基于PCA-BP神经网络的EDXRF分析测定地质样品中铁、 钛元素含量的应用研究

徐立鹏; 葛良全; 谷懿; 刘敏; 张庆贤; 李飞; 罗斌

doi:doi:10.3964/j.issn.1000-0593(2013)05-1392-05

光谱学与光谱分析, 2013, 33 (5): 1392, 网络出版: 2013-05-21

基于PCA-BP神经网络的EDXRF分析测定地质样品中铁、钛元素含量的应用研究

Research on the Application of Principal Component Analysis and Improved BP Neural Network to the Determination of Fe and Ti Contents in Geological Samples

论文大纲

徐立鹏 ^*葛良全谷懿刘敏张庆贤李飞罗斌

作者单位

成都理工大学, 四川成都610059

能量色散X荧光(EDXRF) 主成分分析(PCA) 主成分-误差反向传播网络(PCA-BP) 地质样品 Energy disperse X-ray fluorescence measurement (ED Principal component analysis Principal component analysis-BP neural network Geological samples

摘要

为实现地质样品中元素含量的准确预测, 提出了基于主成分分析(PCA)的改进型BP神经网络模型。采用X荧光光谱法, 对新疆西天山地质样品中Fe, Ti, V, Pb和Zn等元素进行测量, 将得到的X荧光计数作为输入变量, 应用该模型对未知地质样品中Fe和Ti元素进行定量预测。结果表明: 主成分分析与改进型BP神经网络模型取得了较好的预测效果, 预测结果与化学分析值的相对误差小于3%, 为地质样品元素含量预测提供了一种新型有效的方法。

Abstract

Aiming at forecasting elemental contents in geological samples accurately, a principal component analysis and improved BP (PCA-BP) neural network theory is proposed in the present work. The samples from west Tianshan were measured through X-ray fluorescence measurement method, and the X-Ray fluorescence counts of each element such as Fe, Ti, V, Pb, Zn, etc. were input to the PCA-BP neural network as input variables to forecast Fe and Ti contents in uncertified geological samples quantitatively. The results show that the PCA-BP neural network can give an ideal result, and the relative error between the forecast data and chemical analysis data is less than 3%. This method provides a new and effective approach to forecasting elemental contents in geological samples.

参考文献

[1] CAO Li-guo, DING Yi-min, HUANG Zhi-qi(曹利国, 丁益民, 黄志琦). Method of Energy Dispersive X-Ray Fluorescence(能量色散X射线荧光方法). Chengdu: Chengdu Science University Press(成都: 成都科技大学出版社), 1998. 182.

[2] GE Liang-quan, ZHOU Si-chun, LAI Wan-chang(葛良全, 周四春, 赖万昌). In-Situ Radiation Sampling Technique(原位X辐射取样技术). Chengdu: Sichuan Science and Technology Press(成都: 四川科技出版社), 1997. 71.

[3] HUANG Hua(黄华). Journal of Xinjiang Agricultural University(新疆农业大学学报), 2010, 33(6): 535.

[4] FAN Jin-cheng, MEI Chang-lin(范金城, 梅长林). Data Analysis(数据分析). Beijing: Science Press(北京: 科学出版社), 2002. 87.

[5] WANG Xue-ren, WANG Song-gui(王学仁, 王松桂). Static Analysis of Practical Multivariate(实用多元统计分析). Shanghai: Science and Technology Publishing House of Shanghai(上海: 上海科学技术出版社), 1990. 65.

[6] ZHAO Wang-da, XU Zhi-sheng, WU Min(赵望达, 徐志胜, 吴敏). Chinese Engineering Science(中国工程科学), 2007, 9(1): 82.

[7] XU Yue-qing, LI Shuang-cheng, CAI Yun-long(许月卿, 李双成, 蔡运龙). Progress in Geography(地理科学进展), 2006, 25(3): 79.

[8] LI Fei, GE Liang-quan, ZHANG Qing-xian, et al(李飞, 葛良全, 张庆贤, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2012, 32(5): 1410.

[9] YANG Jing, MAO Zong-yuan(杨静, 毛宗源). Computer Engineering and Applications(计算机工程与应用), 2007, 43(25): 246.

[10] LI Jun-mei, HU Yi-hua, TAO Xiao-hong(李军梅, 胡以华, 陶小红). Infrared and Laser Engineering(红外与激光工程), 2005, 34 (6): 719.

徐立鹏, 葛良全, 谷懿, 刘敏, 张庆贤, 李飞, 罗斌. 基于PCA-BP神经网络的EDXRF分析测定地质样品中铁、钛元素含量的应用研究[J]. 光谱学与光谱分析, 2013, 33(5): 1392. XU Li-peng, GE Liang-quan, GU Yi, LIU Min, ZHANG Qing-xian, LI Fei, LUO Bin. Research on the Application of Principal Component Analysis and Improved BP Neural Network to the Determination of Fe and Ti Contents in Geological Samples[J]. Spectroscopy and Spectral Analysis, 2013, 33(5): 1392.

基于PCA-BP神经网络的EDXRF分析测定地质样品中铁、钛元素含量的应用研究

关于本站 Cookie 的使用提示

全站搜索

基于PCA-BP神经网络的EDXRF分析测定地质样品中铁、 钛元素含量的应用研究

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索

基于PCA-BP神经网络的EDXRF分析测定地质样品中铁、钛元素含量的应用研究