Neural network-based matrix effect correction in EDXRF analysis

Neural network-based matrix effect correction in EDXRF analysis 1 corresp first-author Corresponding author. E-mail address: txg@cdut.edu.cn Corresponding author. E-mail address: txg@cdut.edu.cn txg@cdut.edu.cn 1 1 1 Chengdu University of Technology, Chengdu 610059, China Chengdu University of Technology, Chengdu 610059, China In this paper we discuss neural network-based matrix effect correction in energy dispersive X-ray fluorescence (EDXRF) analysis, with detailed algorithm to classify the samples. The method can correct the matrix effect effectively through classifying the samples automatically, and influence of X-ray absorption and enhancement by major elements of the samples is reduced. Experiments for the complex matrix effect correction in EDXRF analysis of samples in Pangang showed improved accuracy of the elemental analysis result. Self-organizing mapping neural network Cluster analysis Matrix effect Sinter mineral References Cheng B , Tuo X , Zhou J . J Chengdu Univ Technol , 2002 , 29 : 65 - 68 . J Chengdu Univ Technol Kohonen T . Biolog Cybern , 1982 , 43 : 665 - 672 . Biolog Cybern Setiono R , Connect Sci , 1995 , 7 : 145 - 164 . Connect Sci Girosi F , Poggio T . Biolog Cybern , 1990 , 6 : 169 - 176 . Biolog Cybern Jiang D , Tang C , Zhang A . IEEE Trans Knowl Data Eng , 2004 , 16 : 1370 - 1386 . IEEE Trans Knowl Data Eng 10.1016/S1001-8042(09)60004-X TL271 + .7 Partially supported by the National Natural Science Foundation of China (No. 40574059) and the Ministry of Education (No. NCET-04-0904) 2008-01-07 2008-10-20 2021-01-19 2008 Nuclear Science and Techniques 05 19