期刊文献+

基于LIBS技术和主成分分析的快速分类方法研究 被引量:8

Research on Fast Classification Based on LIBS Technology and Principle Component Analyses
下载PDF
导出
摘要 将激光诱导击穿光谱(LIBS)技术与主成分分析(PCA)法相结合用于铝合金分类研究,对Al—Cu系、Al—Si系、Al—Mg—Si系、Al—Zn系四类13种铝合金标准样品进行了分类实验,实验结果证明LIBSPCA方法可以实现铝合金的快速分类。通过使用LIBS技术激发130个铝合金标准样品得到130个光谱样本,再用主成分分析方法进行降维分析,计算出贡献率最大的三个主成分并计算各光谱的主成分得分绘制在三维空间中,发现光谱样本点按照铝合金的种类发生了明显的汇聚现象,由此确定了三个主成分和铝合金类型区域。用20个不同类型的铝合金进行实验对所得铝合金类型区域的准确性进行验证,发现所得20个光谱样本点全部落在其对应的标准样品类型区域内,在一定程度上证明所得的铝合金标准样品类型区域的正确性,在此基础上可以进行未知类型铝合金的鉴别。实验结果表明基于LIBS光谱的PCA方法分类精度达到97.14%以上,能够有效的完成不同模式的区分,相比于常用的化学方法,LIBS技术可以原位快速地对待测样品进行检测,样品预处理简单,因此将激光诱导击穿光谱(LIBS)技术与主成分分析(PCA)法相结合用于质量检测和在线工业控制等领域,可以节约大量的时间及成本,提高检测效率。 Laser-induced breakdown spectroscopy (LIBS) and the principle component analysis(PCA) were combined to study a-luminum alloy classification in the present article .Classification experiments were done on thirteen different kinds of standard samples of aluminum alloy which belong to 4 different types ,and the results suggested that the LIBS-PCA method can be used to aluminum alloy fast classification .PCA was used to analyze the spectrum data from LIBS experiments ,three principle compo-nents were figured out that contribute the most ,the principle component scores of the spectrums were calculated ,and the scores of the spectrums data in three-dimensional coordinates were plotted .It was found that the spectrum sample points show clear convergence phenomenon according to the type of aluminum alloy they belong to .This result ensured the three principle compo-nents and the preliminary aluminum alloy type zoning .In order to verify its accuracy ,20 different aluminum alloy samples were used to do the same experiments to verify the aluminum alloy type zoning .The experimental result showed that the spectrum sample points all located in their corresponding area of the aluminum alloy type ,and this proved the correctness of the earlier a-luminum alloy standard sample type zoning method .Based on this ,the identification of unknown type of aluminum alloy can be done .All the experimental results showed that the accuracy of principle component analyses method based on laser-induced breakdown spectroscopy is more than 97.14% ,and it can classify the different type effectively .Compared to commonly used chemical methods ,laser-induced breakdown spectroscopy can do the detection of the sample in situ and fast with little sample preparation ,therefore ,using the method of the combination of LIBS and PCA in the areas such as quality testing and on-line in-dustrial controlling can save a lot of time and cost ,and improve the efficiency of detection greatly .
出处 《光谱学与光谱分析》 SCIE EI CAS CSCD 北大核心 2014年第11期3095-3099,共5页 Spectroscopy and Spectral Analysis
基金 国家(863计划)项目(2013AA102402)资助
关键词 激光诱导击穿光谱 主成分分析 分类 Laser induced breakdown spectroscopy Principle component analyses Classification
  • 相关文献

参考文献3

二级参考文献49

  • 1刘成武,李秀彬.基于生产成本的中国农地利用集约度的变化特征[J].自然资源学报,2006,21(1):9-15. 被引量:94
  • 2黎一畅,周寅康,吴林,金晓斌,王丽萍,胡静.城市土地集约利用的空间差异研究——以江苏省为例[J].南京大学学报(自然科学版),2006,42(3):309-315. 被引量:118
  • 3曹银贵,王静,程烨,付梅臣,饶彩霞,许宁.三峡库区耕地变化研究[J].地理科学进展,2006,25(6):117-125. 被引量:37
  • 4叶健,葛临东,吴月娴.一种优化的RBF神经网络在调制识别中的应用[J].自动化学报,2007,33(6):652-654. 被引量:32
  • 5Chen S, Wang X X, Brown D J. Sparse incremental regression modeling using correlation criterion with boosting search. IEEE Signal Processing Letters, 2005, 12(3): 198-201.
  • 6Chen S, Wolfgang A, Harris C J, Hanzo L. Symmetric RBF classifier for nonlinear detection in multiple-antenna-aided systems. IEEE Transactions on Neural Networks, 2008, 19(5): 737-745.
  • 7Conzalez J, Rojas I, Ortega J, Pomares H, Fernandez F J, Diaz A F. Multi-objective evolutionary optimization of the size, shape, and position parameters of radial basis function networks for function approximation. IEEE Transactions on Neural Networks, 2003, 14(6): 1478-1495.
  • 8Leung F H F, Lam H K, Ling S H, Tam P K S. Tuning of the structure and parameters of a neural network using an improved genetic algorithm. IEEE Transactions on Neural Networks, 2003, 14(1): 79-88.
  • 9Bors A G, Pitas I. Median radial basis function neural network. IEEE Transactions on Neural Networks, 1996, 7(6): 1351-1364.
  • 10Yin H, Allinson N M. Self-organizing mixture networks for probability density estimation. IEEE Transactions on Neural Networks, 2001, 12(2): 405-411.

共引文献234

同被引文献87

引证文献8

二级引证文献33

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部