摘要
煤炭作为我国重要的能源与燃料,占能源消费总量的比例大约75%左右。由于煤炭工业的基础地位,实现安全、高效地可持续发展是中国实现经济重大战略目标的可靠保证。近几年,我国重大煤矿事故的不断发生,说明我国的煤矿安全形势没有得到根本性的好转。煤矿安全是煤炭工业目前最突出、最需要解决的关键问题。
本文将利用突变、再生核神经网络、支持向量机等基本原理给出矿井安全系统中的煤与瓦斯突出、地下煤层面重构及地表沉陷等方面进行安全预测的方法,为矿井安全预测提供有力的理论依据。
1、突变理论是奇点理论和分岔理论研究不连续变化现象的理论,是一个新兴的数学分支。煤与瓦斯突出是发生在矿井煤岩体中的灾害动力现象,是含瓦斯煤岩体的一种剧烈的能量释放形式。基于力学或能量的观点,突出从孕育到启动和从发展到结束都具有明显的突变特征。本文将根据煤与瓦斯突出产生的条件,对煤与瓦斯突出的综合作用过程和突出过程做出系统的理论分析,运用突变学理论,建立燕尾突变模型,实现安全预测。
2、再生核源于不同学科分支,目前已成为函数逼近的重要工具。将再生核与神经网络有机地结合起来,提出一种新型的再生核神经网络。它将网络的训练归结为求解线性方程组问题,建立了一种既有足够精度又能表现系统行为的稀疏解数学模型。这种模型对于断层面的重构方法与样条方法比较,更符合实际情况。本文将利用再生核神经网络对断层面进行重构,及时了解采煤面的变化,预防井塌事故的发生,实现安全预测。
3、煤矿开采所产生的沉降受多个因素的影响,并且每个因素对其作用的函数关系很难界定。因此煤矿开采的地表沉降预测是属于复杂的非线性系统问题。支持向量机理论是对数据挖掘和处理的新方法。从统计学的概率角度考虑比神经元网络更精确,是解决煤矿开采问题的更为有效方法。本文将运用支持向量机方法,通过分析矿区水文地质条件和沉降基本因素,处理地表沉降数据。得到更符合实际的地表沉降的预测模型。给出矿区沉降的预测方法,实现安全预测。
Coal mine, as China’s important energy source and fuel, has the proportion of the total energy demand, about 75% or so. Since the fundamental position, secure implementation, and efficient and sustainable development of coal industry are the reliable guarantee for attaining great economic strategic objectives of China. In recent years, the repeated occurrence of major coal accidents indicates that the coal security situation has not been improved fundamentally. The problem of coal mine security is the most remarkable and urgent one in China that should be solved at present.
This article will give some methods to predict coal and gas outburst, reconstruction of underground coal delamination, and surface subsidence in mine security system, which utilizes the basic principles of mutation, reproducing kernel neural system and support vector machines. It provides the strong evidences for the safe prediction of mine based on theory. Catastrophe theory is a new subdivision of mathematics, a theoretical research studied by singularity theory and bifurcation theory about the discontinous change phenomenon. Coal and gas outburst is a catastrophic dynamic phenomena happening in the mine, coal and rock mass, also a form of violent energy releasing of coal-rock with gas. Based on the opinions of mechanics and energy, distinct mutation features are stressed from gestation to sartup and from development to the end. According to the conditions of producing coal and gas outburst, theroretical analysis is made systematically in this article to the synthetically effects and outburst process in the coal and gas outburst, on the other hand,catastrphe theory is applied, which are both used to build swallowtail catastrophe model and to fulfill secure prediction.
Reproducing kernel originating from different branches, which has become an important tool of approximation currently. Combining reproducing kernel with neural networks organically aims to put forward a new type of reproducing kernel-neural network. his new type contributes network training to the problem solving linear equations, and set up a sparse solution of mathematical model with sufficient accurancy and performing of system behavior. Compared with the reconstruction of fault plane and spline, this model is more in line with the actual situation. This article will take advantage of reproducing kernel-neurual network in order to reconstruct the fault plane, learn changes on surface coal mining, prevent the accidents of well collapse and achieve the secure prediction.
Precipitation produced by coal mining is effected by a number of factors. The relationship between each factor and the function it plays is hard to define. Therefore, the prediction of surface coal mining subsidence belongs to the complicated nonlinear system problems. Support vector machine theory is a new method to data mining and processing. Taking the probability viewpoint of statistics into consideration, it is more accurate than neurual network, and the best way to solve the coal mining problem. This article applies the methods for support vector machines and the analysis of hydro-geological conditions in mine area, settlement and other basic factors lement data, get the prediction model of surface settlement that is more realistic, give the prediction of mine area settlement and achieve security forecast.
引文
[1]赵帅,季淮君,盛真可。煤与瓦斯突出预测技术发展现状分析山西焦煤科技2009,21 369页;
[2]聂百胜,何学秋,王恩元等。煤与瓦斯突出预测技术研究现状及发展趋势中国安全科学学报2003.6 41-42页;
[3]苏文叔。利用瓦斯涌出动态指标预测煤与瓦斯突出[J].煤炭工程师,1996(5):2-7.SU Wen-shu. Probe into prediction of gas and coal outbust with dynamic index of gas emission[J]. Coal Engineer, 1996(5) :p2-7;
[4]胡鹏华大直径钻孔预测与瓦斯突出可行性的理论研究中国地质大学硕士学位论文2007 34-35页;
[5]蔡晓明。基于地理信息系统的煤矿瓦斯突出预测研究昆明理工大学硕士学位论文125-130页;
[6]李军涛,杨建军。浅谈煤与瓦斯突出的防治措施煤矿安全2005 36(9) 59-60页;
[7]黄军,木飞。浅谈防治煤与瓦斯突出安全技术与管理2006(4)51-52页;
[8]孙忠强,苏昭桂,张金峰。煤与瓦斯突出预测预报技术研究现状及发展趋势能源技术与管理2008.2 56-57页;
[9]魏风清等。俄罗斯地震声学预测方法的研究现状及发展前景[[J]煤矿安全,1999,11页;
[10]魏乐平,金及河,陈和平。煤与瓦斯突出几个难点问题的探讨江西煤炭科技2006(2) 55-56页;
[11]聂百胜,何学秋,王恩元等。煤与瓦斯突出预测技术研究现状及发展趋势[J],中国安全科学学报;
[12]漆旺生,凌标灿,蔡嗣经。煤与瓦斯突出预测研究动态及展望[J].中国安全科学学报,2003,13(12):1-4页;
[13]单晓云,赵树果,高智芳。煤与瓦斯突出的预测及防治措施[J].中国煤炭,2005,31(4):34-36页;
[14]王恩元,何学秋,刘贞堂等。煤岩变形破裂电磁辐射规律及其应用研究[J]中国安全科学学报,2000,10(2):35-39页;
[15]郭立稳,俞启香,王凯。煤吸附瓦斯过程温度变化的试验研究[J].中国矿业大学学报,2000,29(3):287-289页;
[16]王宏图,鲜学福,贺建民等。用温度指标预测掘进工作面突出危险性的探讨[J].重庆大学学报,1999,22(2):34-38页;
[17]杨凌霄等。基于支持向量机的煤与瓦斯突出预测研究河南理工大学学报2006,10 348-350页;
[18]陈凤等。模糊小波网络在煤与瓦斯突出预测中的应用煤矿安全2006,10,51-53页;
[19]杨艳国等矿井煤与瓦斯突出危险性模糊综合评价方法研究矿业快报2006,11 30-31页;
[20]马雷舍夫等。煤与瓦斯突出预测方法和防治措施煤炭工业出版社2003 42-47页;
[21]李忠华,潘一山,纪海汛,王海兵。瓦斯煤层冲击地压防治技术及应用国防工业出版社2009 11-13页;
[22]曹传荣高速公路BOT项目经济可行性评价研究北京交通大学硕士学位论文80-83页;
[23]凌复华。突变理论及其应用[M]上海交通大学出版社1988 55页
[24]孙艳。动荷载作用下土体破坏的突变理论应用大连交通大学硕士学位论文35-38页;
[25]勾攀峰等基于突变理论的深井巷道临界深度岩石力学与工程学报2004(12);
[26]王连国。煤柱失稳的突变学特征研究中国矿业大学学报2007.1;
[27]施泽进等。突变理论在断层活动机理中的应用西安地质学院学报1996.3 50-52页;
[28]谷新建。用突变理论分析矿山冒落型地震机理中国安全科学学报2003(10)8-10页;
[29]付鹤林。用突变理论预测地下采场冲击地压发生的可能性湖南有色金属1995(11)17-19页
[30]林放。黑龙江省煤矿采区三维地震勘探技术的发展和作用。煤炭技术,2006(125):100-101页;
[31]陈晓雷。浅谈煤矿地质勘探技术及其重要性。矿业论坛,2009(15):721页;
[32]郭爱煌。煤矿水平钻孔测井数值模拟.矿井物探,1998,26(2):62-65页;
[33]邢相荣,卜昌森等。瑞利波探测技术在矿井中的应用.矿井地质,1997,17(1):40-42页;
[34]李建军,刘鸿福。应用瞬态瑞利波技术跟踪探测煤层夹矸的变化。太原理工大学学报,2004,25(1):32-34页;
[35] S.Bergman. Uber die entwicklung der harmonischen funcktionen der Ebene unddes raumes nach orthogonal funktionen. Math. Ann. 1922, 86:P238-271;
[36] S.Bergman.über Kurvenintegale von Funktionen zweier komplexen Veranderlichen , die DifferentialgleichungenΔV + V= 0 befriedigen.Math.Z.32,1930:P386-406;
[37] S.Bergman.über ein Verfahren zur Konstruktion der Naherungsl?Su-ngsl?sungen der GleichungΔu +τ2 u= 0.Prikl. Mat. Meh. 1936:P97-107 ;
[38] S.Bergman.Zur Theorie der Funktion , die eine linear partielle Differentialgleichung berriedigen. Mat. Sb. 44, 1937: P1169-1198;
[39] S.Bergman.Zur Theorie der Funktion , die eine linear partielle Differentialgleichung. berriedigen. Soviet. Math. Dokl. 15, 1937:P227-230;
[40] S.Bergman.Sur un lien entre lal théorie des equations aux derives Partielles elliptiques et celle des functions d’une variable complexe.C.R.Acal.Sci., Paris.205,1937:1198-1200,P1360-1362;
[41] S.Bergman.The approximation of functions satisfying a linear partial differential equation.Duke Math.J., 1940,6:P537-561;
[42] J.Mercer.Function of Positive and Negative Type and Their Connection with The Theory of Integral Equation. Philos. Trans. Roy.Soe.London Ser.A1909,209:P415-446;
[43] N.Aronszajn.Theory of reproducingKernels. Trans. Amer. Math. soc. 68,1950:P337-404;
[44]张艳英,么焕民,黄丽波。多元插值.哈尔滨师范大学自然科学学报. 1997, (1):9-12页;
[45]张艳英。W 21 (D)空间中的多元迭代插值.哈尔滨理工大学学报1997,(6):81-1-84页;
[46]吴勃英。W 22 (D)空间函数的近似再生.哈尔滨师范大学自然科学学报. 1995,(3):14-24页;
[47]吴勃英,崔明根。W 22 (D)第一类算子方程近似解.高等学校计算数学学报. 1999,21(4):369-374页;
[48]闫玉斌。Volterra积分方程与更新积分方程精确解.哈工大硕士学位论文. 1991;
[49] Cui minggen, Yan yubin. The Representation of The Solution of A Kind of Operator Equation Au = f. Numerical Math, A Journal of Chinese Univerities. 1995,17(1):P82-86;
[50] Yunhui Li, Fazhan Geng, Minggen Cui, The analytical solution of singular linear periodic boundary value problem, Applied Mathematical Science, 1(2)(2007)P77-87;
[51] .Chun-li Li, Minggen Cui, How to solve the equation AuBu+Cu=f, Applied Mathematics and Computation133 (2002) P643-653;
[52] Chun-li Li, Minggen Cui。The exact solution for a class nonlinear operator equations in the reproducing kernel space , Applied Mathematics and Computation 143(2003)P393-399;
[53]李春利,崔明根。再生核空间中非线性方程K 1 uK2u=f的精确解.黑龙江大学学报. 2002,3:14-17页;
[54]李春利。算子方程求解方法.哈工大博士学位论文. 2002;
[55] Alpay Daniela, Dym Harryb. On a New Class of Realization Formulas and Their Application. Linear Algebra and its Applications. 1996,241-243 P3-84;
[56] Hult Henrika. Approximating some Volterra type stochastic integrals with applications to parameter estimation. Stochastic Processes and their Applicati-ons. 2003,105(1):P1-32;
[57] Chong Gua. Penalized Likelihood Estimation: Convergence under Incorrect Model. Statistics & Probability Letters. 1998,36(4): P359-364;
[58] Park B.U.a, Kim W.C.a, Jones M.C. On Identity Reproducing Nonparametric Regression Estimators. Statistics & Probability Letters. 1997 ,32(3):P279-290;
[59] Strauss Daniel J.a , Steidl Gabrielea. Hybrid Wavelet-Support Vector classificati- on of Waveforms. Journal of Computational and Applied Mathematics. 2002,148 (2) :P375-400;
[60] Hao Sua, Liu Wing Kama, Chang Chin Tanga。Computer Implementation of Damage Models by Finite Element and Meshfree Methods. Computer Methods in Applied Mechanics and Engineering. 2000,187(3-4): P401-440;
[61] Günther Franka, Liu Wing Kama 1, Diachin Darina, Christon Mark A.b. Multi-scale Meshfree Parallel Computations for Viscous, compressible flows. Comput- er Methods in Applied Mechanics and Engineering. 2000 ,190(3-4):P279-303 ;
[62] Günther Frank C.a, Liu Wing Kama. Implementation of Boundary Conditions for Meshless Methods. Computer Methods in Applied Mechanics and Engineering. 1998,163(1-4):P205-230;
[63] Han Weimina, Meng Xuepinga. Error Analysis of The Reproducing Kernel Parti- cle Method. Computer Methods in Applied Mechanics and Engineering. 2001,190(46-47):P6157-6181;
[64] Chen Jiun-Shyana, Yoon Sangpilb, Wang Hui-Pingb, Liu Wing Kamc. An Improved Reproducing Kernel Particle Method for Nearly Incompressible Finite Elasticity. Computer Methods in Applied Mechanics and Engineering.2000, 181 (1-3):P117-145 ;
[65] Voth Thomas E.a, Christon Mark A.b. Discretization Errors Associated withReproducing Kernel Methods: One-Dimensional Domains. Computer Methods in Applied Mechanics and Engineering. 2001,190(18-19):P2429-2446;
[66] Liu Wing-Kama , Shaofan Lia , Belytschko Teda. Moving Least-Square Reprodu-cing Kernel Methods (I) Methodology and Convergence. Computer Methods in Applied Mechanics and Engineering. 1997,143(1-2):P 113-154;
[67] Wing KamLiua, Yijung Chena, Uras R. Azizb, Chin Tang Chang. Generalized Multiple Scale Reproducing Kernel Particle Methods. Computer Methods in Applied Mechanics and Engineering. 1996,139(1-4):P91-157;
[68]邹友峰,邓喀中,马伟民等。矿山开采沉陷工程[M].北京:中国矿业大学,2003;
[69]萨武斯托维奇A.地下开采对地表的影响[M].北京:煤炭工业出版社,1955;
[70]何国清,马伟民,王金庄。威布尔分布型影响函数在地表移动计算中的应用碎块体理论研究岩移基本规律的探讨[J].中国矿业学院学报,1982(1);
[71]刘宝琛,廖国华。煤矿地表移动的基本规律[M].北京,中国工业出版;
[72]郝庆旺。采动岩体空隙扩散模型及其在开采沉陷研究中的应用[博士论文].徐州:中国矿业大学,1998;
[73]李增琪。使用富氏积分变换计算开挖引起的地表移动[J].北京:煤炭学报,1983(6);
[74]李增琪。使用富氏积分变换计算开挖引起的地表移动之二-水平煤层空间问题[J].北京:煤炭学报,1985(1);
[75]徐挺。相似方法及其应用。北京:机械工业出版社,1995;
[76]何满潮。条带煤柱的抗滑稳定性分析[J].水文地质与工程地质,1993(6);
[77]邓喀中。开采沉陷中的岩体结构效应研究[博士论文].北京:中国矿业大学,1993:1-50;
[78]高廷法。岩移“四带”模型与动态位移反分析[J].煤炭学报,1996(2);
[79]吴侃等。急倾斜厚煤层条带开采三维有限元模拟分析[J].北京:矿山测量,1994(3);
[80]张俊英。大倾角多煤层条带开采三维有限元模拟[J].北京:煤炭学报,1999(6);
[81]张玉卓,于学馥,焦传武。岩层移动的几种计算方法[C].全国首届岩土工程研究生学术讨论会论文集,1986;
[82]张玉卓。岩石力学模糊系统理论与实践[博士论文].北京:北京科技大学,1988:1-30页;
[83]张玉卓,仲惟林,姚建国。岩层移动的位错理论解及边界元计算[J].煤炭学报,1987(6);
[84]张玉卓,仲惟林,姚建国。断层影响下地表移动规律的统计和数值模拟研究[J].煤炭学报,1983(3);
[85]谢和平,陈至达。非线性大变形有限元分析及在岩层移动中的应用[J].中国矿业大学学报,1998(2);
[86]麻凤海,范学理,王泳嘉。岩层移动动态过程的离散单元法分析[J].煤炭学报,1996(8);
[87]邓喀中。开采沉陷中岩体结构效应研究[M].北京:中国矿业大学出版社,1993:1-125页;
[88]于广明。矿山开采沉陷非线性理论与实践导引[M].北京:煤炭工业出版社,1998:1-135页;
[89]李云鹏,王芝银。开采沉陷粘弹塑性损傻模拟分析[J].西安:西安矿业学院学报,1999(9);
[90]胡建成、马建东煤体结构在煤与瓦斯突出预测实践中应用煤炭技术2004,3 102-104页;
[91]肖福坤,秦宪礼等。煤与瓦斯突出过程的突变分析[J]辽宁工程技术大学学报2004 23(4)442-444页;
[92]周世宁,何学秋。煤和瓦斯突出机理的流变假说[J]中国矿业大学学报1990(2):1-9页;
[93]李萍丰。浅谈煤与瓦斯突出机理的假说——二相流体假说[J]煤矿安全1989(11)29-35页;
[94]梁冰,章梦涛,潘一山。煤和瓦斯突出的固流耦合失稳理论[J]煤炭学报1995.20(5)492-496页;
[95]蒋成林,俞启香。煤与瓦斯突出机理的球壳失稳假说[J]煤炭学报1995 16(2)17-25页;
[96]李刚,梁冰。基于突变理论的煤与瓦斯突出预测分析[J]中国科技论文在线2007(9)1-4页
[97]张振海,文延雷。浅析煤体透气性和瓦斯突出的关系山东煤炭科技2007增刊115-116页;
[98]姜福兴。冲击地压及煤与瓦斯突出和透水的微震监测技术煤炭科学技术2007(1)26-27页;
[99]何学秋,刘明举。含瓦斯煤岩电磁辐射动力学[M]徐州:中国矿业大学出版社,1999,15-38页,130-132页;
[100]郑永达。一起煤与瓦斯延期突出事故的探讨[J].煤矿安全,2005,(9):54-56页;
[101] Zeng Wen-chong. Well logging evaluation technique for oil gas preservation reservoir [M]. Beijing; Petorleum Industry Press, 1991:20-40.曾文冲.油气藏储集层测井评价技术[M].北京:石油工业出版社,1991:20-40页;
[102] N. Aronszajn. Theory of Reproducing Kernels. Trans. Amer. Math. Soc.1950,68:P337-404;
[103] Lin Yingzhen, Cui Minggen, ZhengYi, Representation of the exact solution for infinite system of linear equation, Applied Mathematics and Computation, 168(2005)P636-650;
[104] Shaofan Lia, Wing Kam Liua. Moving Least-Square Reproducing Kernel Method Part II: Fourier Analysis. Computer Methods in Applied Mechanics and Engineering. 1996,139(1-4):P159-193 ;
[105] Fazhan Geng ,Minggen Cui, Solving singular nonlinear second-order periodic boundary value problems in the reproducing kernel space,Applied Mathematics and Computation, (2007), doi:10.1016/j. amc.2007.03.016
[106] Minggen Cui, Fazhan Geng, Solving singular two-point boundary value problem in reproducing kernel space , Journal of Computational and Applied Mathematics, 205(2007)P6-15;
[107] Huanmin Yao, Minggen Cui, A new algorithm for a class of singular boundary value problems, Applied Mathematics and Computation, 186(2007)P1183-1191;
[108] Lihong Yang , Minggen Cui , New algorithm for a class of nonlinear intergro-differential equations in the reproducing kernel space, Applied Mathematics and Computation 174(2006)P942-960;
[109] Minggen Cui, Yingzhen Lin, A new method of solving the coefficient inverseproblem of differential equation, cience in China Series A-Mathematics
[110]文松龙,崔明根。W空间中最佳插值逼近算子.计算数学. 1997,(2):177-184页;
[111]杜红。再生核空间中积分和微分方程的求解方法,哈尔滨工业大学博士论文;
[112] Chen Z, Deng N Y. Some algorithms for the convex guadratic programming problem via the ABS approach[J]. Optimization Methods and Software,1997,8(2):P157-170;
[113]高旅端,杨中华。一个求解二次规划的算法[J].北京工业大学学报,1999,25(4):29-34页;
[114] Gao Lü-duan, Yang Zhong-Hua. An Algorithm for Solving Quadratic Programming. Journal of BeiJing Polytechnic University, 1999,25(4):29-34页;
[115]陈志,高旅端。求解大规模稀疏线性方程组得算法[J].北京工业大学学报,2001,27(3):262-265 Chen Zhi,Gao Lü-duan. An Algorithm for Solving Large-scale Sparse Group of Linear Equations. Journal of BeiJing Polytechnic University, 2001,27(3):P262-265;
[116]顾阿伦,孙永广,鲁红。求解线性方程组的投影算法[J].科技导报,2006,24(7):41-43 Gu A-lun, Sun Yong-guang, Lu Hong.Method of Solving Linear Equations Based on Residual Space. Science & Technology Review, 2006,24(7):41-43页;
[117]张艺.线性方程组求解的一个迭代算法[J].宁波大学学报,2001,14(1):51-55 Zhang Yi. An Iterative Method for Linear Equations. Journal of NingBo University, 2001,14(1):51-55页;
[118]张志海,杨建辉。求解线性方程组的一种迭代方法——ART算法的一种改进[J].CT理论与应用研究,1994,3(4):20-23页;
[119]高望东,姜家辉,张勇.求解大型线性稀疏方程组的中心线法[J].工程数学学报,1997,14(1):92-98页;
[120] Gao Wang-dong,Jiang Jia-hui,Zhang Yong. Center-Line Method for Large Unsymmetric Sparse Linear Equations. Journal of Engineering Mathematics,1997,14(1):P92-98;
[121]张学工,关于统计学习理论与支持向量机自动化学报[J],2000(1):32-42页;
[122] (英)克里斯特安尼(Cristianini.N)等,支持向量机导论[M],李国正,王猛,曾华军译,北京电子工业出版社,2004;
[123]赵洪波,冯夏庭.非线性位移时间序列预测的进化支持向量机方法及应用,岩土工程学报[J]. 2003(254):468-471页;
[124]邓乃杨,田英杰,数据挖掘中的新方法——支持向量机[M],科学出版社,2005;
[125]耿德庸,仲惟林。用岩石综合评价系数P确定地表移动的基本参数[J],煤炭学报,1980年12月,第4期;
[126]关于黑龙江省鸡西矿区采煤沉陷区综合治理二期工程实施方案的评估报告,中国国际工程咨询公司文件,咨能源[2003]1263号;
[127]郭爱国。宽条带充填全柱开采条件下的地表沉陷机理及其影响因素[D]:[硕士学位论文],北京:煤炭科学总院北京开采研究所,2006;
[128] Dokka , Roy K . Modern-day tectonic subsidence in coastal Louisiana[J].Geology,2006,34(4):P281-284;
[129]美Vladimir . N.Vapnik Statistical Learning Theory Publishing House of Electronics Industry P401-405;
[130] Humphrey,Tom.Brdesen proposes coal mining limits:State measure would bar such work near streams.Knoxville News-Sentinel,2009(3);
[131] Tripathi,Singh.Impact of post-mining subsidence on nitrogen transformation in southern tropicaldry deciduous forest. Environmental Research,2009,109(3),P258-266;
[132]赵海峰,蒋迪等。ANSYS8.0工程结构实例分析[M].北京:中国铁道出版社,2005。