img

QQ群聊

img

官方微信

高级检索

黄金科学技术 ›› 2017, Vol. 25 ›› Issue (2): 38-44.doi: 10.11872/j.issn.1005-2518.2017.02.038

• 采选技术与矿山管理 • 上一篇    下一篇

基于分形理论和BP神经网络的充填料性能研究

刘志祥,龚永超,李夕兵   

  1. 中南大学资源与安全工程学院,湖南  长沙   410083
  • 收稿日期:2016-03-02 修回日期:2016-05-19 出版日期:2017-04-28 发布日期:2017-05-12
  • 作者简介:刘志祥(1967-),男,湖南宁乡人,博士,教授,从事采矿与岩石力学研究工作。liulzx@sina.com
  • 基金资助:

    国家自然科学基金项目“金属矿海底基岩开采裂隙分形演化与突水混沌孕育机制”(编号:51674288)资助

Study on the Backfilling Material Properties Based on Fractal Theory and BP Neural Network

LIU Zhixiang,GONG Yongchao,LI Xibing   

  1. School of Resources and Safety Engineering,Central South University,Changsha    410083,Hunan,China
  • Received:2016-03-02 Revised:2016-05-19 Online:2017-04-28 Published:2017-05-12

摘要:

为研究全尾砂粒径级配特征对充填料性能的影响,提出以分维数和分维数相关系数表征全尾砂的几何特征,并选取灰砂配比、料浆浓度、分维数和分维数相关系数作为BP神经网络输入因子,抗压强度、坍落度和泌水率作为输出因子,建立了充填性能预测的分形—BP神经网络模型。对7个矿山实测数据展开分维数和分维数相关系数计算,并采用BP神经网络进行训练和预测。结果表明:(1)尾砂越细,则粒径级配分维数越大,孔隙分维数就越小,且全尾砂的分维数稍大于分级尾砂的分维数;(2)全尾砂的相关系数在0.71~0.97之间,较分级尾砂离散;(3)分形—BP神经网络模型对充填料性能指标预测的相对误差在8%以内。综上可知:分形理论—BP神经网络相结合的充填性能预测模型具有较好的精度,为充填料性能预测提供了一种新途径。

关键词: 粒径级配, 分维数, 神经网络, 充填料性能

Abstract:

In order to investigate the impact of whole tailing characteristics of size grading on the performance of backfilling material,this study selected fractional dimension number and correlation coefficient of fractional dimension number to characterize the geometric features of whole tailing.By using cement-sand ratio,slurry concentration,fractional dimension number and correlation coefficient of fractional dimension number as the input factors,compressive strength,slump and bleeding rate as the output factors,a fractal-BP neural network model was constructed to predict the properties of backfilling material.Then data of 7 mines were calculated by the fractal dimension and correlation coefficient of fractal dimension,and the BP neural network was used for the training and prediction.The results showed that the finer the tailing,the bigger the size grading fractional dimension,but contrary to the pore fractal dimension.Furthermore,the fractional dimension of whole tailing is a little higher than grading tailing.The correlation coefficient of the grading tailing is between 0.71 to 0.97,which is more dispersed than that of whole tailing.The relative error is under 8% using fractal-BP neural network model to predict the properties of backfilling material.In a conclusion,the fractal-BP neural network model had a fine precision,which provides a new approach to predict the properties of filling material.

Key words: size grading, fractional dimension number, neural network, properties of backfilling material

中图分类号: 

  • TD853.34 

[1] Gu Desheng,Li  Xibing.Modern Mining Science and Techno- logy for Metal Mineral Resources[M].Beijing:China Metallur- gical Industry Press,2006.[古德生,李夕兵.现代金属矿床开采科学技术[M].北京:冶金工业出版社,2006.]
[2] Zhou Aimin,Gu Desheng.Ming-filling model based on indus- trial ecology[J].Journal of Central South University (Science and Technology),2004,35(3):468-472.[周爱民,古德生.基于工业生态学的矿山充填模式[J].中南大学学报(自然科学版),2004,35(3):468-472.]
[3]  Liu Tongyou.Technology of Backfill Mining and It’s Application[M].Beijing:Metallurgical Industry Press,2001.[刘同有.充填采矿技术与应用[M].北京:冶金工业出版社,2001.]
[4] Liu Tongyou.Present status and development future of backfill technology in Chinese non-ferrous metal mineral mines[J].China Mining Magazine,2002,11(1):28-34.[刘同有.中国有色矿山充填技术的现状及发展[J].中国矿业,2002,11(1):28-34.]
[5] Cai Sijing,Huang Gang,Wu Di,et al.Experimental and mo- deling study on the rheological properties of tailings backfill [J].Journal of Northeastern University(Natural Science),2015,36(6):882-886.[蔡嗣经,黄刚,吴迪,等.尾砂充填料浆流变性能模型与试验研究[J].东北大学学报(自然科学版),2015,36(6):882-886.]
[6] Hou Guoquan,Guo Lijie,Yang Chao,et al.Testing and study on the rheological properties the high-density filling slurry of the full tailings[J].China Mining Magazine,2014,23(2):238-241.[侯国权,郭利杰,杨超,等.高浓度全尾砂充填料浆流变特性试验研究[J].中国矿业,2014,23(2):238-241.]
[7] Ren Haifeng,Bai Xianwu,Cheng Guanghua,et al.Test on transporation performance and rheological property of classified tailings slurry[J].Nonferrous Metals(Mining Section),2015,67(4):49-53.[任海锋,白贤武,程光华,等.分级尾砂料浆输送性能及流变特性试验研究[J].有色金属(矿山部分),2015,67(4):49-53.]
[8] Zhou Keping.A gray correlativity analysis of influence of particle size distribution of filling body strength[J].Mining Research and Development,1995,15(4):32-35.[周科平.充填体粒径分布对其强度影响的灰色关联分析[J].矿业研究与开发,1995,15(4):32-35.]
[9] Liu Zhixiang,Li Xibing.Chaotic optimization of tailings grad- ation[J].Journal of Central South University (Science and Te- chnology),2005,36(4):683-688.[刘志祥,李夕兵.尾砂级配的混沌优化[J].中南大学学报(自然科学版),2005,36(4):683-688.]
[10] Zhang Qinli,Li Xieping,Yang Wei.Optimization of filling slurry ratio in a mine based on back-propagation neural network [J].Journal of Central South University(Science and Technology),2013,44(7):2867-2874.[张钦礼,李谢平,杨伟.基于 BP 网络的某矿山充填料浆配比优化[J].中南大学学报(自然科学版),2013,44(7):2867-2874.]
[11] Han Bin,Wu Aixiang,Wang Yiming,et al.Optimization and application of cemented hydraulic fill (CHF)with low strength aggregate and extra fine grain full tailings[J].Journal of Central South University(Science and Technology),2012,43(6):2357-2362.[韩斌,吴爱祥,王贻明,等.低强度粗骨料超细全尾砂自流胶结充填配合比优化及应用[J].中南大学学报(自然科学版),2012,43(6):2357-2362.]
[12] Liu Zhixiang,Zhou Shilin.Knowledge bank model of design of backfill strength[J].Journal of Hunan University of Science & Technology(Natural Science Edition),2012,27(2):7-11.[刘志祥,周士霖.充填体强度设计知识库模型[J].湖南科技大学学报(自然科学版),2012,27(2):7-11.]
[13] Zhu Hua,Ji Cuicui.Fractal Theory and Its Application[M].Beijing:Science Press,2011.[朱华,姬翠翠.分形理论及其应用[M].北京:科学出版社,2011.]
[14] Tang Shaohui,Sang Yufa.The fractal characteristic of phy- sical and mechanical properties of cemented filling body[J].Nonferrous Metals(Mining Section),1996(5):14-17.[唐绍辉,桑玉发.胶结充填体物理力学性质的分形特性[J].有色金属(矿山部分),1996 (5):14-17.]
[15] Xu Yongfu,Sun Wanying.On fractal structure of expansive soils in China[J].Journal of Hohai University (Natural Sci-ences),1997,25(1):18-23. [徐永福,孙婉莹.我国膨胀土的分形结构的研究[J].河海大学学报(自然科学版),1997,25(1):18-23.]
[16] Gui Weihua,Hu Zhikun,Peng Xiaoqi.A coupled exercise algorithm of forward  neural  network  combined with gradient search and chaotic optimization search[J].Journal of Central South University of Technology(Natural Sci-ence),2002,33(6):629-631.[桂卫华,胡志坤,彭小奇.前馈网络的混沌梯度搜索耦合学习算法及应用[J].中南工业大学学报(自然科学版),2002,33(6):629-631.]
[17] Wu Jiang,Huang Furong,Huang Caihuan,et al.Study on near infrared spectroscopy of transgenic soybean iden-tification based on principal component analysis and neural network[J].Spectroscopy and Spectral Analysis,2013,33(6):1537-1541. [吴江,黄富荣,黄才欢,等.近红外光谱结合主成分分析和BP神经网络的转基因大豆无损鉴别研究[J].光谱学与光谱分析,2013,33(6):1537-1541.]
[18] Kobayashi M,Hattori M,Yamazaki H.Multidirectional as- sociative memory with a hidden layer[J].Systems and Com- puters in Japan,2002,33(6):1-9.
[19] Zhang L P,Yu H J,Hus X.Optimal choice of parameters for particle swarm optimization[J].Journal of Zhejiang Univer- sity:Science A,2005,6(6):528-534.
[20] Liu Zhixiang,Li Xibing.Study on fractal gradation of tailings and knowledge bank of its cementing strength[J].Chinese Journal of Rock Mechanics and Engineering,2005,24(10):1789-1793.[刘志祥,李夕兵.尾砂分形级配与胶结强度的知识库研究[J].岩石力学与工程学报,2005,24(10):1789-1793.]

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!