光子学报 ›› 2019, Vol. 48 ›› Issue (10): 1030001-1030001.doi: 10.3788/gzxb20194810.1030001

• 光谱学 • 上一篇    下一篇

基于LIBS技术对岩石识别的数据降噪方法

王翀1, 张笑墨1, 朱香平2,3, 罗文峰1, 单娟3   

  1. 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
  • 收稿日期:2019-04-30 出版日期:2019-10-25 发布日期:2019-06-14
  • 通讯作者: 朱香平(1974-),男,副研究员,博士,主要研究方向为激光诱导拉曼、荧光和LIBS等.Email:xpzhu@opt.ac.cn E-mail:xpzhu@opt.ac.cn
  • 作者简介:王翀(1972-),男,副教授,硕士,主要研究方向为光信息及光纤传输、通信技术、光电子学.Email:cw72@xupt.edu.cn
  • 基金资助:

    国家重点研发计划(No.2016YFB0303804)

Data Denoising Method for Rock Identification Based on LIBS Technology

WANG Chong1, ZHANG Xiao-mo1, ZHU Xiang-ping2,3, LUO Wen-feng1, SHAN Juan3   

  1. 1. School of Electronic Engineering Institute, Xi'an University of Posts and Telecommunications, Xi'an, 710121, China;
    2. University of Chinese Academy of Sciences, Beijing 100049, China;
    3. State Key Laboratory of Transient Optics and Photonics, Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an 710119, China
  • Received:2019-04-30 Online:2019-10-25 Published:2019-06-14
  • Contact: 2019-06-14 E-mail:xpzhu@opt.ac.cn
  • Supported by:

    The National Key Research and Development Program of China (No. 2016YFB0303804)

摘要:

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%.

关键词: 原岩识别, 主成分分析法, 激光诱导击穿光谱技术, 降噪, 等离子体

Abstract:

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%.

Key words: Rock, Plasma, Noise reduction, Principal component analysis, Laser induced breakdown spectroscopy

中图分类号: