X射线荧光光谱结合BP神经网络识别进口铜精矿产地

doi:10.3964/j.issn.1000-0593(2020)09-2884-07

Abstract
References
Related Citation (15)

Download: PDF (2216 KB)
Export: BibTeX | EndNote (RIS)

Abstract Copper concentrate is the basic industrial raw material for smelting copper and its alloys. Imported Copper concentrate with different origins varies in elemental composition and content. Cases of imported copper concentrate falsifying, adulterating and exceeding the standard of harmful elements frequently occur, which endangers national economic security. So it is necessary to establish a rapid identification model of the origin of imported copper concentrates in major importing countries, which is conducive to risk classification and early warning. The research objects of this paper are 280 imported copper concentrate samples from 8 countries in Chile, Peru, Philippines, Spain, Namibia, Iran, Malaysia and Albania. The elemental composition and content of all research samples were determined by wavelength dispersive X-ray fluorescence spectrum standard-less analysis method, and it turned out that elements detected from copper concentrate samples are 53 in total. Among them, we chose 17 elements and conducted a BP neural network prediction model, including O, Mg, Al, Si, P, S, K, Ca, Ti, Fe, Cu, Zn, Mn, As, Mo, Ag, Pb. Moreover, 13 elements including O, Mg, Al, Si, P, S, K, Ca, Cu, Zn, Mo, Ag, Pb were screened out as valid variables by F-score, and the Fisher discriminant analysis prediction model and BP neural network prediction model were established for importing copper concentrate countries respectively. The results of the three prediction models are as follows: the Fisher discriminant analysis model, which uses F-score to screen variables, the recognition accuracy of the model for the modeled sample was 94.2%, the one of cross-validation was 92.8%, and that of the predicted sample reached 96.8%. The accuracy rate of training set, calibration set, validation set, modeling set and prediction sample of BP neural network with input layer of 17 and 13 variables is: 100%, 97.1%, 94.1%, 98.2%, 100% and 100%, 97.1%, 100%, 99.6% and 100%, respectively. Comparing the results of three times of modeling can be seen that the model established by BP neural network has the highest accurate recognition degree after the variables are screened by f-score. This method can not only reduce the input variables of modeling, but also improve the recognition accuracy. Although the wavelength dispersion X-ray fluorescence spectrum standard-less analysis method is a semi-quantitative analysis method, it has the advantages of fast analysis speed and good stability. The country identification of copper concentrate can be realized by using this method combined with F-score screening variables for BP neural network pattern recognition.

Key words：Copper concentrate; X-ray fluorescence spectrum; BP neural network; Discriminant analysis; Origin identification

Received: 2019-07-28 Accepted: 2019-11-16

ZTFLH:

O657.3

Corresponding Authors: LIU Shu, XING Yan-jun E-mail: liu_shu@customs.gov.cn；yjxing@dhu.edu.cn

Cite this article:

URL:

http://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2020)09-2884-07 OR http://www.gpxygpfx.com/EN/Y2020/V40/I09/2884

[1] MEI Yan-xiong，PEI Rong-fu，YANG De-feng，et al（梅燕雄，裴荣富，杨德凤，等）. Mineral Deposits （矿床地质），2009，28(4)：383.
[2] Giulio Binetti，Laura Del Coco，Rosa Ragone，et al. Food Chemistry，2017，219：131.
[3] Moncayo S，Rosales J D，Izquierdo-Hornillos R，et al. Talanta，2016，158：185.
[4] MENG Hai-dong，YIN Yue，SUN Jia-ju，et al（孟海东，殷跃，孙家驹，等）. West-China Exploration Engineering（西部探矿工程），2012，24(8)：137.
[5] GAO Bin，ZHAO Peng-fei，LU Yu-xi，et al（高斌，赵鹏飞，卢昱欣）. Spectroscopy and Spectral Analysis（光谱学与光谱分析），2018, 38（10）：3136.
[6] YIN Jiang-ning，XIAO Ke-yan，LI Nan，et al（阴江宁，肖克燕，李楠，等）. Geological Bulletin of China（地质通报），2010，29（10）：1564.
[7] Navid Khajehzadeh, Olli Haavisto，Lauri Koresaar. Minerals Engineering，2017，113：83.
[8] ZHOU Ping，TANG Jin-rong，YANG Zong-xi，et al（周平，唐金荣，杨宗喜，等）. Strategic Analysis of Copper Resources（铜矿资源战略分析）. Beijing：Geological Publishing House（北京：地质出版社），2012. 12.
[9] WANG Xin-jie，LI Hai-feng，MA Lin，et al（王欣杰，李海峰，马琳，等）. Journal of Yanshan University（燕山大学学报），2014, 38（5）：432.
[10] Sabzi S，Javadikia P，Rabani H，et al. Measurement，2013，46(9)：3333.
[11] DU Qiang，JIA Li-yan（杜强，贾丽艳）. SPSS Statistical Analysis（SPSS统计分析）. Beijing：Posts and Telecom Press（北京：人民邮电出版社），2009. 307.
[12] Verpoort P C，MacDonald P，Conduit G J. Materials Science，2018，147：176.
[13] Roberto Battiti，Mauro Brunato. Machine Learning Plus Intelligent Optimization（机器学习与优化）. Translated by WANG Yu-ge（王彧戈，译）. Beijing：Posts and Telecom Press（北京：人民邮电出版社），2018. 76.