X-ray fluorescence spectra quantitative analysis based on characteristic spectra optimization of partial least-squares method
The quantitative analysis of X-ray fluorescence (XRF) spectra is studied using the partial least-squares (PLS) method. The characteristic variables of spectra matrix of PLS are optimized by genetic algorithm. The subset of multi-component characteristic spectra matrix is established which is corresponding to their concentration. The individual fitness is calculated which combines the crossover validation parameters (prediction error square summation) and correlation coefficients (R2). The experimental result indicates that the predicated values improve using the PLS model of characteristic spectra optimization. Compared to the nonoptimized XRF spectra, the linear dependence of processed spectra averagely decreases by about 7%, root mean square error of calibration averagely increases by about 79.32, and root mean square error of cross-validation averagely increases by about 14.2.
Lianfei Duan：New Star Research Institute of Applied Technology, Hefei 230031, China
Luozheng Zhang：New Star Research Institute of Applied Technology, Hefei 230031, China
Yujun Zhang：Key Laboratory of Environment Optics and Technology, Anhui Institute of Optics and Fine Mechanics, the Chinese Academy of Sciences, Hefei 230031, China
Liuyi Ling：Key Laboratory of Environment Optics and Technology, Anhui Institute of Optics and Fine Mechanics, the Chinese Academy of Sciences, Hefei 230031, China
Yunjun Yang：New Star Research Institute of Applied Technology, Hefei 230031, China
备注：This work was supported by the Project of the Academic Fund (No. 2013XYJJ-008), the Science and Technology Program of Anhui province (No. 1206c0805012), and the National "863" Program (No. 2013AA065502).
【1】A. Ji, G. Y. Tao, S. J. Zhuo, and L. Q. Luo, X-ray Fluorescence Spectra Analysis (Science Press, 2003).
【2】R. Jenkins, X-Ray Fluorescence Spectrometry (Wiley, 1999).
【3】N. Tsoulfanidis, Measurement and Detection of Radiation (Taylor & Francis, 1995).
【4】Y. Liang, Spectral Analysis Foundation of XRF (Science Press, 2007).
【5】H. Wold, Path Models with Latent Variables: The NIPALS Approach, Quantitative Sociology: International Perspectives on Mathematical and Statistical Model Building (Academic Press, 1975).
【6】S. Wold, A. Ruhe, H. Wold, and W. J. Dunn, SIAM J. Sci. Stat. Comput. 5, 735 (1984).
【7】D. M. Haaland and E. V. Thomas, Am. Chem. Soc. 60, 1192 (1988).
【8】D. E. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning (Addison-Wesley, 1989).
【9】A. Popov, Genetic Algorithms for Optimization, User Manual (Hamburg, 2005).
【10】K. Hasegawa, Y. Miyashita, and K. Funatsu, J. Chem. Inf. Comput. Sci. 37, 306 (1997).
【11】V. E. Vinzi, W. W. Chin, J. Henseler, and H. Wang, Handbook of Partial Least Squares (Springer-Verlag, 2010).
Wei Zhang, Lianfei Duan, Luozheng Zhang, Yujun Zhang, Liuyi Ling, Yunjun Yang, "X-ray fluorescence spectra quantitative analysis based on characteristic spectra optimization of partial least-squares method," Chinese Optics Letters 12(s2), S23001 (2014)