基于灰色关联分析的PSO-BP算法预测矿震危险性
|
摘要
以矿山微震监测数据为基础,结合地质、开采条件等因素,建立矿震危险性神经网络预测模型。首先,利用神经网络变量选择的方法,根据BP神经网络的权值和阈值,对多因素诱导的矿震危险性进行分析;然后,通过灰色关联分析消除输出指标的偶然性,建立基于矿震能量消噪值的神经网络,对矿震危险性进行预测;最后,用基于杂交的粒子群算法优化神经网络。研究结果表明:矿震危险性受爆破药量、岩层强度比、开采深度和空区体积的影响非常大,占总影响值的87.35%,而受其他因素的影响较小,说明矿震与开采深度和空区规模之间呈高度的非线性关系;采用该预测模型使BP网络的收敛速度加快,训练精度较高,预测结果的相对误差下降52.64%。该模型对硬岩金属矿山的矿震活动研究有一定的参考价值。
Based on the data of micro-seismic system of mine,combining with mining and geological conditions and other factors,the prediction model of neural network was established.Firstly,using the method of variable selection based on neural network,according to the weights and thresholds of BP neural network,risk of multi-factor-induced mine earthquake was analyzed.Then contingency of output index was eliminated through grey correlation analysis,and the neural network based on de-nosing value for energy of mining tremor was established to predict risk of mine earthquake.Finally,particle swarm optimization algorithm was used to optimize neural network based on hybridization.The results show that mine earthquake is affected mainly by blasting capacity,ratio to intensity of strata,mining depth and gap volume,accounting for 87.35% of the total impact value,but it is less affected by other factors,so there is nonlinear relationship between mine earthquake and human exploitation to a great extent.This prediction model speeds up the convergence rate of BP network,and improves the training accuracy,and the relative error of predictions decreases by 52.64%.The method provides some reference value for the study of mine earthquake of the hard-rock metal mines.
Based on the data of micro-seismic system of mine,combining with mining and geological conditions and other factors,the prediction model of neural network was established.Firstly,using the method of variable selection based on neural network,according to the weights and thresholds of BP neural network,risk of multi-factor-induced mine earthquake was analyzed.Then contingency of output index was eliminated through grey correlation analysis,and the neural network based on de-nosing value for energy of mining tremor was established to predict risk of mine earthquake.Finally,particle swarm optimization algorithm was used to optimize neural network based on hybridization.The results show that mine earthquake is affected mainly by blasting capacity,ratio to intensity of strata,mining depth and gap volume,accounting for 87.35% of the total impact value,but it is less affected by other factors,so there is nonlinear relationship between mine earthquake and human exploitation to a great extent.This prediction model speeds up the convergence rate of BP network,and improves the training accuracy,and the relative error of predictions decreases by 52.64%.The method provides some reference value for the study of mine earthquake of the hard-rock metal mines.
引文
[1]袁子清,杨小聪,唐礼忠.冬瓜山铜矿矿山地震活动响应规律研究[J].有色金属,2009,61(1):113-115.YUAN Zi-qing,YANG Xiao-cong,TANG Li-zhong.Response law of mining-induced seismicity in Dongguashan copper Mine[J].Nonferrous Metals,2009,61(1):113-115.
[2]袁子清,杨小聪,唐礼忠.硬岩金属矿山开采活动与矿山地震活动的关系研究[J].中国安全科学学报,2008,18(4):16-19.YUAN Zi-qing,YANG Xiao-cong,TANG Li-zhong.Research on the relationship between exploiting activity of hard-rock metal mines and mining-induced seismicity[J].China Safety Science Journal,2008,18(4):16-19.
[3]张向东,李永靖,兰常玉.模糊神经网络在矿震预测中的应用[J].中国地质灾害与防治学报,2005,16(2):71-73.ZHANG Xiang-dong,LI Yong-jing,LAN Chang-yu.Application of fuzzy neural network system in mine earthquake prediction[J].The Chinese Journal of Geological Hazard and Control,2005,16(2):71-73.
[4]蔡美峰,李治平,纪洪广,等.神经网络在开采与矿山地震活动性关系研究中的应用[J].中国矿业,2002,11(2):6-9.CAI Mei-feng,LI Zhi-ping,JI Hong-guang,et al.Neural networks application to study the relation between Mining activities and seismic vibrations[J].China Mining Magazine,2002,11(2):6-9.
[5]Kabiesz J.神经网络预测矿震危险性[J].窦林名,译.煤炭科技,2007(4):71-74.Kabiesz J.Influence of data on the quality of mine tremors hazard assessment using neural networks[J].DOU Lin-ming,trans.Coal Science&Technology Magazine,2007(4):71-74.
[6]龚纯,王正林.精通MATLAB最优化计算[M].北京:电子工业出版社,2009:307-311.GONG Chun,WANG Zheng-lin.Proficient in MATLAB optimization calculation[M].Beijing:Electronics Industry Press,2009:307-311.
[7]彭扬,伍蓓.物流系统优化与仿真[M].北京:中国物质出版社,2007:173-180.PENG Yang,WU Bei.Logistics system optimization and simulation[M].Beijing:China Materials Press,2007:173-180.
[8]秦毅男,廖晓辉,赵庆治.一种基于粒子群优化算法的神经网络训练方法[J].河南师范大学学报:自然科学版,2007,35(3):169-171.QIN Yi-nan,LIAO Xiao-hui,ZHAO Qing-zhi.A neural network training algorithm based on particle swarm optimization[J].Journal of Henan Normal University:Natural Science,2007,35(3):169-171.
[9]许敏.基于PSO算法的BP神经网络在边坡稳定性评价中的应用[J].温州职业技术学院学报,2009,9(2):49-51.XU Min.Application of BP neural network in slope stability evaluation on the basis of PSO algorithm[J].Journal of Wenzhou Vocational and Technical College,2009,9(2):49-51.
[10]赵振江.基于PSO-BP神经网络的网络流量预测与研究[J].计算机应用与软件,2009,26(1):218-221.ZHAO Zhen-jiang.Prediction and research on network traffic based on PSO-BP neural network[J].2009,26(1):218-221.
[11]杜栋,庞庆华.现代综合评价方法与案例精选[M].2版.北京:清华大学出版社,2008:203-208.DU Dong,PANG Qing-hua.Modern comprehensive evaluation methods and case selection[M].2nd ed.Beijing:Tsinghua University Press,2008:203-208.
[12]唐礼忠.深井矿山地震活动与岩爆监测及预测研究[D].长沙:中南大学资源与安全工程学院,2008:121-129.TANG Li-zhong.Study on monitoring and prediction of seismicity and rockburst in a deep mine[D].Changsha:Central South University.School of Resources and Safety Engineering,2008:121-129.
[13]袁子清.矿震地震活动响应规律及其危险性预测研究[D].长沙:中南大学资源与安全工程学院,2007:133-137.YUAN Zi-qing.Research on risk prediction and response law of mining-induced seismicity[D].Changsha:Central South University.School of Resources and Safety Engineering,2007:133-137.
[14]杨璐,高自友.用神经网络进行变量选择[J].北方交通大学学报,1999,23(3):53-56.YANG Lu,GAO Zi-you.Useing neural network for variable selection[J].Journal of Northern Jiaotong University,1999,23(3):53-56.
[15]高仁祥,张世英,刘豹.基于神经网络的变量选择方法[J].系统工程学报,1998,13(2):32-37.GAO Ren-xiang,ZHANG Shi-ying,LIU Bao.Variable selection approach based on neural network analysis[J].Journal of Systems Engineering,1998,13(2):32-37.
[16]闻新.MATLAB神经网络应用设计[M].北京:科学出版社,2001:278-283.WEN Xing.Neural network simulation and application based on MATLAB[M].Beijing:Science Press,2003:278-283.
[2]袁子清,杨小聪,唐礼忠.硬岩金属矿山开采活动与矿山地震活动的关系研究[J].中国安全科学学报,2008,18(4):16-19.YUAN Zi-qing,YANG Xiao-cong,TANG Li-zhong.Research on the relationship between exploiting activity of hard-rock metal mines and mining-induced seismicity[J].China Safety Science Journal,2008,18(4):16-19.
[3]张向东,李永靖,兰常玉.模糊神经网络在矿震预测中的应用[J].中国地质灾害与防治学报,2005,16(2):71-73.ZHANG Xiang-dong,LI Yong-jing,LAN Chang-yu.Application of fuzzy neural network system in mine earthquake prediction[J].The Chinese Journal of Geological Hazard and Control,2005,16(2):71-73.
[4]蔡美峰,李治平,纪洪广,等.神经网络在开采与矿山地震活动性关系研究中的应用[J].中国矿业,2002,11(2):6-9.CAI Mei-feng,LI Zhi-ping,JI Hong-guang,et al.Neural networks application to study the relation between Mining activities and seismic vibrations[J].China Mining Magazine,2002,11(2):6-9.
[5]Kabiesz J.神经网络预测矿震危险性[J].窦林名,译.煤炭科技,2007(4):71-74.Kabiesz J.Influence of data on the quality of mine tremors hazard assessment using neural networks[J].DOU Lin-ming,trans.Coal Science&Technology Magazine,2007(4):71-74.
[6]龚纯,王正林.精通MATLAB最优化计算[M].北京:电子工业出版社,2009:307-311.GONG Chun,WANG Zheng-lin.Proficient in MATLAB optimization calculation[M].Beijing:Electronics Industry Press,2009:307-311.
[7]彭扬,伍蓓.物流系统优化与仿真[M].北京:中国物质出版社,2007:173-180.PENG Yang,WU Bei.Logistics system optimization and simulation[M].Beijing:China Materials Press,2007:173-180.
[8]秦毅男,廖晓辉,赵庆治.一种基于粒子群优化算法的神经网络训练方法[J].河南师范大学学报:自然科学版,2007,35(3):169-171.QIN Yi-nan,LIAO Xiao-hui,ZHAO Qing-zhi.A neural network training algorithm based on particle swarm optimization[J].Journal of Henan Normal University:Natural Science,2007,35(3):169-171.
[9]许敏.基于PSO算法的BP神经网络在边坡稳定性评价中的应用[J].温州职业技术学院学报,2009,9(2):49-51.XU Min.Application of BP neural network in slope stability evaluation on the basis of PSO algorithm[J].Journal of Wenzhou Vocational and Technical College,2009,9(2):49-51.
[10]赵振江.基于PSO-BP神经网络的网络流量预测与研究[J].计算机应用与软件,2009,26(1):218-221.ZHAO Zhen-jiang.Prediction and research on network traffic based on PSO-BP neural network[J].2009,26(1):218-221.
[11]杜栋,庞庆华.现代综合评价方法与案例精选[M].2版.北京:清华大学出版社,2008:203-208.DU Dong,PANG Qing-hua.Modern comprehensive evaluation methods and case selection[M].2nd ed.Beijing:Tsinghua University Press,2008:203-208.
[12]唐礼忠.深井矿山地震活动与岩爆监测及预测研究[D].长沙:中南大学资源与安全工程学院,2008:121-129.TANG Li-zhong.Study on monitoring and prediction of seismicity and rockburst in a deep mine[D].Changsha:Central South University.School of Resources and Safety Engineering,2008:121-129.
[13]袁子清.矿震地震活动响应规律及其危险性预测研究[D].长沙:中南大学资源与安全工程学院,2007:133-137.YUAN Zi-qing.Research on risk prediction and response law of mining-induced seismicity[D].Changsha:Central South University.School of Resources and Safety Engineering,2007:133-137.
[14]杨璐,高自友.用神经网络进行变量选择[J].北方交通大学学报,1999,23(3):53-56.YANG Lu,GAO Zi-you.Useing neural network for variable selection[J].Journal of Northern Jiaotong University,1999,23(3):53-56.
[15]高仁祥,张世英,刘豹.基于神经网络的变量选择方法[J].系统工程学报,1998,13(2):32-37.GAO Ren-xiang,ZHANG Shi-ying,LIU Bao.Variable selection approach based on neural network analysis[J].Journal of Systems Engineering,1998,13(2):32-37.
[16]闻新.MATLAB神经网络应用设计[M].北京:科学出版社,2001:278-283.WEN Xing.Neural network simulation and application based on MATLAB[M].Beijing:Science Press,2003:278-283.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心