基于安全监控系统实测数据的瓦斯浓度预测预警研究
|
摘要
瓦斯灾害一直是目前困扰我国煤矿安全生产的最重要因素之一。充分利用煤矿现场的海量安全监测数据并加以有效分析，实现准确、可靠的瓦斯浓度预测，将能够显著提高对于瓦斯灾害的预警能力。瓦斯浓度预测是瓦斯灾害防控的有效手段，也是矿井通风瓦斯安全研究中的重要课题。本文针对煤矿安全监测监控系统实时采集的瓦斯监测数据，研究基于关联分析的瓦斯浓度预测及预警分析方法，开展了以下研究工作：
研究了煤矿瓦斯监测数据的预处理方法。分析了煤矿现场瓦斯监测数据的实际表现特点，通过对瓦斯监测数据进行异常数据替代、缺失数据补齐、数据消噪处理，在尽可能消除随机、不确定性因素对预测分析影响的前提下，研究了瓦斯监测数据希尔伯特—黄变换（HHT）分析方法，通过经验模态分解（EMD）方法将瓦斯浓度时间序列分解成不同瞬时频率固有模态函数（IMF）分量的叠加，依据瓦斯浓度时间序列的瞬时特征选取适合的方法进行预测，以降低预测复杂度并提高预测精度，实现了有效的瓦斯监测数据预处理，并为准确、可靠的瓦斯浓度预测奠定了基础。
研究了监测点瓦斯浓度预测方法。基于瓦斯浓度监测数据预处理，以预测有效度作为预测精度的评估准则；结合灰色关联聚类分析方法和高斯过程回归模型，动态确定瓦斯浓度时间序列样本最佳重构维数；通过将瓦斯浓度样本划分成关联度较强的若干类别，作为虚拟变量表示诸多随机、不确定性因素共同作用下的瓦斯浓度动态特征，以消除这些因素对预测精度的影响；依据瓦斯浓度时间序列HHT分析结果，综合自回归模型（AR）和高斯过程回归（GPR）两种预测，实现监测点瓦斯浓度自适应预测。
研究了工作面多变量瓦斯浓度预测方法。基于瓦斯浓度监测数据预处理，将工作面及其关联巷道监测点瓦斯浓度时间序列视为关联变量，通过贝叶斯网络学习，建立了多变量瓦斯浓度时间序列关联分析模型；应用贝叶斯网络推理提取工作面瓦斯浓度时间序列强关联变量，形成工作面强关联多变量瓦斯浓度时间序列样本组；通过混沌相空间重构方法确定多变量瓦斯浓度时间序列样本重构维数，构建多变量瓦斯浓度预测模型，应用高斯过程回归方法实现工作面瓦斯浓度预测。
研究了基于瓦斯浓度预测的瓦斯预警分析方法。在瓦斯浓度预测的基础上，将预警指标确定为预警基本指标和关联性指标，通过瓦斯浓度监测数据的统计分析确定基本指标阈值；通过瓦斯浓度监测数据关联分析方法分析瓦斯浓度样本的关联特征，确定关联性指标阈值；通过预测值与预警指标阈值的比较进行瓦斯浓度异常分析，划分预警等级，实现动态和精细化的瓦斯预警分析。
研究了瓦斯浓度预测及预警分析应用。通过对宁夏汝箕沟煤矿瓦斯监测数据的应用分析表明，井下重要监测点和主要采掘工作面瓦斯浓度预测精度较高，预测区间有效，预警阈值及结果表达合理，验证了该技术应用于煤矿现场的有效性和适用性。
本文针对煤矿瓦斯监测数据的特点，基于时间序列数学方法的综合应用所提出的瓦斯浓度预测及预警模型，对于煤矿现场的瓦斯浓度预测及预警表现出了良好的适应性和精度控制能力，为煤矿瓦斯灾害的风险预控提供了新的决策支持方法和手段。
Gas disaster has long been a major threat to safe production of coal mines in China. Through effective analysis of gas monitoring data in mine-site to gain accurate and reliable gas concentration prediction, pre-warning of gas abnormal situation can be achieved to enhance the gas safety management in the mine. Based on real-time gas monitoring data, the methods for gas concentration prediction and pre-warning analysis are studied in the dissertation, in which the main research contents are presented as follows:
Study on data pre-processing: The characteristics of real-time monitoring data in a mine is analyzed and data pre-processing is performed, including abnormal data substitution, supplementary treatment of missing data and noise suppression of data, thus to eliminate the potential interference from random and uncertain factors as much as possible. The HHT analysis on the time series of gas concentration data is studied through its decomposition into IMF components with different instantaneous frequencies based on EMD model, and suitable prediction methods are selected to reduce the complexity in prediction, and to improve its accuracy.
Study on the gas concentration prediction at a sensor site: The effectiveness of gas concentration prediction is taken as the criteria of accuracy assessment in prediction performance. The grey cluster relational analysis and GPR are adopted jointly to determine the best sample dimension through reconstruction of the data dynamically. The data is divided into several categories of strong relevance as dummy variables to express the dynamic characteristics of gas concentration influenced by unavoidably random and uncertain factors, so as to relieve the influence exerted by those factors. Based on HHT analysis, AR and GPR are integrated to achieve an adaptive gas concentration prediction at the sensor site.
Study on multi-variable gas concentration prediction in a face region: The monitoring data collected from multi-sensors in a face region is taken as Bayesian network variables, and the multi-variable correlation analysis is performed with Bayesian network learning, and the multivariate time series relating to the gas concentration at the face is formed by Bayesian network inference to extract the most closely related variables, the dimension of multivariate data is determined by chaotic phase space reconstruction, and the multi-variable gas concentration prediction model is established with the gas concentration prediction at the face achieved by GPR application.
Study on the judgment of gas abnormality pre-warning: On the basis of gas concentration prediction, two kinds of pre-warning index, i.e., basic index and correlation index are determined. The threshold of basic index is identified by statistical analysis of the gas concentration data, and the threshold of correlation index is determined by correlation analysis of gas concentration data, the analysis of gas abnormality is conducted by comparing the prediction value of gas concentration with the pre-mentioned thresholds to determine the pre-warning level, thus the dynamic and meticulous gas pre-warning analysis is achieved.
Study on the application of gas prediction and pre-warning: The data collected from various locations and regions in Rujigou Coal Mine is thoroughly analyzed. The results show that the accuracy of prediction is satisfactory, the range of prediction fields is reliable, the pre-warning thresholds are reasonable, which indicates that the gas prediction and pre-warning analysis is verified.
The achievements of gas concentration prediction and pre-warning models are suitable for the real-time analysis of monitoring data, and can provide a new technique to the management and control of gas safety in coal mines.
研究了煤矿瓦斯监测数据的预处理方法。分析了煤矿现场瓦斯监测数据的实际表现特点，通过对瓦斯监测数据进行异常数据替代、缺失数据补齐、数据消噪处理，在尽可能消除随机、不确定性因素对预测分析影响的前提下，研究了瓦斯监测数据希尔伯特—黄变换（HHT）分析方法，通过经验模态分解（EMD）方法将瓦斯浓度时间序列分解成不同瞬时频率固有模态函数（IMF）分量的叠加，依据瓦斯浓度时间序列的瞬时特征选取适合的方法进行预测，以降低预测复杂度并提高预测精度，实现了有效的瓦斯监测数据预处理，并为准确、可靠的瓦斯浓度预测奠定了基础。
研究了监测点瓦斯浓度预测方法。基于瓦斯浓度监测数据预处理，以预测有效度作为预测精度的评估准则；结合灰色关联聚类分析方法和高斯过程回归模型，动态确定瓦斯浓度时间序列样本最佳重构维数；通过将瓦斯浓度样本划分成关联度较强的若干类别，作为虚拟变量表示诸多随机、不确定性因素共同作用下的瓦斯浓度动态特征，以消除这些因素对预测精度的影响；依据瓦斯浓度时间序列HHT分析结果，综合自回归模型（AR）和高斯过程回归（GPR）两种预测，实现监测点瓦斯浓度自适应预测。
研究了工作面多变量瓦斯浓度预测方法。基于瓦斯浓度监测数据预处理，将工作面及其关联巷道监测点瓦斯浓度时间序列视为关联变量，通过贝叶斯网络学习，建立了多变量瓦斯浓度时间序列关联分析模型；应用贝叶斯网络推理提取工作面瓦斯浓度时间序列强关联变量，形成工作面强关联多变量瓦斯浓度时间序列样本组；通过混沌相空间重构方法确定多变量瓦斯浓度时间序列样本重构维数，构建多变量瓦斯浓度预测模型，应用高斯过程回归方法实现工作面瓦斯浓度预测。
研究了基于瓦斯浓度预测的瓦斯预警分析方法。在瓦斯浓度预测的基础上，将预警指标确定为预警基本指标和关联性指标，通过瓦斯浓度监测数据的统计分析确定基本指标阈值；通过瓦斯浓度监测数据关联分析方法分析瓦斯浓度样本的关联特征，确定关联性指标阈值；通过预测值与预警指标阈值的比较进行瓦斯浓度异常分析，划分预警等级，实现动态和精细化的瓦斯预警分析。
研究了瓦斯浓度预测及预警分析应用。通过对宁夏汝箕沟煤矿瓦斯监测数据的应用分析表明，井下重要监测点和主要采掘工作面瓦斯浓度预测精度较高，预测区间有效，预警阈值及结果表达合理，验证了该技术应用于煤矿现场的有效性和适用性。
本文针对煤矿瓦斯监测数据的特点，基于时间序列数学方法的综合应用所提出的瓦斯浓度预测及预警模型，对于煤矿现场的瓦斯浓度预测及预警表现出了良好的适应性和精度控制能力，为煤矿瓦斯灾害的风险预控提供了新的决策支持方法和手段。
Gas disaster has long been a major threat to safe production of coal mines in China. Through effective analysis of gas monitoring data in mine-site to gain accurate and reliable gas concentration prediction, pre-warning of gas abnormal situation can be achieved to enhance the gas safety management in the mine. Based on real-time gas monitoring data, the methods for gas concentration prediction and pre-warning analysis are studied in the dissertation, in which the main research contents are presented as follows:
Study on data pre-processing: The characteristics of real-time monitoring data in a mine is analyzed and data pre-processing is performed, including abnormal data substitution, supplementary treatment of missing data and noise suppression of data, thus to eliminate the potential interference from random and uncertain factors as much as possible. The HHT analysis on the time series of gas concentration data is studied through its decomposition into IMF components with different instantaneous frequencies based on EMD model, and suitable prediction methods are selected to reduce the complexity in prediction, and to improve its accuracy.
Study on the gas concentration prediction at a sensor site: The effectiveness of gas concentration prediction is taken as the criteria of accuracy assessment in prediction performance. The grey cluster relational analysis and GPR are adopted jointly to determine the best sample dimension through reconstruction of the data dynamically. The data is divided into several categories of strong relevance as dummy variables to express the dynamic characteristics of gas concentration influenced by unavoidably random and uncertain factors, so as to relieve the influence exerted by those factors. Based on HHT analysis, AR and GPR are integrated to achieve an adaptive gas concentration prediction at the sensor site.
Study on multi-variable gas concentration prediction in a face region: The monitoring data collected from multi-sensors in a face region is taken as Bayesian network variables, and the multi-variable correlation analysis is performed with Bayesian network learning, and the multivariate time series relating to the gas concentration at the face is formed by Bayesian network inference to extract the most closely related variables, the dimension of multivariate data is determined by chaotic phase space reconstruction, and the multi-variable gas concentration prediction model is established with the gas concentration prediction at the face achieved by GPR application.
Study on the judgment of gas abnormality pre-warning: On the basis of gas concentration prediction, two kinds of pre-warning index, i.e., basic index and correlation index are determined. The threshold of basic index is identified by statistical analysis of the gas concentration data, and the threshold of correlation index is determined by correlation analysis of gas concentration data, the analysis of gas abnormality is conducted by comparing the prediction value of gas concentration with the pre-mentioned thresholds to determine the pre-warning level, thus the dynamic and meticulous gas pre-warning analysis is achieved.
Study on the application of gas prediction and pre-warning: The data collected from various locations and regions in Rujigou Coal Mine is thoroughly analyzed. The results show that the accuracy of prediction is satisfactory, the range of prediction fields is reliable, the pre-warning thresholds are reasonable, which indicates that the gas prediction and pre-warning analysis is verified.
The achievements of gas concentration prediction and pre-warning models are suitable for the real-time analysis of monitoring data, and can provide a new technique to the management and control of gas safety in coal mines.
引文
[1]刘星魁,谢金亮.煤矿安全生产现状及对策探讨[J].煤炭技术,2008,27(1):139~140.
[2]黄盛初,刘文革,徐亮.中国煤炭行业海外发展战略研究[J].中国煤炭,2010,36(7):11~14.
[3]陈娟,赵耀江.近十年来我国煤矿事故统计分析及启示[J].煤炭工程,2012,(3):137~139.
[4]康淑云,李江.坚持科学发展安全发展推进煤矿安全生产形势稳定好转—访国家安全监管总局副局长兼国家煤矿安全监察局局长赵铁锤[J].煤炭经济研究,2012,32(2):13~17.
[5]李树刚,林海飞,成连华,等.我国煤矿瓦斯灾害事故发生原因及防治对策[A].中国职业安全健康协会2010年学术年会论文集[C].2010.
[6]马丕梁,范启炜.我国煤矿抽放瓦斯现状及展望[J].中国煤炭,2004,30(2):5~7.
[7]胡方坤,杨林青,蒋谷硕.探析煤矿瓦斯爆炸的原因及其防治措施[J].煤炭技术,2010,29(5):226~227.
[8]王建政.构建本质安全化煤矿刍议[J].中国矿业大学学报（社会科学版）,2007,(2):76~78.
[9]彭立军.矿井监测监控的发展[J].科技情报开发与经济,2003,(4):205~206.
[10]国家煤矿安全监察局.国家安全监管总局国家煤矿安监局关于近期几起煤矿事故的通报[J].国家安全生产监督管理总局国家煤矿安全监察局公告,2010,(1):22~25.
[11]汪云甲,杨敏,张克.数字矿山与煤矿瓦斯监测及预警[J].地理信息世界,2008,(5):26~31.
[12]宋冬冬.基于FIS的煤矿智能安检信息管理系统的研究[D].保定:河北农业大学,2008.
[13]刘源骏,袁梅,马科伟.煤矿安全监测监控系统探讨[J].矿业工程,2010,8(2):49~51.
[14]刘祖德,梁开水.煤矿通风瓦斯信息管理系统的设计与实现[J].工矿自动化,2008,(3):94~96.
[15]刘勇燕.基于网格的矿井通风计算并行处理模式研究[D].西安:西安科技大学,2003.
[16]倪景峰.矿井通风仿真系统可视化研究[D].阜新:辽宁工程技术大学,2004.
[17]王从陆.复杂通风网络解算及参数可调度研究[D].长沙:中南大学,2003.
[18]胡永梅.煤矿瓦斯事故预测分析系统[D].淮南:安徽理工大学,2004.
[19]杜学胜,杨勇,陈秀珍,等.基于Web-GIS的矿井通风安全信息系统[J].煤矿安全,2005,36(10):31~34.
[20]张国建.掘进工作面智能通风控制系统的设计与应用[J].煤炭科学技术,2008,3(5):76~79.
[21]付华.煤矿瓦斯灾害特征提取与信息融合技术研究[D].阜新:辽宁工程技术大学,2006.
[22]付华,王雨虹.基于数据挖掘的瓦斯灾害信息融合模型的研究[J].传感器与微系统,2008,27(1):52~54.
[23]齐冀,彭泓,王涛.基于模糊信息融合的矿井火灾监测系统研究[J].煤矿机电,2009,(3):34~37.
[24] N.Lili, I.Obradovi, A.Cvjeti. An intelligent hybrid system for surface coal minesafety analysis[J]. Engineering Applications of Artificial Intelligence,2010,23(4):453~462.
[25]周静.矿井通风系统可靠性研究[D].阜新:辽宁工程技术大学,2002.
[26]王洪德,刘贞堂.矿井通风网络可靠性的定量分析与评价[J].中国矿业大学学报,2007,36(3):371~374.
[27]王洪德.基于粗集—神经网络的矿井通风系统可靠性理论与方法研究[D].阜新:辽宁工程技术大学,2004.
[28]何金灿.信息融合技术在矿井通风系统安全评价中的应用研究[D].南京:河海大学,2006.
[29] Jia Jinzhang, Zang Guangwei, Qian Zhou, et al. A new algorithm for calculatingventilation network reliability based on truncation error theory and networksimplification[J]. Procedia Earth and Planetary Science,2009,1(1):169~172.
[30] Jia Tinggui, Liu Jian. Stability of mine ventilation system based on multiple regressionanalysis[J]. Mining Science and Technology,2009,19(4):463~466.
[31]刘泽功.通风安全工程中的计算机模拟技术及发展[A].中国煤炭协会第六届青年科学技术研讨会论文集[C].2000.
[32]常心坦.矿井火灾通风的模拟计算[J].煤矿安全,1991,(4):23~29.
[33] Zhou Fubao, Wang Deming, Zhou Yan. Experimental Study on air flow reversal withinbypass branch during mine Fire[J]. Journal of China University of Mining&Technology,2001,11(2):95~99.
[34] E.K.Stefopoulos, D.G.Damigos. Design of emergency ventilation system for anunderground storage facility[J]. Tunneling and Underground Space Technology,2007,22:293~302.
[35] J.Maiti, V.V.Khanzode. Development of a relative risk model for roof and side fall fatalaccidents in underground coal mines in India[J]. Safety Science,2009,47:1068~1076.
[36] S.K.Palei, S.K.Das. Sensitivity analysis of support safety factor for predicting theeffects of contributing[J]. International Journal of Coal Geology,2008,75:241~247.
[37] S.D.S.Gillies. Probabilistic method for mine heat prediction[J]. Soc of MiningEngineers of AIME,1987:145~151.
[38] Roszczynialski, Wiodzimierz. Airflow rates in mine headings and their variance atrandom variation of aerodynamic drag branches of mine ventilation network[J].1988,33(4):441~453.
[39] M.T.Parra, J.M.Villafruela, F.Castro, et al. Numerical and experimental analysis ofdifferent ventilation systems in deep mines[J]. Building and Environment,2006,41(2):87~93.
[40] M.B.Wold, L.D.Connell, S.K.Choi. The role of spatial variability in coal seamparameters on gas outburst behavior during coal mining[J]. International Journal ofCoal Geology,2008,75:1~14.
[41] M.Sari, A.S.Selcuk, C.Karpuz, et al. Stochastic modeling of accident risks associatedwith an underground coal mine in Turkey[J]. Safety Science,2009,47:78~87.
[42]李高正.煤矿监控系统瓦斯数据分析技术研究[J].煤炭科学技术,2008,36(4):58~60.
[43]张强,常心坦,许晋源.矿井风量监测异常值研究的模型与算法[J].西安矿业学院学报,1998,18(4):301~304.
[44]魏引尚.基于概率统计的通风巷道瓦斯积聚危险性分析研究[D].西安:西安科技大学,2004.
[45]张进.矿井瓦斯涌出及瓦斯流动预测的统计研究[D].西安:西安科技大学,2005.
[46]赵龙.基于控制分区瓦斯监测数据可信度与分析[D].西安:西安科技大学,2007.
[47]王俭.基于安全分区的通风瓦斯风险控制研究[D].西安:西安科技大学,2008.
[48]王红刚,吴奉亮,常心坦.基于蒙特卡洛方法的瓦斯测值分析模型[J].工矿自动化,2009,(4):52~55.
[49]杨叔子,吴雅,轩建平,等.时间序列分析的工程应用（第二版）[M].武汉:华中科技大学出版社,2007.
[50]施仁杰,卢科学.时间序列分析引论[M].西安:西安电子科技大学出版社,1988.
[51]杨位钦,顾岚.时间序列分析与动态数据建模[M].北京:北京工业学院出版社,1989.
[52] M.L.Padgett, U.Desail. Neural network applications[J]. Proceedings of SPIE-TheInternational Society for Optical Engineering,1993,1721:5~9.
[53] R.Rosipal, M.Koska, I.Farkas. Prediction of chaotic time-series with a resource-allocating RBF network[J]. Neural processing letters,1998,(7):185~197.
[54]周波,石爱国,蔡烽,等.基于多尺度分析和神经网络的时间序列预报[J].计算机应用与软件,2005,22(2):93~94.
[55]殷佳.基于小波神经网络的混沌时间序列建模研究[D].大连:大连理工大学,2007.
[56]谢乃明.序列算子与灰色预测模型研究[D].南京:南京航空航天大学,2005.
[57]王忠桃.灰色预测模型相关技术研究[D].成都:西南交通大学,2005.
[58]张军.灰色预测模型的改进及其应用[D].西安:西安理工大学,2008.
[59]蔡岩.基于灰色预测模型的短期交通流预测研究[D].成都:西南交通大学,2006.
[60]刘金英.灰色预测理论与评价方法在水环境中的应用研究[D].长春:吉林大学,2004.
[61]韩敏.混沌时间序列预测理论与方法[M].北京:中国水利水电出版社,2007.
[62]李天舒.混沌时间序列分析方法研究及其应用[D].哈尔滨:哈尔滨工程大学,2006.
[63]殷礼胜.交通流量时间序列混沌特性分析及预测研究[D].重庆:重庆大学,2007.
[64]刘立霞.多变量金融时间序列的非线性检验及重构研究[D].天津:天津大学,2007.
[65] Cao Liangyue, M.Alistair, J.Kevin. Dynamics from multivariate time series[J]. PhysicaD: Nonlinear Phenomena,1998,121(2):75~88.
[66]徐恺.基于支持向量机的股指时间序列预测[D].成都:西南交通大学,2008.
[67]岳敏.基于BBN-SVM和PCV的多变量时间序列预测算法研究[D].兰州:兰州大学,2010.
[68]李亚娇.基于现代分析技术的水文时间序列预测方法研究[D].西安:西安理工大学,2007.
[69]孟庆芳.非线性系统时间序列分析方法及应用研究[D].济南:山东大学,2008.
[70] Wu Dongmei, Zhao Yuemin, Cheng Yuanping, et al. DP index with different gascompositions for instantaneous outburst prediction in coal mines[J]. Mining Science andTechnology,2010,20:723~726.
[71]王汉斌.煤与瓦斯突出的分形预测理论及应用[D].太原:太原理工大学,2009.
[72]李刚.瓦斯浓度的分形分析与混沌预测模型研究[D].北京:中国矿业大学,2004.
[73]金芳勇.基于分形—混沌理论的煤与瓦斯突出预测研究[D].合肥:安徽理工大学,2006.
[74] Li Sheng, Zhang Hongwei. Pattern recognition and forecast of coal and gas outburst [J].Journal of China University of Mining&Technology,2005,15(3):251~254.
[75]陈祖云.煤与瓦斯突出前兆的非线性预测及支持向量机识别研究[D].徐州:中国矿业大学,2009.
[76] Qiao Meiying, Ma Xiaoping, Lan Jianyi, et al. Time-series gas prediction model usingLS-SVR within a Bayesian framework[J]. Mining Science and Technology,2011,21:153~157.
[77] Wang Chao, Wang Enyuan, Xu Jiankun, et al. Bayesian discriminant analysis forprediction of coal and gas outbursts and application[J]. Mining Science and Technology,2010,20(4):520~523.
[78]潘结南,陈江峰,徐文鹏. R/S分析及矿井瓦斯涌出量的分形预测[J].煤田地质与勘探,2001,(3):14~15.
[79] Xu Changkai, Wang Yaocai, Wang Junwei. Research on forecast technology of mine gasemission based on fuzzy data mining[J]. Journal of China University of Mining&Technology,2004,14(2):174~178.
[80]伍爱友,田云丽,宋译,等.灰色系统理论在矿井瓦斯涌出量预测中的应用[J].煤炭学报,2005,30(5):389~392.
[81]陶云奇,许江,李树春.改进的灰色马尔柯夫模型预测采煤工作面瓦斯涌出量[J].煤炭学报,2007,32(4):391~395.
[82] Pan Jienan, Meng Zhaoping, Liu Yachuan. Grey smoothing model for predicting minegas emission[J]. Journal of China University of Mining&Technology,2003,13(1):76~78.
[83]黄文标,施式亮.基于改进Lyapunov指数的瓦斯涌出时间序列预测[J].煤炭学报,2009,34(12):1666~1668.
[84]何利文.煤矿回采工作面瓦斯涌出非线性特性分析及预测仿真理论研究[D].长沙：中南大学,2009.
[85]何华刚,胡敏涛.基于改进CC方法的瓦斯涌出混沌预测[J].矿业研究与开发,2009,29(4):69~71.
[86]施式亮,宋译,何利文.矿井掘进工作面瓦斯涌出混沌特性判别研究[J].煤炭学报,2006,31(6):702~705.
[87] C. zgen, Karacan. Modeling and prediction of ventilation methane emissions ofU.S.longwall mines using supervised artificial neural networks[J]. International Journalof Coal Geology,2008,73:371~387.
[88]洪菁,赵毅,陈强.基于模糊粗糙集的瓦斯涌出量预测模型的研究[J].微计算机信息,2007,23(2):259~261.
[89] Pan Yumin, Zhang Xiaoyu, Xue Pengqian. The amount prediction of gas emitted viawavelet neural network with grey correlation analysis[A]. Proceedings2010SixthInternational Conference on Natural Computation[C].2010.
[90] Chen Xiang, Cai Weihua. Wavelet neural net based work face gas emissionprediction[A].2009IEEE International Conference on Intelligent Computing andIntelligent Systems[C].2009.
[91] Wang Jianping, Huang Hongxia, Li Hongbiao, et al. Prediction of mine gas emissionrate based on the SVM model[A].2008Chinese Control Conference[C].2008.
[92] Ning Yuncai, Chen Xiang. Coal face gas emission prediction based on support vectormachine[A]. Proceedings of the2009International Conference on Artificial Intelligenceand Computational Intelligence[C].2009.
[93]黄为勇,童敏明,任子晖.基于SVM的瓦斯涌出量非线性组合预测方法[J].中国矿业大学学报,2009,38(2):235~238.
[94]马文涛.基于WT与GALSSVM的瓦斯涌出量预测[J].采矿与安全工程学报,2009,26(4):524~527.
[95] Wang Changlong, Fu Weihua. Gas emission rate prediction in fully-mechanizedexcavated faces based on support vector machine[A]. Proceedings of the20093rdInternational Symposium on Intelligent Information Technology Application Workshops
[C].2009.
[96]郭德勇,郑茂杰,鞠传磊,等.采煤工作面瓦斯涌出量预测逐步回归方法[J].北京科技大学学报,2009,31(9):1095~1097.
[97]蔡武,袁莎莎,戚洋.基于多元线性回归分析法预测矿井瓦斯涌出量[J].煤矿安全,2010,(1):91~94.
[98]李苏旺.时间序列数据建模及其在瓦斯预测中的应用研究[D].太原:太原理工大学,2003.
[99]杨胜远,李金林,杨东朋. ARMA模型在瓦斯浓度预测中的应用[J].中国煤炭,2008,34(6):14~16.
[100]吕品,马云歌,周心权.上隅角瓦斯浓度动态预测模型的研究及应用[J].煤炭学报,2006,31(4):462~465.
[101]Qu Zhiming, Liang Xiaoying. Application of grey relation clustering and CGNN in gasconcentration prediction in top corner of coal mine[A].2009International Conferenceon Computational Intelligence and Natural Computing[C].2009.
[102]段霄鹏.基于商空间的煤矿瓦斯数据挖掘研究[D].太原:太原理工大学,2010.
[103]高莉,胡延军,于洪珍.基于W-RBF的瓦斯时间序列预测方法[D].煤炭学报,2008,33(1):68~70.
[104]Gao Li, Yu Hongzhen. Prediction of gas emission based on information fusion andchaotic time series [J]. Journal of China University of Mining&Technology,2006,16(1):94~96.
[105]施式亮,何利文,宋译,等.基于混沌与神经网络耦合模型的回采工作面瓦斯涌出时序分析与预侧[A].中国职业安全健康协会2008年学术年会论文集[C].2008.
[106]王其军,程久龙.基于免疫神经网络模型的瓦斯浓度智能预测[J].煤炭学报,2008,33(6):666~668.
[107]Shao Yuxiang, Zhang Dongmei. Mine forecast based on genetic annealing neuralnetwork[A]. Proceedings2009International Conference on Information Technology andComputer Science[C].2009.
[108]朱宇.构造神经网络在瓦斯时间序列预测中的应用[D].太原:太原理工大学,2010.
[109]白峻尧.基于SVM的瓦斯涌出的自学习模型研究应用[D].西安:西安科技大学,2006.
[110]Qian Jiansheng, Cheng Jian, Guo Yinan. A novel multiple support vector machinesarchitecture for chaotic time series prediction[A]. Advances in Natural Computation:Second International Conference[C].2006.
[111]Cheng Jian, Qian Jiansheng, Niu Guangdong, et al. Gas concentration forecasting basedon support vector regression in correlation space via KPCA[A]. Advances in NeuralNetworks:6th International Symposium on Neural Networks[C].2009.
[112]王泉夫,赵小虎,王刚.在线最小二乘支持向量机在瓦斯预测中的研究与应用[A].2010（沈阳）国际安全科学与技术学术研讨会论文集[C].2010.
[113]Zhao Xiaohu, Wang Gang, Zhao Keke, et al. On-line least squares support vectormachine algorithm in gas prediction [J]. Mining Science and Technology,2009,19(2):194~198.
[114]Zhao Xiaohu, Zhao Keke. Study of an improved online least squares support vectormachine algorithm and its application in gas prediction[A].2008Fourth InternationalConference on Natural Computation[C].2008.
[115]崔小彦,赵国强.混沌预测在井下瓦斯浓度监测的应用[J].辽宁工程技术大学学报（自然科学版）,2008,27(5):185~186.
[116]程健,白静宜,钱建生,等.基于混沌时间序列的煤矿瓦斯浓度短期预测[J].中国矿业大学学报,2008,37(2):231~234.
[117]刘婷婷,史久根,韩江洪.基于SVM的瓦斯体积分数混沌时间序列预测[J].合肥工业大学学报（自然科学版）,2009,32(8):1150~1153.
[118]杜晓坤.改进的混沌预测方法在瓦斯监测中的应用[J].微计算机信息,2010,26(11):190~191.
[119]赵金宪,于光华.瓦斯浓度预测的混沌时序RBF神经网络模型[J].黑龙江科技学院学报[J].2010,2(2):131~134.
[120]Zhao Jinxian, Jin Hongzhang, Yu Guanghua. Coalmine gas concentration forecastingbased on chaotic theory and neural network model[A]. Proceedings of the ThirdInternational Conference on Information and Computing Science[C].2010.
[121]张剑英,许徽,陈娟,等.基于粒子群优化的支持向量机在瓦斯浓度预测中的应用研究[J].工矿自动化,2010,(10):32~35.
[122]邵良杉.基于粗糙集理论的煤矿瓦斯预测技术[J].煤炭学报,2009,34(3):371~374.
[123]Shao Liangshan, Fu Guixiang. Disaster prediction of coal mine gas based on datamining[J]. Journal of Coal Science&Engineering,2008,(3):458~463.
[124]Zhang Yueqin, Duan Xiaopeng. Based on cluster cover algorithm in coal mine gasforecast application[A]. Proceedings of the2010International Conference on IntelligentComputation Technology and Automation[C].2010.
[125]Liu Yujun, Zhang Yueqin, Zhu Yu. A constructive neural network learning method basedon quotient space and its application in coal mine gas prediction[A].2010InternationalConference on Intelligent Computing and Cognitive Informatics[C].2010.
[126]许徽,张剑英,陈娟,等.基于分段线性方法的瓦斯浓度时间序列模式表示[J].工矿自动化,2010,(8):41~44.
[127]管河山.金融多元时间序列挖掘方法研究与应用[D].厦门:厦门大学,2008.
[128]方子良,高骏,王军辉.多因素时间序列法的研究[J].南京理工大学学报,2003,27(3):298~300.
[129]隰熙,蒋艳,李臣学.多属性决策的时间序列数据转换方法[J].统计与决策,2007,(9):9~10.
[130]李松臣.多元非线性非平稳时间序列的建模方法研究[D].天津:天津大学,2007.
[131]李汉东.多变量时间序列波动持续性研究[D].天津:天津大学,2000.
[132]陆嘉佳.多变量时间序列模型的参数估计及其实证检验[D].上海:华东师范大学,2008.
[133]王广江,金世国.多元随机时间序列参数估计的多尺度方法[J].科技信息,2010,(10):1~3.
[134]卢山,王海燕.多变量时间序列相空间重构的优化[J].系统工程理论方法应用,2006,15(3):234~236.
[135]王海燕,盛昭瀚,张进.多变量时间序列复杂系统的相空间重构[J].东南大学学报（自然科学版）,2003,31(3):115~118.
[136]刘立霞.多变量金融时间序列的非线性检验及重构研究[D].天津:天津大学,2007.
[137]樊重俊. Bayes多元时间序列分析方法及其应用[J].系统管理学报,2010,19(2):191~194.
[138]方芬.多变量混沌时间序列预测及其在股票市场中的应用[D].南京:东南大学,2006.
[139]方芬.多变量混沌时间序列Volterra自适应实时预测[J].系统工程与电子技术,2009,31(10):2476~2479.
[140]陈涛.多变量时间序列的重构与预测方法[J].统计与决策,2009,(14):31~33.
[141]王一颉.多元混沌时间序列相关性分析及预测方法研究[D].大连:大连理工大学,2008.
[142]魏茹.多元混沌时间序列的变量选择及预测方法研究[D].大连:大连理工大学,2007.
[143]苏变萍,曹艳平,王婷.多因素时间序列的灰色预测模型[J].西安建筑科技大学学报,2007,39(2):289~292.
[144]贾真.神经网络在煤矿瓦斯预警系统中的应用研究[D].长春:长春工业大学,2007.
[145]Liu Xiaosheng, Huang Xiaobin. Research on pre-warning expert system of coal minegas safety based on object-oriented[A].2008IEEE International Symposium onKnowledge Acquisition and Modeling Workshop[C].2008.
[146]熊廷伟.煤矿瓦斯爆炸预警技术研究[D].重庆:重庆大学,2005.
[147]李华.矿井掘进瓦斯爆炸实时智能预警监控系统[D].西安:西安科技大学,2005.
[148]牛聚粉.基于Mapx的煤与瓦斯预测预警技术研究[D].北京:中国地质大学,2006.
[149]Qian Jiansheng, Yin Hongsheng, Liu Xiurong, et al. Data processing model of coalminegas early-warning system[J]. Journal of China University of Mining and Technology,2007,17(10):20~24.
[150]Ma Xianmin. Application of data fusion theory in coal gas fire prediction system[A].2008International Conference on Intelligent Computation Technology and Automation
[C].2008.
[151]Lin Jipeng. Pre-alarm system of coal mine based on ICA and kalman filter[A].2010Sixth International Conference on Natural Computation[C].2010.
[152]Xie Guomin, Fu Hua, Wang Shiyun. Study on early warning of gas in coal mine basedon extension data mining[A].20102nd International Conference on EducationTechnology and Computer[C].2010.
[153]Song Jinxing, Liu Yufang. Study on the mine gas disaster prevention system by GIS[A].20102nd Conference on Environmental Science and Information ApplicationTechnology[C].2010.
[154]钟震宇.小煤矿通风瓦斯集群监控系统的研究[D].武汉:中国地质大学,2006.
[155]杨禹华,钟震宇,蔡康旭.基于模糊模式识别的瓦斯含量指标异常预警技术[J].中国安全科学学报,2007,17(9):172~175.
[156]邵良杉,付贵祥.基于数据融合理论的煤矿瓦斯动态预测技术[J].煤炭学报,2008,33(5):551~554.
[157]Cao Shugang, Liu Yanbao, Wang Yanping. A forecasting and forewarning model formethane hazard in working face of coal mine based on LS-SVM[J]. Journal of ChinaUniversity of Mining and Technology,2008,18(2):172~176.
[158]黄为勇.基于支持向量机数据融合的矿井瓦斯预警技术研究[D].徐州:中国矿业大学,2009.
[159]李骥平.商空间理论在煤矿预警中的应用[D].太原:太原理工大学,2010.
[160]王沁.时间序列分析及其应用[M].成都:西南交通大学出版社,2008.
[161]R.A.Davis. Introduction to time series and forecasting[M]. Beijing:Post&TelecomPress,2009.
[162]李颖.时间序列指数平滑算法的改进研究[D].阜新:辽宁工程技术大学,2009.
[163]D.B.Percival, A.T.Walden. Wavelet methods for time series analysis[M]. Beijing:ChinaMachine Press,2006.
[164]李智.小波理论与经济金融时序应用研究[D].厦门:厦门大学,2007.
[165]葛哲学,沙威.小波分析理论与MATLAB R2007实现[M].北京:电子工业出版社,2007.
[166]胡昌华,张军波,夏军,等.基于MATLAB的系统分析与设计—小波分析[M].西安:西安电子科技大学出版社,2000.
[167]李弼程,罗建书.小波分析及其应用[M].北京:电子工业出版社,2005.
[168]文莉,刘正士,葛运建.小波去噪的几种方法[J].合肥工业大学学报（自然科学版）,2002,25(2):167~172.
[169]姚恩营,周玉国,孙国栋,等.基于多尺度小波分解的时间序列预测方法研究[J].计算机时代,2009,(1):4~6.
[170]Z.K.Peng, W.Peter, F.L.Chu. An improved Hilbert-Huang transform and its applicationsin vibration signal analysis[J]. Journal of Sound and Vibration,2005,286:187~205.
[171]王慧. HHT方法及其若干应用研究[D].合肥:合肥工业大学,2009.
[172]N.E.Huang, Z.Shen, S.R.Long, et a1.The empirical mode decomposition and the Hilbertspectrum for non-linear and non-stationary time series analysis[J]. Proceedings of theRoyal Society of London,1998,454(1):903~995.
[173]陈一贤. HHT分析方法[D].杭州:浙江大学,2007.
[174]N.E.Huang, M.L.Wu, S.R.Long, et al. A confidence limit for the empirical modedecomposition and Hilbert spectrum analysis[J]. Proceedings of the Royal Society ofLondon,2003,459:2317~2345.
[175]Q.Chen, N.E.Huang, S.Riemenschneider, et al. A B-spline approach for empirical modedecomposition[J]. Adv. Compute. Math,2006,20:18~734.
[176]N.E.Huang, Z.Shen, S.R.Long．A new view of nonlinear water waves：the Hilbertspectrum[J]. Annual Review of Fluid Mechanics,1999,31:417~457．
[177]S.R.Qin, Y.M.Zhong. A new envelope algorithm of Hilbert-Huang transform[J].Mechanical System and Signal Processing,2006,20:1941~1952.
[178]董丁稳,李树刚,常心坦,等.基于HHT方法的矿井瓦斯体积分数预测[J].中国安全科学学报,2011,21(9):100~105.
[179]谷川,秦世伟.基于预测有效度的变形数据组合预测[J].大地测量与地球动力学,2008,28(5):73~76.
[180]陈华友.基于预测有效度的组合预测模型近似求解[J].安徽大学学报（自然科学版）,2003,27(3):7~10.
[181]张春明.灰色关联聚类的最大支撑树方法[J].山东交通学院学报,2004,12(2):72~75.
[182]廖向旗,李欣然,李培强,等.基于灰色关联聚类的负荷特性分类[J].电力科学与技术学报,2007,22(2):28~34.
[183]许秀莉.灰色关联、聚类、预测的改进及应用[D].厦门:厦门大学,2001.
[184]刘家学.时序多指标决策的灰色关联分析法[J].运筹与管理,1997,6(3):6~10.
[185]董丁稳,李树刚,常心坦,等.瓦斯浓度区间预测的灰色聚类与高斯过程模型[J].中国安全科学学报,2011,21(5):40~45.
[186]沈赟.基于高斯过程的时间序列分析[D].上海:上海交通大学,2009.
[187]R.Turner, M.P.Deisenroth, C.E.Rasmussen. State-space inference and learning withGaussian processes[A].13th International Conferenceon Artificial Intelligence andStatistics[C].2010.
[188]G.Pillonetto, G.De.Nicolao. A new kernel-based approach for linear systemidentification[J]. Automatica,2010,46:81~93.
[189]C.E.Rasmussen. Advances in Gaussian processes[A]. Proceedings of the NeuralInformation Processing Systems Conference[C]. the MIT Press,2006.
[190]J.Ko, D.Fox. Learning GP-BayesFilters via Gaussian process latent variable models[J].Autonomous Robots,2009,27:75~90.
[191]Dong Dingwen, Zhang Taowei, Li Shugang, et al. Gaussian process model for timeseries analysis of mine gas emission[A].2010International Conference on InformationSecurity and Artificial Intelligence[C].2010.
[192]C.E.Rasmussen, C.K.I.Williams. Gaussian processes for machine learning[M]. The MITPress,2006.
[193]G.Gregor i, G.Lightbody. Gaussian process approach for modelling of nonlinearsystems[J]. Engineering Applications of Artificial Intelligence,2009,22:522~533.
[194]G.Gregor i, G.Lightbody. Nonlinear system identification: From multiple-modelnetworks to Gaussian processes[J].Engineering Applications of Artificial Intelligence,2008,21:1035~1055.
[195]M.Deisenroth, C.E.Rasmussen, J.Peters. Gaussian process dynamic programming[J].Neurocomputing,2009,72:1508~1524.
[196]张连文,郭海鹏.贝叶斯网引论[M].北京:科学出版社,2006.
[197]Dong Dingwen, Li Shugang, Chang Xintan. Method for risk analysis of gas explosionbased on Bayesian networks[A].2010International Symposium on Safety Science andTechnology[C].2010.
[198]Dong Dingwen, Zhang Jianrang, Zhao Huajie, et al. The method for risk analysis andevaluation of hazards in coal mine based on Bayesian networks[A].2009China-JapanSymposium on Safety Management Theory and Practice[C].2010.
[199]M.E.Borsuk. Bayesian Networks[J]. Encyclopedia of Ecology,2008,(3):307~317.
[200]J.PERAL. Fusion, propagation and structuring in belief[J]. Artificial intelligence,1986,29(3):241~248.
[201]J.PERAL. Evidential reasoning using stochastic simulation of casual models[J].Artificial intelligence,1987,32(2):245~257.
[202]K.P.Murphy. Dynamic Bayesian networks: representation, inference and learning[D].Berkeley: University of California,2002.
[203]C.Simon, P.Weber, A.Evsukoff. Bayesian networks inference algorithm to implementDempster Shafer theory in reliability analysis[J]. Reliability Engineering and SystemSafety,2008,93(7):950~963.
[204]G.Cooper. Computational complexity of probabilistic inference using Bayesian beliefnetworks[J].Artificial Intelligence,1990,42(2):393~405.
[205]黄友平.贝叶斯网络研究[D].北京:中国科学院计算技术研究所,2005.
[206]董丁稳,李树刚,常心坦,等.工作面多变量瓦斯浓度时间序列预测模型[J].采矿与安全工程学报,2012,29(1):135~139.
[207]B.Samanta. Prediction of chaotic time series using computational intelligence[J]. ExpertSystems with Applications,2011,38(9):11406~11411.
[208]Xu Pengcheng. Differential phase space reconstructed for chaotic time series[J].Applied Mathematical Modeling,2009,33(2):999~1013.
[2]黄盛初,刘文革,徐亮.中国煤炭行业海外发展战略研究[J].中国煤炭,2010,36(7):11~14.
[3]陈娟,赵耀江.近十年来我国煤矿事故统计分析及启示[J].煤炭工程,2012,(3):137~139.
[4]康淑云,李江.坚持科学发展安全发展推进煤矿安全生产形势稳定好转—访国家安全监管总局副局长兼国家煤矿安全监察局局长赵铁锤[J].煤炭经济研究,2012,32(2):13~17.
[5]李树刚,林海飞,成连华,等.我国煤矿瓦斯灾害事故发生原因及防治对策[A].中国职业安全健康协会2010年学术年会论文集[C].2010.
[6]马丕梁,范启炜.我国煤矿抽放瓦斯现状及展望[J].中国煤炭,2004,30(2):5~7.
[7]胡方坤,杨林青,蒋谷硕.探析煤矿瓦斯爆炸的原因及其防治措施[J].煤炭技术,2010,29(5):226~227.
[8]王建政.构建本质安全化煤矿刍议[J].中国矿业大学学报（社会科学版）,2007,(2):76~78.
[9]彭立军.矿井监测监控的发展[J].科技情报开发与经济,2003,(4):205~206.
[10]国家煤矿安全监察局.国家安全监管总局国家煤矿安监局关于近期几起煤矿事故的通报[J].国家安全生产监督管理总局国家煤矿安全监察局公告,2010,(1):22~25.
[11]汪云甲,杨敏,张克.数字矿山与煤矿瓦斯监测及预警[J].地理信息世界,2008,(5):26~31.
[12]宋冬冬.基于FIS的煤矿智能安检信息管理系统的研究[D].保定:河北农业大学,2008.
[13]刘源骏,袁梅,马科伟.煤矿安全监测监控系统探讨[J].矿业工程,2010,8(2):49~51.
[14]刘祖德,梁开水.煤矿通风瓦斯信息管理系统的设计与实现[J].工矿自动化,2008,(3):94~96.
[15]刘勇燕.基于网格的矿井通风计算并行处理模式研究[D].西安:西安科技大学,2003.
[16]倪景峰.矿井通风仿真系统可视化研究[D].阜新:辽宁工程技术大学,2004.
[17]王从陆.复杂通风网络解算及参数可调度研究[D].长沙:中南大学,2003.
[18]胡永梅.煤矿瓦斯事故预测分析系统[D].淮南:安徽理工大学,2004.
[19]杜学胜,杨勇,陈秀珍,等.基于Web-GIS的矿井通风安全信息系统[J].煤矿安全,2005,36(10):31~34.
[20]张国建.掘进工作面智能通风控制系统的设计与应用[J].煤炭科学技术,2008,3(5):76~79.
[21]付华.煤矿瓦斯灾害特征提取与信息融合技术研究[D].阜新:辽宁工程技术大学,2006.
[22]付华,王雨虹.基于数据挖掘的瓦斯灾害信息融合模型的研究[J].传感器与微系统,2008,27(1):52~54.
[23]齐冀,彭泓,王涛.基于模糊信息融合的矿井火灾监测系统研究[J].煤矿机电,2009,(3):34~37.
[24] N.Lili, I.Obradovi, A.Cvjeti. An intelligent hybrid system for surface coal minesafety analysis[J]. Engineering Applications of Artificial Intelligence,2010,23(4):453~462.
[25]周静.矿井通风系统可靠性研究[D].阜新:辽宁工程技术大学,2002.
[26]王洪德,刘贞堂.矿井通风网络可靠性的定量分析与评价[J].中国矿业大学学报,2007,36(3):371~374.
[27]王洪德.基于粗集—神经网络的矿井通风系统可靠性理论与方法研究[D].阜新:辽宁工程技术大学,2004.
[28]何金灿.信息融合技术在矿井通风系统安全评价中的应用研究[D].南京:河海大学,2006.
[29] Jia Jinzhang, Zang Guangwei, Qian Zhou, et al. A new algorithm for calculatingventilation network reliability based on truncation error theory and networksimplification[J]. Procedia Earth and Planetary Science,2009,1(1):169~172.
[30] Jia Tinggui, Liu Jian. Stability of mine ventilation system based on multiple regressionanalysis[J]. Mining Science and Technology,2009,19(4):463~466.
[31]刘泽功.通风安全工程中的计算机模拟技术及发展[A].中国煤炭协会第六届青年科学技术研讨会论文集[C].2000.
[32]常心坦.矿井火灾通风的模拟计算[J].煤矿安全,1991,(4):23~29.
[33] Zhou Fubao, Wang Deming, Zhou Yan. Experimental Study on air flow reversal withinbypass branch during mine Fire[J]. Journal of China University of Mining&Technology,2001,11(2):95~99.
[34] E.K.Stefopoulos, D.G.Damigos. Design of emergency ventilation system for anunderground storage facility[J]. Tunneling and Underground Space Technology,2007,22:293~302.
[35] J.Maiti, V.V.Khanzode. Development of a relative risk model for roof and side fall fatalaccidents in underground coal mines in India[J]. Safety Science,2009,47:1068~1076.
[36] S.K.Palei, S.K.Das. Sensitivity analysis of support safety factor for predicting theeffects of contributing[J]. International Journal of Coal Geology,2008,75:241~247.
[37] S.D.S.Gillies. Probabilistic method for mine heat prediction[J]. Soc of MiningEngineers of AIME,1987:145~151.
[38] Roszczynialski, Wiodzimierz. Airflow rates in mine headings and their variance atrandom variation of aerodynamic drag branches of mine ventilation network[J].1988,33(4):441~453.
[39] M.T.Parra, J.M.Villafruela, F.Castro, et al. Numerical and experimental analysis ofdifferent ventilation systems in deep mines[J]. Building and Environment,2006,41(2):87~93.
[40] M.B.Wold, L.D.Connell, S.K.Choi. The role of spatial variability in coal seamparameters on gas outburst behavior during coal mining[J]. International Journal ofCoal Geology,2008,75:1~14.
[41] M.Sari, A.S.Selcuk, C.Karpuz, et al. Stochastic modeling of accident risks associatedwith an underground coal mine in Turkey[J]. Safety Science,2009,47:78~87.
[42]李高正.煤矿监控系统瓦斯数据分析技术研究[J].煤炭科学技术,2008,36(4):58~60.
[43]张强,常心坦,许晋源.矿井风量监测异常值研究的模型与算法[J].西安矿业学院学报,1998,18(4):301~304.
[44]魏引尚.基于概率统计的通风巷道瓦斯积聚危险性分析研究[D].西安:西安科技大学,2004.
[45]张进.矿井瓦斯涌出及瓦斯流动预测的统计研究[D].西安:西安科技大学,2005.
[46]赵龙.基于控制分区瓦斯监测数据可信度与分析[D].西安:西安科技大学,2007.
[47]王俭.基于安全分区的通风瓦斯风险控制研究[D].西安:西安科技大学,2008.
[48]王红刚,吴奉亮,常心坦.基于蒙特卡洛方法的瓦斯测值分析模型[J].工矿自动化,2009,(4):52~55.
[49]杨叔子,吴雅,轩建平,等.时间序列分析的工程应用（第二版）[M].武汉:华中科技大学出版社,2007.
[50]施仁杰,卢科学.时间序列分析引论[M].西安:西安电子科技大学出版社,1988.
[51]杨位钦,顾岚.时间序列分析与动态数据建模[M].北京:北京工业学院出版社,1989.
[52] M.L.Padgett, U.Desail. Neural network applications[J]. Proceedings of SPIE-TheInternational Society for Optical Engineering,1993,1721:5~9.
[53] R.Rosipal, M.Koska, I.Farkas. Prediction of chaotic time-series with a resource-allocating RBF network[J]. Neural processing letters,1998,(7):185~197.
[54]周波,石爱国,蔡烽,等.基于多尺度分析和神经网络的时间序列预报[J].计算机应用与软件,2005,22(2):93~94.
[55]殷佳.基于小波神经网络的混沌时间序列建模研究[D].大连:大连理工大学,2007.
[56]谢乃明.序列算子与灰色预测模型研究[D].南京:南京航空航天大学,2005.
[57]王忠桃.灰色预测模型相关技术研究[D].成都:西南交通大学,2005.
[58]张军.灰色预测模型的改进及其应用[D].西安:西安理工大学,2008.
[59]蔡岩.基于灰色预测模型的短期交通流预测研究[D].成都:西南交通大学,2006.
[60]刘金英.灰色预测理论与评价方法在水环境中的应用研究[D].长春:吉林大学,2004.
[61]韩敏.混沌时间序列预测理论与方法[M].北京:中国水利水电出版社,2007.
[62]李天舒.混沌时间序列分析方法研究及其应用[D].哈尔滨:哈尔滨工程大学,2006.
[63]殷礼胜.交通流量时间序列混沌特性分析及预测研究[D].重庆:重庆大学,2007.
[64]刘立霞.多变量金融时间序列的非线性检验及重构研究[D].天津:天津大学,2007.
[65] Cao Liangyue, M.Alistair, J.Kevin. Dynamics from multivariate time series[J]. PhysicaD: Nonlinear Phenomena,1998,121(2):75~88.
[66]徐恺.基于支持向量机的股指时间序列预测[D].成都:西南交通大学,2008.
[67]岳敏.基于BBN-SVM和PCV的多变量时间序列预测算法研究[D].兰州:兰州大学,2010.
[68]李亚娇.基于现代分析技术的水文时间序列预测方法研究[D].西安:西安理工大学,2007.
[69]孟庆芳.非线性系统时间序列分析方法及应用研究[D].济南:山东大学,2008.
[70] Wu Dongmei, Zhao Yuemin, Cheng Yuanping, et al. DP index with different gascompositions for instantaneous outburst prediction in coal mines[J]. Mining Science andTechnology,2010,20:723~726.
[71]王汉斌.煤与瓦斯突出的分形预测理论及应用[D].太原:太原理工大学,2009.
[72]李刚.瓦斯浓度的分形分析与混沌预测模型研究[D].北京:中国矿业大学,2004.
[73]金芳勇.基于分形—混沌理论的煤与瓦斯突出预测研究[D].合肥:安徽理工大学,2006.
[74] Li Sheng, Zhang Hongwei. Pattern recognition and forecast of coal and gas outburst [J].Journal of China University of Mining&Technology,2005,15(3):251~254.
[75]陈祖云.煤与瓦斯突出前兆的非线性预测及支持向量机识别研究[D].徐州:中国矿业大学,2009.
[76] Qiao Meiying, Ma Xiaoping, Lan Jianyi, et al. Time-series gas prediction model usingLS-SVR within a Bayesian framework[J]. Mining Science and Technology,2011,21:153~157.
[77] Wang Chao, Wang Enyuan, Xu Jiankun, et al. Bayesian discriminant analysis forprediction of coal and gas outbursts and application[J]. Mining Science and Technology,2010,20(4):520~523.
[78]潘结南,陈江峰,徐文鹏. R/S分析及矿井瓦斯涌出量的分形预测[J].煤田地质与勘探,2001,(3):14~15.
[79] Xu Changkai, Wang Yaocai, Wang Junwei. Research on forecast technology of mine gasemission based on fuzzy data mining[J]. Journal of China University of Mining&Technology,2004,14(2):174~178.
[80]伍爱友,田云丽,宋译,等.灰色系统理论在矿井瓦斯涌出量预测中的应用[J].煤炭学报,2005,30(5):389~392.
[81]陶云奇,许江,李树春.改进的灰色马尔柯夫模型预测采煤工作面瓦斯涌出量[J].煤炭学报,2007,32(4):391~395.
[82] Pan Jienan, Meng Zhaoping, Liu Yachuan. Grey smoothing model for predicting minegas emission[J]. Journal of China University of Mining&Technology,2003,13(1):76~78.
[83]黄文标,施式亮.基于改进Lyapunov指数的瓦斯涌出时间序列预测[J].煤炭学报,2009,34(12):1666~1668.
[84]何利文.煤矿回采工作面瓦斯涌出非线性特性分析及预测仿真理论研究[D].长沙：中南大学,2009.
[85]何华刚,胡敏涛.基于改进CC方法的瓦斯涌出混沌预测[J].矿业研究与开发,2009,29(4):69~71.
[86]施式亮,宋译,何利文.矿井掘进工作面瓦斯涌出混沌特性判别研究[J].煤炭学报,2006,31(6):702~705.
[87] C. zgen, Karacan. Modeling and prediction of ventilation methane emissions ofU.S.longwall mines using supervised artificial neural networks[J]. International Journalof Coal Geology,2008,73:371~387.
[88]洪菁,赵毅,陈强.基于模糊粗糙集的瓦斯涌出量预测模型的研究[J].微计算机信息,2007,23(2):259~261.
[89] Pan Yumin, Zhang Xiaoyu, Xue Pengqian. The amount prediction of gas emitted viawavelet neural network with grey correlation analysis[A]. Proceedings2010SixthInternational Conference on Natural Computation[C].2010.
[90] Chen Xiang, Cai Weihua. Wavelet neural net based work face gas emissionprediction[A].2009IEEE International Conference on Intelligent Computing andIntelligent Systems[C].2009.
[91] Wang Jianping, Huang Hongxia, Li Hongbiao, et al. Prediction of mine gas emissionrate based on the SVM model[A].2008Chinese Control Conference[C].2008.
[92] Ning Yuncai, Chen Xiang. Coal face gas emission prediction based on support vectormachine[A]. Proceedings of the2009International Conference on Artificial Intelligenceand Computational Intelligence[C].2009.
[93]黄为勇,童敏明,任子晖.基于SVM的瓦斯涌出量非线性组合预测方法[J].中国矿业大学学报,2009,38(2):235~238.
[94]马文涛.基于WT与GALSSVM的瓦斯涌出量预测[J].采矿与安全工程学报,2009,26(4):524~527.
[95] Wang Changlong, Fu Weihua. Gas emission rate prediction in fully-mechanizedexcavated faces based on support vector machine[A]. Proceedings of the20093rdInternational Symposium on Intelligent Information Technology Application Workshops
[C].2009.
[96]郭德勇,郑茂杰,鞠传磊,等.采煤工作面瓦斯涌出量预测逐步回归方法[J].北京科技大学学报,2009,31(9):1095~1097.
[97]蔡武,袁莎莎,戚洋.基于多元线性回归分析法预测矿井瓦斯涌出量[J].煤矿安全,2010,(1):91~94.
[98]李苏旺.时间序列数据建模及其在瓦斯预测中的应用研究[D].太原:太原理工大学,2003.
[99]杨胜远,李金林,杨东朋. ARMA模型在瓦斯浓度预测中的应用[J].中国煤炭,2008,34(6):14~16.
[100]吕品,马云歌,周心权.上隅角瓦斯浓度动态预测模型的研究及应用[J].煤炭学报,2006,31(4):462~465.
[101]Qu Zhiming, Liang Xiaoying. Application of grey relation clustering and CGNN in gasconcentration prediction in top corner of coal mine[A].2009International Conferenceon Computational Intelligence and Natural Computing[C].2009.
[102]段霄鹏.基于商空间的煤矿瓦斯数据挖掘研究[D].太原:太原理工大学,2010.
[103]高莉,胡延军,于洪珍.基于W-RBF的瓦斯时间序列预测方法[D].煤炭学报,2008,33(1):68~70.
[104]Gao Li, Yu Hongzhen. Prediction of gas emission based on information fusion andchaotic time series [J]. Journal of China University of Mining&Technology,2006,16(1):94~96.
[105]施式亮,何利文,宋译,等.基于混沌与神经网络耦合模型的回采工作面瓦斯涌出时序分析与预侧[A].中国职业安全健康协会2008年学术年会论文集[C].2008.
[106]王其军,程久龙.基于免疫神经网络模型的瓦斯浓度智能预测[J].煤炭学报,2008,33(6):666~668.
[107]Shao Yuxiang, Zhang Dongmei. Mine forecast based on genetic annealing neuralnetwork[A]. Proceedings2009International Conference on Information Technology andComputer Science[C].2009.
[108]朱宇.构造神经网络在瓦斯时间序列预测中的应用[D].太原:太原理工大学,2010.
[109]白峻尧.基于SVM的瓦斯涌出的自学习模型研究应用[D].西安:西安科技大学,2006.
[110]Qian Jiansheng, Cheng Jian, Guo Yinan. A novel multiple support vector machinesarchitecture for chaotic time series prediction[A]. Advances in Natural Computation:Second International Conference[C].2006.
[111]Cheng Jian, Qian Jiansheng, Niu Guangdong, et al. Gas concentration forecasting basedon support vector regression in correlation space via KPCA[A]. Advances in NeuralNetworks:6th International Symposium on Neural Networks[C].2009.
[112]王泉夫,赵小虎,王刚.在线最小二乘支持向量机在瓦斯预测中的研究与应用[A].2010（沈阳）国际安全科学与技术学术研讨会论文集[C].2010.
[113]Zhao Xiaohu, Wang Gang, Zhao Keke, et al. On-line least squares support vectormachine algorithm in gas prediction [J]. Mining Science and Technology,2009,19(2):194~198.
[114]Zhao Xiaohu, Zhao Keke. Study of an improved online least squares support vectormachine algorithm and its application in gas prediction[A].2008Fourth InternationalConference on Natural Computation[C].2008.
[115]崔小彦,赵国强.混沌预测在井下瓦斯浓度监测的应用[J].辽宁工程技术大学学报（自然科学版）,2008,27(5):185~186.
[116]程健,白静宜,钱建生,等.基于混沌时间序列的煤矿瓦斯浓度短期预测[J].中国矿业大学学报,2008,37(2):231~234.
[117]刘婷婷,史久根,韩江洪.基于SVM的瓦斯体积分数混沌时间序列预测[J].合肥工业大学学报（自然科学版）,2009,32(8):1150~1153.
[118]杜晓坤.改进的混沌预测方法在瓦斯监测中的应用[J].微计算机信息,2010,26(11):190~191.
[119]赵金宪,于光华.瓦斯浓度预测的混沌时序RBF神经网络模型[J].黑龙江科技学院学报[J].2010,2(2):131~134.
[120]Zhao Jinxian, Jin Hongzhang, Yu Guanghua. Coalmine gas concentration forecastingbased on chaotic theory and neural network model[A]. Proceedings of the ThirdInternational Conference on Information and Computing Science[C].2010.
[121]张剑英,许徽,陈娟,等.基于粒子群优化的支持向量机在瓦斯浓度预测中的应用研究[J].工矿自动化,2010,(10):32~35.
[122]邵良杉.基于粗糙集理论的煤矿瓦斯预测技术[J].煤炭学报,2009,34(3):371~374.
[123]Shao Liangshan, Fu Guixiang. Disaster prediction of coal mine gas based on datamining[J]. Journal of Coal Science&Engineering,2008,(3):458~463.
[124]Zhang Yueqin, Duan Xiaopeng. Based on cluster cover algorithm in coal mine gasforecast application[A]. Proceedings of the2010International Conference on IntelligentComputation Technology and Automation[C].2010.
[125]Liu Yujun, Zhang Yueqin, Zhu Yu. A constructive neural network learning method basedon quotient space and its application in coal mine gas prediction[A].2010InternationalConference on Intelligent Computing and Cognitive Informatics[C].2010.
[126]许徽,张剑英,陈娟,等.基于分段线性方法的瓦斯浓度时间序列模式表示[J].工矿自动化,2010,(8):41~44.
[127]管河山.金融多元时间序列挖掘方法研究与应用[D].厦门:厦门大学,2008.
[128]方子良,高骏,王军辉.多因素时间序列法的研究[J].南京理工大学学报,2003,27(3):298~300.
[129]隰熙,蒋艳,李臣学.多属性决策的时间序列数据转换方法[J].统计与决策,2007,(9):9~10.
[130]李松臣.多元非线性非平稳时间序列的建模方法研究[D].天津:天津大学,2007.
[131]李汉东.多变量时间序列波动持续性研究[D].天津:天津大学,2000.
[132]陆嘉佳.多变量时间序列模型的参数估计及其实证检验[D].上海:华东师范大学,2008.
[133]王广江,金世国.多元随机时间序列参数估计的多尺度方法[J].科技信息,2010,(10):1~3.
[134]卢山,王海燕.多变量时间序列相空间重构的优化[J].系统工程理论方法应用,2006,15(3):234~236.
[135]王海燕,盛昭瀚,张进.多变量时间序列复杂系统的相空间重构[J].东南大学学报（自然科学版）,2003,31(3):115~118.
[136]刘立霞.多变量金融时间序列的非线性检验及重构研究[D].天津:天津大学,2007.
[137]樊重俊. Bayes多元时间序列分析方法及其应用[J].系统管理学报,2010,19(2):191~194.
[138]方芬.多变量混沌时间序列预测及其在股票市场中的应用[D].南京:东南大学,2006.
[139]方芬.多变量混沌时间序列Volterra自适应实时预测[J].系统工程与电子技术,2009,31(10):2476~2479.
[140]陈涛.多变量时间序列的重构与预测方法[J].统计与决策,2009,(14):31~33.
[141]王一颉.多元混沌时间序列相关性分析及预测方法研究[D].大连:大连理工大学,2008.
[142]魏茹.多元混沌时间序列的变量选择及预测方法研究[D].大连:大连理工大学,2007.
[143]苏变萍,曹艳平,王婷.多因素时间序列的灰色预测模型[J].西安建筑科技大学学报,2007,39(2):289~292.
[144]贾真.神经网络在煤矿瓦斯预警系统中的应用研究[D].长春:长春工业大学,2007.
[145]Liu Xiaosheng, Huang Xiaobin. Research on pre-warning expert system of coal minegas safety based on object-oriented[A].2008IEEE International Symposium onKnowledge Acquisition and Modeling Workshop[C].2008.
[146]熊廷伟.煤矿瓦斯爆炸预警技术研究[D].重庆:重庆大学,2005.
[147]李华.矿井掘进瓦斯爆炸实时智能预警监控系统[D].西安:西安科技大学,2005.
[148]牛聚粉.基于Mapx的煤与瓦斯预测预警技术研究[D].北京:中国地质大学,2006.
[149]Qian Jiansheng, Yin Hongsheng, Liu Xiurong, et al. Data processing model of coalminegas early-warning system[J]. Journal of China University of Mining and Technology,2007,17(10):20~24.
[150]Ma Xianmin. Application of data fusion theory in coal gas fire prediction system[A].2008International Conference on Intelligent Computation Technology and Automation
[C].2008.
[151]Lin Jipeng. Pre-alarm system of coal mine based on ICA and kalman filter[A].2010Sixth International Conference on Natural Computation[C].2010.
[152]Xie Guomin, Fu Hua, Wang Shiyun. Study on early warning of gas in coal mine basedon extension data mining[A].20102nd International Conference on EducationTechnology and Computer[C].2010.
[153]Song Jinxing, Liu Yufang. Study on the mine gas disaster prevention system by GIS[A].20102nd Conference on Environmental Science and Information ApplicationTechnology[C].2010.
[154]钟震宇.小煤矿通风瓦斯集群监控系统的研究[D].武汉:中国地质大学,2006.
[155]杨禹华,钟震宇,蔡康旭.基于模糊模式识别的瓦斯含量指标异常预警技术[J].中国安全科学学报,2007,17(9):172~175.
[156]邵良杉,付贵祥.基于数据融合理论的煤矿瓦斯动态预测技术[J].煤炭学报,2008,33(5):551~554.
[157]Cao Shugang, Liu Yanbao, Wang Yanping. A forecasting and forewarning model formethane hazard in working face of coal mine based on LS-SVM[J]. Journal of ChinaUniversity of Mining and Technology,2008,18(2):172~176.
[158]黄为勇.基于支持向量机数据融合的矿井瓦斯预警技术研究[D].徐州:中国矿业大学,2009.
[159]李骥平.商空间理论在煤矿预警中的应用[D].太原:太原理工大学,2010.
[160]王沁.时间序列分析及其应用[M].成都:西南交通大学出版社,2008.
[161]R.A.Davis. Introduction to time series and forecasting[M]. Beijing:Post&TelecomPress,2009.
[162]李颖.时间序列指数平滑算法的改进研究[D].阜新:辽宁工程技术大学,2009.
[163]D.B.Percival, A.T.Walden. Wavelet methods for time series analysis[M]. Beijing:ChinaMachine Press,2006.
[164]李智.小波理论与经济金融时序应用研究[D].厦门:厦门大学,2007.
[165]葛哲学,沙威.小波分析理论与MATLAB R2007实现[M].北京:电子工业出版社,2007.
[166]胡昌华,张军波,夏军,等.基于MATLAB的系统分析与设计—小波分析[M].西安:西安电子科技大学出版社,2000.
[167]李弼程,罗建书.小波分析及其应用[M].北京:电子工业出版社,2005.
[168]文莉,刘正士,葛运建.小波去噪的几种方法[J].合肥工业大学学报（自然科学版）,2002,25(2):167~172.
[169]姚恩营,周玉国,孙国栋,等.基于多尺度小波分解的时间序列预测方法研究[J].计算机时代,2009,(1):4~6.
[170]Z.K.Peng, W.Peter, F.L.Chu. An improved Hilbert-Huang transform and its applicationsin vibration signal analysis[J]. Journal of Sound and Vibration,2005,286:187~205.
[171]王慧. HHT方法及其若干应用研究[D].合肥:合肥工业大学,2009.
[172]N.E.Huang, Z.Shen, S.R.Long, et a1.The empirical mode decomposition and the Hilbertspectrum for non-linear and non-stationary time series analysis[J]. Proceedings of theRoyal Society of London,1998,454(1):903~995.
[173]陈一贤. HHT分析方法[D].杭州:浙江大学,2007.
[174]N.E.Huang, M.L.Wu, S.R.Long, et al. A confidence limit for the empirical modedecomposition and Hilbert spectrum analysis[J]. Proceedings of the Royal Society ofLondon,2003,459:2317~2345.
[175]Q.Chen, N.E.Huang, S.Riemenschneider, et al. A B-spline approach for empirical modedecomposition[J]. Adv. Compute. Math,2006,20:18~734.
[176]N.E.Huang, Z.Shen, S.R.Long．A new view of nonlinear water waves：the Hilbertspectrum[J]. Annual Review of Fluid Mechanics,1999,31:417~457．
[177]S.R.Qin, Y.M.Zhong. A new envelope algorithm of Hilbert-Huang transform[J].Mechanical System and Signal Processing,2006,20:1941~1952.
[178]董丁稳,李树刚,常心坦,等.基于HHT方法的矿井瓦斯体积分数预测[J].中国安全科学学报,2011,21(9):100~105.
[179]谷川,秦世伟.基于预测有效度的变形数据组合预测[J].大地测量与地球动力学,2008,28(5):73~76.
[180]陈华友.基于预测有效度的组合预测模型近似求解[J].安徽大学学报（自然科学版）,2003,27(3):7~10.
[181]张春明.灰色关联聚类的最大支撑树方法[J].山东交通学院学报,2004,12(2):72~75.
[182]廖向旗,李欣然,李培强,等.基于灰色关联聚类的负荷特性分类[J].电力科学与技术学报,2007,22(2):28~34.
[183]许秀莉.灰色关联、聚类、预测的改进及应用[D].厦门:厦门大学,2001.
[184]刘家学.时序多指标决策的灰色关联分析法[J].运筹与管理,1997,6(3):6~10.
[185]董丁稳,李树刚,常心坦,等.瓦斯浓度区间预测的灰色聚类与高斯过程模型[J].中国安全科学学报,2011,21(5):40~45.
[186]沈赟.基于高斯过程的时间序列分析[D].上海:上海交通大学,2009.
[187]R.Turner, M.P.Deisenroth, C.E.Rasmussen. State-space inference and learning withGaussian processes[A].13th International Conferenceon Artificial Intelligence andStatistics[C].2010.
[188]G.Pillonetto, G.De.Nicolao. A new kernel-based approach for linear systemidentification[J]. Automatica,2010,46:81~93.
[189]C.E.Rasmussen. Advances in Gaussian processes[A]. Proceedings of the NeuralInformation Processing Systems Conference[C]. the MIT Press,2006.
[190]J.Ko, D.Fox. Learning GP-BayesFilters via Gaussian process latent variable models[J].Autonomous Robots,2009,27:75~90.
[191]Dong Dingwen, Zhang Taowei, Li Shugang, et al. Gaussian process model for timeseries analysis of mine gas emission[A].2010International Conference on InformationSecurity and Artificial Intelligence[C].2010.
[192]C.E.Rasmussen, C.K.I.Williams. Gaussian processes for machine learning[M]. The MITPress,2006.
[193]G.Gregor i, G.Lightbody. Gaussian process approach for modelling of nonlinearsystems[J]. Engineering Applications of Artificial Intelligence,2009,22:522~533.
[194]G.Gregor i, G.Lightbody. Nonlinear system identification: From multiple-modelnetworks to Gaussian processes[J].Engineering Applications of Artificial Intelligence,2008,21:1035~1055.
[195]M.Deisenroth, C.E.Rasmussen, J.Peters. Gaussian process dynamic programming[J].Neurocomputing,2009,72:1508~1524.
[196]张连文,郭海鹏.贝叶斯网引论[M].北京:科学出版社,2006.
[197]Dong Dingwen, Li Shugang, Chang Xintan. Method for risk analysis of gas explosionbased on Bayesian networks[A].2010International Symposium on Safety Science andTechnology[C].2010.
[198]Dong Dingwen, Zhang Jianrang, Zhao Huajie, et al. The method for risk analysis andevaluation of hazards in coal mine based on Bayesian networks[A].2009China-JapanSymposium on Safety Management Theory and Practice[C].2010.
[199]M.E.Borsuk. Bayesian Networks[J]. Encyclopedia of Ecology,2008,(3):307~317.
[200]J.PERAL. Fusion, propagation and structuring in belief[J]. Artificial intelligence,1986,29(3):241~248.
[201]J.PERAL. Evidential reasoning using stochastic simulation of casual models[J].Artificial intelligence,1987,32(2):245~257.
[202]K.P.Murphy. Dynamic Bayesian networks: representation, inference and learning[D].Berkeley: University of California,2002.
[203]C.Simon, P.Weber, A.Evsukoff. Bayesian networks inference algorithm to implementDempster Shafer theory in reliability analysis[J]. Reliability Engineering and SystemSafety,2008,93(7):950~963.
[204]G.Cooper. Computational complexity of probabilistic inference using Bayesian beliefnetworks[J].Artificial Intelligence,1990,42(2):393~405.
[205]黄友平.贝叶斯网络研究[D].北京:中国科学院计算技术研究所,2005.
[206]董丁稳,李树刚,常心坦,等.工作面多变量瓦斯浓度时间序列预测模型[J].采矿与安全工程学报,2012,29(1):135~139.
[207]B.Samanta. Prediction of chaotic time series using computational intelligence[J]. ExpertSystems with Applications,2011,38(9):11406~11411.
[208]Xu Pengcheng. Differential phase space reconstructed for chaotic time series[J].Applied Mathematical Modeling,2009,33(2):999~1013.