基于粒子群优化算法和ANFIS的矿体品位插值
|
摘要
地质模型在矿产勘探与开发中具有重要作用,但在矿山生产实践中,由于成本和技术等诸多因素影响,很难获得整个区块的地质数据,而且传统插值方法依靠经验确定参数有很大局限性。提出将粒子群优化算法(PSO)和自适应神经模糊推理系统(ANFIS)应用到矿体品位插值中,利用粒子群优化算法的快速搜索能力,神经网络的学习机制和模糊系统的语言推理能力等优势构建PSO-ANFIS品位插值模型,并借助MATLAB生成571组样本数据作为输入空间对模型进行训练,其中每一个训练样本由待估点三维坐标及真实值和其周围8个样品点组成,最后用训练后的PSO-ANFIS模型对待估点进行品位插值,并与距离幂次反比插值法进行对比,其均方根误差(RMSE)提高了近15%,验证了该模型的可行性和有效性。
Geological model plays an important role in mineral exploration and development, but in the practice of mine production, because of the influence of cost and technology, it is difficult to obtain the geological data of the whole block,and the spatial interpolation is an important means to solve this problem. The particle swarm optimization(PSO) and adaptive neuro-fuzzy inference system(ANFIS) were applied to the grade interpolation of orebody, which overcomes the limitation of traditional interpolation method based on empirical determination of parameters, PSO-ANFIS grade interpolation model was constructed by using the fast searching ability of particle swarm optimization, the learning mechanism of neural network and the language reasoning ability of fuzzy system. Selecting 571 groups of sample points as training data to train the model with the cross verification method in MATALB, each of these training samples consists of three-dimensional coordinates and true values of the estimated points and eight surrounding sample points, finally, the PSO-ANFIS model was used to evaluate the evaluation point and the mean square root error(RMSE) was improved by comparing with the distance power-time inverse interpolation method, which is nearly 15%. The feasibility and effectiveness of the model were validated.
Geological model plays an important role in mineral exploration and development, but in the practice of mine production, because of the influence of cost and technology, it is difficult to obtain the geological data of the whole block,and the spatial interpolation is an important means to solve this problem. The particle swarm optimization(PSO) and adaptive neuro-fuzzy inference system(ANFIS) were applied to the grade interpolation of orebody, which overcomes the limitation of traditional interpolation method based on empirical determination of parameters, PSO-ANFIS grade interpolation model was constructed by using the fast searching ability of particle swarm optimization, the learning mechanism of neural network and the language reasoning ability of fuzzy system. Selecting 571 groups of sample points as training data to train the model with the cross verification method in MATALB, each of these training samples consists of three-dimensional coordinates and true values of the estimated points and eight surrounding sample points, finally, the PSO-ANFIS model was used to evaluate the evaluation point and the mean square root error(RMSE) was improved by comparing with the distance power-time inverse interpolation method, which is nearly 15%. The feasibility and effectiveness of the model were validated.
引文
[1]崔清松.空间插值算法在地质建模中的应用[D].成都:西南石油大学,2010.CUI Qing-song.Application of spatial interpolation algorithm in geological modeling[D].Chengdu:Southwest Petroleum University,2010.
[2]刘青,袁玮,王宝,彭良振.基于GA-BP神经网络的金精矿品位的预测[J].东北大学学报(自然科学版),2015,36(2):237-240.LIU Qing,YUAN Wei,WANG Bao,PENG Liang-zhen.Concentrate grade prediction of gold ore based on GA-BP neural network[J].Journal of Northeastern University(Natural Science),2015,36(2):237-240.
[3]韩万林,张幼蒂,张作祥.智能化方法在矿石品位估值中的应用[J].有色金属(矿山部分),2000,52(5):6-8.HAN Wan-lin,ZHANG You-di,ZHANG Zuo-xiang.Application of intelligent method in ore grade valuation[J].Nonferrous Metals(Mining Section),2000,52(5):6-8.
[4]韩万林,张幼蒂.用改进BP算法估算矿石品位[J].中国矿业,2000,9(3):83-85.HAN Wan-lin,ZHANG You-di.Estimation of ore grade by improved BP algorithm[J].China Mining Magazine,2000,9(3):83-85.
[5]谭正华,荆永滨,王李管,文中华,黄俊歆,陈建宏.基于空间变异性的IDW矿石品位估值改进方法[J].中国矿业大学学报,2011,40(6):928-932.TAN Zheng-hua,JING Yong-bin,WANG Li-guan,WENZhong-hua,HUANG Jun-xin,CHEN Jian-hong.Improved IDWmethod for ore grade estimation based on spatial variation[J].Journal of China University of Mining&Technology,2011,40(6):928-932.
[6]李娟,李翠平,李仲学.基于支持向量回归机的矿体品位插值[J].北京科技大学学报,2009,31(12):1498-1502.LI Juan,LI Cui-ping,LI Zhong-xue.Grade interpolation in orebody based on support vector regression[J].Journal of University of Science and Technology Beijing,2009,31(12):1498-1502.
[7]贾明涛,叶加冕,寇向宇,王李管.品位估值的自适应径向基神经网络构建技术[J].煤炭学报,2010,35(9):1524-1530.JIA Ming-tao,YE Jia-mian,KOU Xiang-yu,WANG Li-guan.The adaptive Radius Basis Function neural network modeling for the deposit grade estimation[J].Journal of China Coal Society,2010,35(9):1524-1530.
[8]李翠平,郑瑶瑕,张佳,侯定勇.基于遗传算法优化的支持向量机品位插值模型[J].北京科技大学学报,2013,35(7):837-843.LI Cui-ping,ZHENG Yao-xia,ZHANG Jia,HOU Ding-yong.Ore grade interpolation model based on support vector machines optimized by genetic algorithms[J].Journal of University of Science and Technology Beijing,2013,35(7):837-843.
[9]李翠平,李仲学,余东明.基于泰森多边形法的空间品位插值[J].辽宁工程技术大学学报,2007,26(4):488-491.LI Cui-ping,LI Zhong-xue,YU Dong-ming.Ore grade interpolation based on Thiessen polygon method[J].Journal of Liaoning Technical University,2007,26(4):488-491.
[10]SHI Xiu-zhi,ZHOU Jian,WU Bang-biao,HUANG Dan,WEIWei.Support vector machines approach to mean particle size of rock fragmentation due to bench blasting prediction[J].Transactions of Nonferrous Metals Society of China,2012,22(2):432-441.
[11]ZHOU Jian,LI Xi-bing,SHI Xiu-zhi,WEI Wei,WU Bang-biao.Predicting pillar stability for underground mine using Fisher discriminant analysis and SVM methods[J].Transactions of Nonferrous Metals Society of China,2011,21(12):2734-2743.
[12]张玉祥.小波神经网络遗传算法及其在矿山压力预报中的应用[J].中国有色金属学报,1999,9(2):240-244.ZHANG Yu-xiang.Gentic algorithm of wavelet network and its application in forecasting ground pressure[J].The Chinese Journal of Nonferrous Metals,1999,9(2):240-244.
[13]周仲礼,马腾,陈秀荣,秦飞龙.基于改进RBF的空间插值算法及其在矿体三维可视化中的应用[J].成都理工大学学报(自然科学版),2014,41(5):645-650.ZHOU Zhong-li,MA Teng,CHEN Xiu-rong,QIN Fei-long.Spatial interpoltaion algorithm based on improved RBF and its application to orebody 3D visualization[J].Journal of Chengdu University of Technology(Science&Technology Edition),2014,41(5):645-650.
[14]SHI Y,EBERHART R C.Empirical study of particle swarm optimization[C].Proceedings of the 1999 Congress.Washington:DC:IEEE,1999:1945-1950.
[15]崔益安,李溪阳,向恩明,柳建新,朱肖雄,纪铜鑫.基于粒子群优化的双频激电数据联合反演[J].中国有色金属学报,2013,23(9):2498-2505.CUI Yian-an,LI Xi-yang,XIANG En-ming,LIU Jian-xin,ZHOU Xiao-xiong,JI Tong-xin.Joint inversion of dual frequency IP data using PSO[J].The Chinese Journal of Nonferrous Metals,2013,23(9):2498-2505.
[16]REZAKAZEMI M,DASHTI A,ASGHARI M,SHIRAZIA S.H2-selective mixed matrix membranes modeling using ANFIS,PSO-ANFIS,GA-ANFIS[J].International Journal of Hydrogen Energy,2017,42(22):15211-15225.
[17]HASANIPANAH M,SHAHNAZAR A,ARAB H,GOLZAR SB,AMIRI M.Developing a new hybrid-AI model to predict blast-induced backbreak[J].Engineering with Computers,2017,33(3):349-359.
[18]RINI D P,SHAMSUDDIN S M,YUHANIZ S S.Particle swarm optimization for ANFIS interpretability and accuracy[J].Soft Computing,2016,20(1):1-12.
[19]POUSINHO H M I,MENDES V M F,CATAL?O J P S.Ahybrid PSO-ANFIS approach for short-term wind power prediction in Portugal[J].Energy Conversion&Management,2011,52(1):397-402.
[20]LIU P,LENG W,FANG W.Training ANFIS model with an improved quantum-behaved particle swarm optimization algorithm[J].Mathematical Problems in Engineering,2013,2013(1):78-88.
[2]刘青,袁玮,王宝,彭良振.基于GA-BP神经网络的金精矿品位的预测[J].东北大学学报(自然科学版),2015,36(2):237-240.LIU Qing,YUAN Wei,WANG Bao,PENG Liang-zhen.Concentrate grade prediction of gold ore based on GA-BP neural network[J].Journal of Northeastern University(Natural Science),2015,36(2):237-240.
[3]韩万林,张幼蒂,张作祥.智能化方法在矿石品位估值中的应用[J].有色金属(矿山部分),2000,52(5):6-8.HAN Wan-lin,ZHANG You-di,ZHANG Zuo-xiang.Application of intelligent method in ore grade valuation[J].Nonferrous Metals(Mining Section),2000,52(5):6-8.
[4]韩万林,张幼蒂.用改进BP算法估算矿石品位[J].中国矿业,2000,9(3):83-85.HAN Wan-lin,ZHANG You-di.Estimation of ore grade by improved BP algorithm[J].China Mining Magazine,2000,9(3):83-85.
[5]谭正华,荆永滨,王李管,文中华,黄俊歆,陈建宏.基于空间变异性的IDW矿石品位估值改进方法[J].中国矿业大学学报,2011,40(6):928-932.TAN Zheng-hua,JING Yong-bin,WANG Li-guan,WENZhong-hua,HUANG Jun-xin,CHEN Jian-hong.Improved IDWmethod for ore grade estimation based on spatial variation[J].Journal of China University of Mining&Technology,2011,40(6):928-932.
[6]李娟,李翠平,李仲学.基于支持向量回归机的矿体品位插值[J].北京科技大学学报,2009,31(12):1498-1502.LI Juan,LI Cui-ping,LI Zhong-xue.Grade interpolation in orebody based on support vector regression[J].Journal of University of Science and Technology Beijing,2009,31(12):1498-1502.
[7]贾明涛,叶加冕,寇向宇,王李管.品位估值的自适应径向基神经网络构建技术[J].煤炭学报,2010,35(9):1524-1530.JIA Ming-tao,YE Jia-mian,KOU Xiang-yu,WANG Li-guan.The adaptive Radius Basis Function neural network modeling for the deposit grade estimation[J].Journal of China Coal Society,2010,35(9):1524-1530.
[8]李翠平,郑瑶瑕,张佳,侯定勇.基于遗传算法优化的支持向量机品位插值模型[J].北京科技大学学报,2013,35(7):837-843.LI Cui-ping,ZHENG Yao-xia,ZHANG Jia,HOU Ding-yong.Ore grade interpolation model based on support vector machines optimized by genetic algorithms[J].Journal of University of Science and Technology Beijing,2013,35(7):837-843.
[9]李翠平,李仲学,余东明.基于泰森多边形法的空间品位插值[J].辽宁工程技术大学学报,2007,26(4):488-491.LI Cui-ping,LI Zhong-xue,YU Dong-ming.Ore grade interpolation based on Thiessen polygon method[J].Journal of Liaoning Technical University,2007,26(4):488-491.
[10]SHI Xiu-zhi,ZHOU Jian,WU Bang-biao,HUANG Dan,WEIWei.Support vector machines approach to mean particle size of rock fragmentation due to bench blasting prediction[J].Transactions of Nonferrous Metals Society of China,2012,22(2):432-441.
[11]ZHOU Jian,LI Xi-bing,SHI Xiu-zhi,WEI Wei,WU Bang-biao.Predicting pillar stability for underground mine using Fisher discriminant analysis and SVM methods[J].Transactions of Nonferrous Metals Society of China,2011,21(12):2734-2743.
[12]张玉祥.小波神经网络遗传算法及其在矿山压力预报中的应用[J].中国有色金属学报,1999,9(2):240-244.ZHANG Yu-xiang.Gentic algorithm of wavelet network and its application in forecasting ground pressure[J].The Chinese Journal of Nonferrous Metals,1999,9(2):240-244.
[13]周仲礼,马腾,陈秀荣,秦飞龙.基于改进RBF的空间插值算法及其在矿体三维可视化中的应用[J].成都理工大学学报(自然科学版),2014,41(5):645-650.ZHOU Zhong-li,MA Teng,CHEN Xiu-rong,QIN Fei-long.Spatial interpoltaion algorithm based on improved RBF and its application to orebody 3D visualization[J].Journal of Chengdu University of Technology(Science&Technology Edition),2014,41(5):645-650.
[14]SHI Y,EBERHART R C.Empirical study of particle swarm optimization[C].Proceedings of the 1999 Congress.Washington:DC:IEEE,1999:1945-1950.
[15]崔益安,李溪阳,向恩明,柳建新,朱肖雄,纪铜鑫.基于粒子群优化的双频激电数据联合反演[J].中国有色金属学报,2013,23(9):2498-2505.CUI Yian-an,LI Xi-yang,XIANG En-ming,LIU Jian-xin,ZHOU Xiao-xiong,JI Tong-xin.Joint inversion of dual frequency IP data using PSO[J].The Chinese Journal of Nonferrous Metals,2013,23(9):2498-2505.
[16]REZAKAZEMI M,DASHTI A,ASGHARI M,SHIRAZIA S.H2-selective mixed matrix membranes modeling using ANFIS,PSO-ANFIS,GA-ANFIS[J].International Journal of Hydrogen Energy,2017,42(22):15211-15225.
[17]HASANIPANAH M,SHAHNAZAR A,ARAB H,GOLZAR SB,AMIRI M.Developing a new hybrid-AI model to predict blast-induced backbreak[J].Engineering with Computers,2017,33(3):349-359.
[18]RINI D P,SHAMSUDDIN S M,YUHANIZ S S.Particle swarm optimization for ANFIS interpretability and accuracy[J].Soft Computing,2016,20(1):1-12.
[19]POUSINHO H M I,MENDES V M F,CATAL?O J P S.Ahybrid PSO-ANFIS approach for short-term wind power prediction in Portugal[J].Energy Conversion&Management,2011,52(1):397-402.
[20]LIU P,LENG W,FANG W.Training ANFIS model with an improved quantum-behaved particle swarm optimization algorithm[J].Mathematical Problems in Engineering,2013,2013(1):78-88.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |