滨海金矿涌水危险评价及涌水量混沌预测研究
|
摘要
针对涌水危险评价中的不确定性及随机性问题,以水文地质条件中10个因素作为评价指标,建立了滨海金矿涌水危险的云模型并进行评价。基于评价结果,对危险中段的涌水量时间序列进行相空间重构;分析了涌水量相点距离演变规律,建立了涌水安全预警机制;结合重构相空间,建立了涌水量RBF神经网络预测模型。研究表明:云模型的评价结果准确可靠;相空间重构揭示了系统的混沌特性,最邻近相点演化放大了涌水量变化的细微特征,为涌水安全预警机制的建立提供了依据;混沌RBF神经网络实现了涌水量的短期精确预测,可为井下安全开采提供技术保障。
In view of the uncertainty and randomness in the process of risk assessment of water inrush,10 factors of hydrogeological conditions were considered to construct evaluation index system,and a cloud model for water inrush risk assessment in coastal gold mine was established.Based on the evaluation results,the phase space reconstruction of the water inrush time series is carried out.The evolution law of the influx phase distance is analyzed,and the early warning mechanism of water inrush is established.Combined with the reconstructed phase space,the RBF neural network prediction model is established.The results show that the evaluation results of the cloud model are accurate and reliable.The phase space reconstruction reveals the chaotic characteristics of the system.The nearest neighbor phase evolution magnifies the subtle characteristics of the water inflow change,which provides a basis for the establishment of the early warning mechanism of the water inrush.The chaotic RBF nerve network short-term accurate predictions of water inflow and provides technical support for safe underground mining.
In view of the uncertainty and randomness in the process of risk assessment of water inrush,10 factors of hydrogeological conditions were considered to construct evaluation index system,and a cloud model for water inrush risk assessment in coastal gold mine was established.Based on the evaluation results,the phase space reconstruction of the water inrush time series is carried out.The evolution law of the influx phase distance is analyzed,and the early warning mechanism of water inrush is established.Combined with the reconstructed phase space,the RBF neural network prediction model is established.The results show that the evaluation results of the cloud model are accurate and reliable.The phase space reconstruction reveals the chaotic characteristics of the system.The nearest neighbor phase evolution magnifies the subtle characteristics of the water inflow change,which provides a basis for the establishment of the early warning mechanism of the water inrush.The chaotic RBF nerve network short-term accurate predictions of water inflow and provides technical support for safe underground mining.
引文
[1]郭牡丹,王述红,荣晓洋,等.基于流固耦合理论的隧道涌水量预测[J].东北大学学报(自然科学版),2011,32(5):745-748.GUO Mudan,WANG Shuhong,RONG Xiaoyang,et al.Using coupled fluid-solid theory to forecast tunnel water inflow[J].Journal of Northeastern University(Natural Science),2011,32(5):745-748.
[2]BOUW P C,MORTON K L.Calculation of mine water inflow using interactively agroundwater model and an inflow model[J].International Journal of Mine Water,1987,6(4):31-50
[3]HOLMΦY K H,NILSEN B.Significance of geological parameters for predicting water inflow in hard rock tunnels[J].Rock Mechanics and Rock Engineering,2014,47:853-868.
[4]GUO H,ADHIKARY D P,M S CRAIG.Simulation of mine water inflow and gas emission during longwall mining[J].Rock Mechanics and Rock Engineering,2009,42:25-51.
[5]乔伟,李文平,赵成喜.煤矿底板突水评价突水系数-单位涌水量法[J].岩石力学与工程学报,2009,28(12):2466-2474.QIAO Wei,LI Wenping,ZHAO Chengxi.Water inrush coefficient-unit inflow method for water inrush evaluation of coal mine floor[J].Chinese Journal of Rock Mechanics and Engineering,2009,28(12):2466-2474.
[6]周宗青,李术才,李利平,等.岩溶隧道突涌水危险性评价的属性识别模型及其工程应用[J].岩土力学,2013,34(3):818-826.ZHOU Zongqing,LI Shucai,LI Liping,et al.Attribute recognition model of fatalness assessment of water inrush in karst tunnels and its application[J].Rock and Soil Mechanics,2013,34(3):818-826.
[7]LI B,CHEN Y L.Risk Assessment of coal floor water inrush from underlying aquifers based on GRA-AHP and its application[J].Geotechnical and Geological Engineering,2016,34(1):143-154.
[8]HU S Y,LI D R,LIU Y L,et al.Mining weights of land evaluation factors based on cloud model and correlation analysis[J].Geo-spatial Information Science,2007,10(3):218-222.
[9]ZHANG F Z,ZHANG W Y,GENG J Z,et al.Prediction analysis of traffic flow based on cloud model[M]//Advances in Intelligent and Soft Computing.Berlin:Springer-Verlag,2012:219-227.
[10]KWONG C K,BAI H.A fuzzy AHP approach to the determination of importance weights of customer requirements in quality function deployment[J].Journal of Intelligent Manufacturing,2002,13(5):367-377.
[11]WANG T,CHEN J S,WANG T,el at.Entropy weightset pair analysis based on tracer techniques for dam leakage investigation[J].Nat Hazards,2015,76(2):747-767.
[12]STRAK J.Recursive prediction of chaotic time series[J].Journal of Nonlinear Science,1993,3(1):197-223.
[13]ALBANO A M,MUENCH J,SCHWA RTZ C,et al.Singular-value decomposition and the Grassberger-Procaccia algorithm[J].Physical Review A,1988,38(6):3017-3026
[14]LI X B,WANG Q S,YAI J R,et al.Chaotic time series prediction for surrounding rock’s deformation of deep mine lanes in soft rock[J].Journal of Central South University of Technology,2008,15(2):224-229.
[15]ZHANG S Q,HU Y T,BAO H Y,et al.Parameters determination method of phase-space reconstruction based on differential entropy ratio and RBF neural network[J].Journal of Electronics,2014,31(1):61-67.
[16]DU B X,XU W,SONG B B,et al.Prediction of chaotic time series of RBF neural network based on particle swarm optimization[M]//Intelligent data analysis and its applications,Volume II.Berlin:Springer-Verlag,2014:489-497.
[2]BOUW P C,MORTON K L.Calculation of mine water inflow using interactively agroundwater model and an inflow model[J].International Journal of Mine Water,1987,6(4):31-50
[3]HOLMΦY K H,NILSEN B.Significance of geological parameters for predicting water inflow in hard rock tunnels[J].Rock Mechanics and Rock Engineering,2014,47:853-868.
[4]GUO H,ADHIKARY D P,M S CRAIG.Simulation of mine water inflow and gas emission during longwall mining[J].Rock Mechanics and Rock Engineering,2009,42:25-51.
[5]乔伟,李文平,赵成喜.煤矿底板突水评价突水系数-单位涌水量法[J].岩石力学与工程学报,2009,28(12):2466-2474.QIAO Wei,LI Wenping,ZHAO Chengxi.Water inrush coefficient-unit inflow method for water inrush evaluation of coal mine floor[J].Chinese Journal of Rock Mechanics and Engineering,2009,28(12):2466-2474.
[6]周宗青,李术才,李利平,等.岩溶隧道突涌水危险性评价的属性识别模型及其工程应用[J].岩土力学,2013,34(3):818-826.ZHOU Zongqing,LI Shucai,LI Liping,et al.Attribute recognition model of fatalness assessment of water inrush in karst tunnels and its application[J].Rock and Soil Mechanics,2013,34(3):818-826.
[7]LI B,CHEN Y L.Risk Assessment of coal floor water inrush from underlying aquifers based on GRA-AHP and its application[J].Geotechnical and Geological Engineering,2016,34(1):143-154.
[8]HU S Y,LI D R,LIU Y L,et al.Mining weights of land evaluation factors based on cloud model and correlation analysis[J].Geo-spatial Information Science,2007,10(3):218-222.
[9]ZHANG F Z,ZHANG W Y,GENG J Z,et al.Prediction analysis of traffic flow based on cloud model[M]//Advances in Intelligent and Soft Computing.Berlin:Springer-Verlag,2012:219-227.
[10]KWONG C K,BAI H.A fuzzy AHP approach to the determination of importance weights of customer requirements in quality function deployment[J].Journal of Intelligent Manufacturing,2002,13(5):367-377.
[11]WANG T,CHEN J S,WANG T,el at.Entropy weightset pair analysis based on tracer techniques for dam leakage investigation[J].Nat Hazards,2015,76(2):747-767.
[12]STRAK J.Recursive prediction of chaotic time series[J].Journal of Nonlinear Science,1993,3(1):197-223.
[13]ALBANO A M,MUENCH J,SCHWA RTZ C,et al.Singular-value decomposition and the Grassberger-Procaccia algorithm[J].Physical Review A,1988,38(6):3017-3026
[14]LI X B,WANG Q S,YAI J R,et al.Chaotic time series prediction for surrounding rock’s deformation of deep mine lanes in soft rock[J].Journal of Central South University of Technology,2008,15(2):224-229.
[15]ZHANG S Q,HU Y T,BAO H Y,et al.Parameters determination method of phase-space reconstruction based on differential entropy ratio and RBF neural network[J].Journal of Electronics,2014,31(1):61-67.
[16]DU B X,XU W,SONG B B,et al.Prediction of chaotic time series of RBF neural network based on particle swarm optimization[M]//Intelligent data analysis and its applications,Volume II.Berlin:Springer-Verlag,2014:489-497.