms for identifying geological samples with the ChemCam laser-induced breakdown spectroscopy instrument. Applied Optics,2012,51(7):B130-B142 CSCD被引 3 次    
8.  Sirven J B. Feasibility study of rock identification at the surface of Mars by remote laser-induced breakdown spectroscopy and three chemometric methods. Journal of Analytical Atomic Spectrometry,2007,22(12):1471-1480 CSCD被引 12 次    
9.  Moros J. Dual-spectroscopy platform for the surveillance of mars mineralogy using a decisions fusion architecture on simultaneous LIBS-Raman data. Analytical Chemistry,2018,90(3):2079-2087 CSCD被引 1 次    
10.  Ebo E A. Simulated laser-induced breakdown spectra of graphite and synthetic shergottite glass under Martian conditions. Spectrochimica Acta Part B:Atomic Spectroscopy,2018,148:31-43 CSCD被引 3 次    
11.  Saverio S G. Identification and classification of meteorites by a handheld LIBS instrument coupled with a fuzzy logic-based method. Journal of Analytical Atomic Spectrometry,2016,31:1-13 CSCD被引 1 次    
12.  Harmon R S. Discriminating volcanic centers with handheld laserinduced breakdown spectroscopy(LIBS). Journal of Archaeological Science,2018,98:112-127 CSCD被引 3 次    
13.  Yang Hongxing. Laser-induced breakdown spectroscopy applied to the characterization of rock by support vector machine combined with principal component analysis. Chinese Physics B,2016,25(6):065201 CSCD被引 14 次    
14.  Li W. In situ classification of rocks using stand-off laser-induced breakdown spectroscopy with a compact spectrometer. Journal of Analytical Atomic Spectrometry,2018,33:461-467 CSCD被引 6 次    
15.  Yu Jianlong. Provenance classification of nephrite jades using multivariate LIBS:a comparative study. Analytical Methods,2018,10:281-289 CSCD被引 5 次    
16.  Yelamela M. Support vector machine based classification of seafloor rock types measured underwater using Laser Induced Breakdown Spectroscopy,2016 CSCD被引 1 次    
17.  Huang Suyun. Robust kernel principal component analysis. Neural Computation,2009,21(11):3179-3213 CSCD被引 4 次    
18.  Vitkov A. Comparative study on fast classification of brick samples by combination of principal component analysis and linear discriminant analysis using stand-off and table-top laser-induced breakdown spectroscopy. Spectrochimica Acta Part B:Atomic Spectroscopy,2014,101:191-199 CSCD被引 3 次    
19.  Ho T K. The random subspace method for constructing decision forests. IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(8):832-844 CSCD被引 235 次    
20.  Yang Guang. Rock and Soil Classification Using PLS-DA and SVM Combined with a Laser-Induced Breakdown Spectroscopy Library. Plasma Science & Technology,2015,17(8):656-663 CSCD被引 11 次    
引证文献 1 篇

1 邱苏玲 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 中国激光,2021,48(16):1611002
CSCD被引 12 次

显示所有1篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号