基于列文伯格-马夸尔特-食品安全质量检测学报.PDF

7 3 Vol. 7 No. 3 2016 3 Journal of Food Safety and Quality Mar. , 2016 -- X 李 芳 1, 3, 陆安祥 1, 2, 3*, 王纪华 1, 2, 3 (1. , 100097; 2. (), 100097; 3. , 100097) 摘 要: 目的 --(Levenberg-Marquardt back-propagation artificial neural networks, LM-BP-ANN)X (XRF)方法 84 , (PCA), 422121(MSE)(R2 2 )(SEC)(r )(SEP) (RPD), LM-BP-ANNBP-ANNPLS , 结果 : 60.1 8, 3 LM-BP-ANN , 0.98, 结论 , , X 关键词: -; ; X Quantitative analysis method based on Levenberg-Marquardt back-propagation artificial neural network for X-ray fluorescence spectrometry LI Fang1, 3, LU An-Xiang1, 2, 3*, WANG Ji-Hua1, 2, 3 (1. Beijing Research Center for Agricultural Standards and Testing, Beijing 100097, China ; 2. Risk Assessment Lab for Agro-products (Beijing), Ministry of Agriculture, Beijing 100097, China; 3. Beijing Municipal Key Laboratory of Agriculture Environment Monitoring , Beijing 100097, China) ABSTRACT: Objective To establish a quantitative detection analysis method based on Levenberg-Marquardt back-propagation artificial neural network (LM-BP-ANN) for X-ray fluorescence spectrometry (XRF). Methods The spectrometry data of all 84 soil samples were colle