煤矿瓦斯监测数据发展趋势的智能预测方法研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
为了明确煤矿井下瓦斯浓度、瓦斯涌出量、煤与瓦斯突出等预测器的输入主因素、降低其样本的复杂度并简化样本空间,为了确定预测器输入变量的不确定性对预测结果的影响,以及在其相关影响因素作用程度发生改变的情形下还能够进行准确的预测,本文开展了下列工作:
     为了识别瓦斯浓度、瓦斯涌出量等预测器的输入主因素,提出一种与预测精度相关的预测器输入主因素的遴选算法。在一定显著水平下对增添或删除若干因素前后预测器的预测残差进行F检验,用以确定具有改进作用的增添或删除操作。遍历增添和删除的所有情形后,即可确定能获得预测器在该地质、环境等条件下的最佳输入主因素,即预测性能最大改进的主因素输入组合。
     针对煤矿井下瓦斯浓度、瓦斯涌出量等时间序列往往呈现出较强的随机性和复杂性的情形,提出一种基于小波变换的瓦斯浓度、瓦斯涌出量等时间序列的预测方法。通过小波分解降低时间序列的复杂度,将小波分解后各个分量转化为具有历史特征的新样本分别进行预测,所得到结果进行综合作为最终预测结果。用时间序列分解到小波函数空间(或尺度函数空间)上的能量作为尺度能量,依据尺度能量与满足预测精度的最大误差能量的比值关系提出了小波最佳分解级数的计算方法。基于粒子群优化算法计算得到了预测模型的优化参数。
     针对煤矿井下瓦斯分布具有模糊性和不确定性等特点,提出基于模糊C-均值聚类(FCM)的瓦斯浓度、瓦斯涌出量等预测方法,对样本数据进行FCM聚类分析,依据所得到的不同类别分别建立预测模型,并对样本空间的参数、预测器的参数和FCM的参数采用基于蚁群算法并以预测差残的F检验值作为适应值的方法进行了优化。
     为了确定瓦斯浓度、瓦斯涌出量等预测器输入变量的不确定性对于预测结果的影响,提出基于抽样盲数的估计方法,解决了相关因素任意概率分布特性的处理问题。提出相关因素的不确定性在预测过程中的传递算法、高阶抽样盲数降阶的计算方法以及输入因素不确定性下预测器输出结果的概率分布和置信区间的计算方法。
     为了在瓦斯浓度、瓦斯涌出量等的相关影响因素作用程度发生改变的情形下,还能够进行准确预测,提出了基于虚拟状态变量的、系统网络结构可以自适应的预测方法。用能够反映待预测对象的输入变量在模式识别网络输出空间上的特征响应作为虚拟状态变量。基于虚拟状态变量建立预测模型,对待预测对象进行预测。通过预测误差建立反馈机制,以此对模式识别网络的结构朝着符合待预测对象(如瓦斯涌出量)变化的方向进行调整,从而得到适合的虚拟状态变量,以适应相关影响因素作用程度的改变。
     基于本文的研究成果,将上述方法应用于一些实例,对煤矿井下瓦斯浓度、瓦斯涌出量和煤与瓦斯突出等进行预测,结果表明:预测性能改善显著,表明所建议的方法是可行的和有效的。
The aim is to make clear the forecaster main input factors of coal mine underground gasconcentration, gas emission quantity, coal and gas outburst, etc, reduce the complexity of theirsamples and simplify the samples attributes. It is also for evaluation the influence of the inputfactors uncertainties on the forecasting results as well as accurate prediction the gas hazardeven when the effect of the related factors changes. The following observations have beenmade:
     For recognition the main input factors of gas concentration and gas emission quantity, ect,an approach related to prediction precision to select the main input factors of gas hazardforecasting is proposed. The necessary elimination or adding of input factors are determinedby F test for the forecasting variances before and after elimination or adding. Afterinvestigating on all cases, the most suitable input factor under the current geologicalenvironment and other conditions can be identified, that is the main input factor combinationof the most improved prediction performance.
     With regard to the situation that time series of gas concentration and gas emissionquantity often show strong randomness and complexity, an approach based on wavelettransform is put forward to predict gas concentration, gas emission quantity and other timeseries. Wavelet decomposition is used to reduce the complexity of time series, and the waveletcomponents are transformed into new samples with historical characteristics, which are usedin the prediction, respectively. The final forecasting results are obtained by combining all ofthe predicted results. The energy of time series decomposed into wavelet or scaling functionalspace is used as the scaling energy, based on which, the method calculation best waveletdecomposition level is presented according to the ratio of the scaling energy and the largestforecasting biases energy under the allowed prediction precision. The optimized parameters of forecasting model is obtained by a Particle Swarm Optimization based program.
     Concerning the distribution of coal mine underground gas having fuzziness, uncertaintyand other characteristics, an approach is suggested to forecast gas concentration and gasemission quantity based on Fuzzy C-means Clustering (FCM). FCM is introduced to classifythe samples into different categories. The corresponding forecaster is constructed for eachcategory, respectively. The parameters of samples space, predictor and FCM are optimizedbased on the ant colony optimization algorithm by using F test of the prediction residual asthe fitness value.
     In order to evaluate the influence of the input variables uncertainties on the forecastingresults of gas concentration and gas emission quantity, ect,, an estimation approach based onSampled-Blind-Number (SBN) is proposed, based on which, the problem of processing theprobability distribution with various types is solved. The transfer algorithm of the relatedfactors uncertainties in forecasting, the way of high order SBN converting lower order oneand the method of the probability distribution and the confidence interval of the forecastingresults with the input factors having uncertainty are put forward.
     To accurately predict the gas concentration and gas emission quantity even when theeffects of the related factors change, an approach based on the virtual state variables andself-adaptive network structure is proposed. The input variables with the capability ofreflecting the awaiting forecasting objec are mapped by a pattern recognition network, and theobtained characteristics responses of the output space are used as the virtual state variables.The awaiting forecasting objec is predicted by the virtual state variables based forecaster. Thestructure of the pattern recognition network is adjusted according with the change of theawaiting forecasting object such as gas concentration by the feedback mechanism basedforecasting biases. Consequently, the suitable virtual state variables which can adapt to thechanges of the related factors effect are obtained.
     Based on the research achievements in this paper, the above methods are applied in someexamples, and gas concentration, gas emission quantity, coal and gas outburst are predicted.The results show that the forecasting performance is remarkably improved indicating that theproposed approaches are feasible and effective.
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,2008,23(4):45-48.
    [2]温家宝.关于制定国民经济和社会发展第十一个五年规划建议的说明,2005.10.
    [3]国家发展和改革委员会能源局网站.2005年全国煤矿安全生产状况分析报告. [EB/OL].(2006-06-23)[2010-11-02].http://nyj.ndrc.gov.cn/mtwsfz/jyxx/t20060213_59246.htm.
    [4]新华网.我国煤矿瓦斯事故不断:投入不足基础薄弱[EB/OL].(2008-08-10)[2010-11-02].http://news.xinhuanet.com/fortune/2008-03/10/content_7755893.htm.
    [5]国家发展和改革委员会能源局网站.2008年煤矿瓦斯防治工作情况总结. [EB/OL].(2009-01-12)[2010-11-02].http://nyj.ndrc.gov.cn/mtwsfz/jyxx/t20090217_261392.htm.
    [6]中国政府网.全国煤矿瓦斯事故三年降近六成但形势依然严峻.[EB/OL].(2009-01-12)[2010-11-02].http://www.gov.cn/jrzg/2009-01/12/content_1203358.htm.
    [7]国家发展和改革委员会能源局网站.吴吟同志在煤矿瓦斯防治(集中整治)领导小组办公室主任会议上的讲话. [EB/OL].(2010-06-29)[2010-11-02].http://nyj.ndrc.gov.cn/mtwsfz/jyxx/t20100723_362413.htm.
    [8]新华网.中国将开展煤矿瓦斯治理专项检查. [EB/OL].(2010-08-17)[2010-11-02].http://news.xinhuanet.com/society/2010-08/17/c_12456307.htm.
    [9]王汉斌.煤与瓦斯突出的分形预测理论及应用[D].太原理工大学博士学位论文,2009.
    [10]范启炜,王魁军,曹林.我国煤矿瓦斯灾害事故频发的原因分析[J].中国煤炭,2003,29(7):9-11.
    [11]于不凡,王佑安.煤矿瓦斯灾害防治及利用技术手册[M].北京:煤炭工业出版社,2000.
    [12]李胜.煤与瓦斯突出区域预测的模式识别方法研究[D].辽宁工程技术大学博士学位论文,2004.
    [13]付华.煤矿瓦斯灾害特征提取与信息融合技术研究[D].辽宁工程技术大学博士学位论文,2006.
    [14]安全生产“十一五”规划草案征求社会意见稿,国家安监总局,2005.11.
    [15]Zhang Yun,Zhou Quan,Sun Caixin,et al.RBF Neural Network and ANFIS-BasedShort-Term Load Forecasting Approach in Real-Time Price Environment[J].IEEE TransOn Power System,August,2008,23(3): 853-858.
    [16]Shrivastava V,Misra R B.A Novel Approach of Input Variable Selection for ANN BasedLoad Forecasting[C].Power System Technology and IEEE Power India Conference,2008:1-5
    [17]Mandal P,Srivastava A K,Negnevitsky M,et al.An Effort to Optimize Similar DaysParameters for ANN Based Electricity Price Forecasting[C].IEEE internationalconferment on Industry Applications Society Annual Meeting,2008:1-9.
    [18]Azadeh A,Ghadrei S F,Nokhandan B P.One day ahead load forecasting for electricitymarket of Iran by ANN[C].IEEE international conferment on Power Engineering,Energyand Electrical Drives,2009: 670– 674.
    [19]M Sforna F,Proverbio.A neural network operator oriented short-term and online loadforecasting environment[J].Electric Power Systems Research,1995,(33):139-149.
    [20]Zhang Bailing,Zhao Yangdong.An adaptive neural-wavelet model for short term loadforecasting[J].Electric Power Systems Research,2001,(59) :121–129.
    [21]Kalaitzakis K,Stavrakakis G S,E M Anagnostakis.Short-term load forecasting based onartificial neural networks parallel implementation[J].Electric Power Systems Research2002,(63):185-196.
    [22]James W,Taylor,Roberto B.Neural Network Load Forecasting With Weather EnsemblePredictions[J]. IEEE Transactions on Power Systems,2002,17(3):676-632.
    [23]田水承,李华,陈勇刚.基于神经网络的掘进面瓦斯爆炸危险源安全评价[J].煤田地质与勘探,2005,33(3):19-21.
    [24]朱红青,常文杰,张彬.回采工作面瓦斯涌出BP神经网络分源预测模型及应用[J].煤炭学报,2007,32(5):504-508.
    [25]唐朝伟,何国田,徐昌彪,等.神经网络在采煤工作面瓦斯涌出量预测中的应[J].计算机应用,2007,27:202-204.
    [26]施式亮,刘宝琛.基于人工神经网络的矿井瓦斯涌出预测模型及其应用,矿冶工程[J].1999,19(1):21-23.
    [27]付琳燕,华刚.基于人工神经网络的煤矿瓦斯涌出量预测系统[J].矿山机械,2006,54(11):30-32.
    [28]郝吉生.BP算法及其在煤与瓦斯突出预测中的应用[J].辽宁工程技术大学学报,2004,23(1):9-11.
    [29]田云丽,周利华.基于BP神经网络的煤与瓦斯突出预测方法的研究[J].系统工程理论与实践,2005,12:102-106.
    [30]Karacan C,Ozgen.Forecasting gob gas venthole production performances usingintelligent computing methods for optimum methane control in longwall coal mines[J].Elsevier,Amsterdam,Netherlands,2009,79(4):131-144.
    [31]You Wei,Wang Kun,Li Huixiao,et al.Prediction of the Coal and Gas Outburst ByNeural Network[C].IEEE international conferment on Symposium on ComputationalIntelligence and Design,2009:405-409.
    [32]魏建平,郝天轩,刘明.基于构造复杂程度定量评价的瓦斯含量预测BP模型[J].煤炭学报,2009,34(8):1090-1094.
    [33]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].人工智能,2007,23(3):259-261.
    [34]谭云亮,肖亚勋,孙伟芳.煤与瓦斯突出自适应小波基神经网络辨识和预测模型[J].岩石力学与工程学报,2007,26(s1):3373-3377.
    [35]倪小明,王延斌,郭良.基于BP神经网络的煤与瓦斯突出预测专家系统[J].煤炭科学技术,2006,34(6):70-84.
    [36]杨敏,汪云甲,程远平.煤与瓦斯突出预测的改进差分进化神经网络模型研究[J].中国矿业大学学报,2009,38(3):439-444.
    [37]高雷阜.煤与瓦斯突出灾害的预测——基于遗传和BP算法[J].辽宁工程技术大学学报,2002,21(4):408-410.
    [38]位爱竹,王凯,伍永生.基于GA-BP混合算法的煤与瓦斯突出强度预测研究[J].矿业安全与环保,2006,33(4):4-6.
    [39]吴财芳,曾勇.基于遗传神经网络的瓦斯含量预测研究[J].地学前缘,2003,10(1):219-224.
    [40]Sun Yanjing,Qian Jiansheng.Forecast the Dangerous Level of Gas Outburst Based onGASA Neural Networks in Coal Mine[C].IEEE international conferment on ThirdInternational Conference on Natural Computation,2007: 641– 645.
    [41]Sun Yanjing,Qian Jiansheng,Li Shiyin,et al.Intelligent Prediction System of Coal-GasOutburst Based on Evolutionary Neural Nets[C].IEEE International Joint Conference onNeural Networks,2006:2650-2655.
    [42]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):665-669.
    [43]Zhu Yu,Zhang Hong,Kong Lingdong.Research of Coal and Gas Outburst ForecastingBased on Immune Genetic Neural Network[C].IEEE international conferment on SecondInternational Workshop on Knowledge Discovery and Data Mining,2009:28-31.
    [44]Wang Dongfeng,Han Pu,Han Wei,et al.Typical grey prediction control methods andsimulation studies[C].IEEE International Conference on Machine Learning andCybernetics,2003 International,2003:513– 518.
    [45]Liu Sifeng,Forrest J.Advances in grey systems theory and its applications[C].IEEEInternational Conference on Grey Systems and Intelligent Services,2007:1-6.
    [46]Chiang H K,Tseng C H.Integral variable structure controller with grey prediction forsynchronous reluctance motor drive[J].Electric Power Applications,IEEE Proceeding2004,151(3): 349– 358.
    [47]El-Fouly T H M,El-Saadany E F,Salama M M A.Improved Grey predictor rollingmodels for wind power prediction[J].Generation,Transmission & Distribution,IET,2007,1(6): 928– 937.
    [48]El-Fouly T H M,El-Saadany E F,Salama M M A.Grey predictor for wind energyconversion systems output power prediction[J].IEEE Transactions on Power Systems,2006,21(3): 1450 - 1452.
    [49]Li Wei,Han Zhuhua.Application of improved grey prediction model for power loadforecasting[C].IEEE 12th International Conference on Computer Supported CooperativeWork in Design,2008:1116– 1121.
    [50]Lu M,Wevers K.Forecasting and evaluation of traffic safety impacts: driving assistancesystems against road infrastructure measures[J].Intelligent Transport Systems,IET 2007,1(2): 117– 123.
    [51]Gwo-Jen Hwang.Gray Forecast Approach for Developing Distance Learning andDiagnostic Systems[J].IEEE Transactions on Systems,Man and Cybernetics,Part C:Applications and Reviews,2007,52(1): 280– 290.
    [52]Su Shunfeng,Lin Chanben,Shu Yenseng.A high precision global prediction approachbased on local prediction approaches[J].IEEE Transactions on Systems,Man andCybernetics,Part C: Applications and Reviews,2002,32(4): 416– 425.
    [53]Jer Min Jou,Chen Peiyin,Sun Jianming.The gray prediction search algorithm for blockmotion estimation[J].IEEE Transactions on Circuits and Systems for Video Technology,1999,9(6):843– 848.
    [54]李念友,郭德勇,范满长.灰关联分析方法在煤与瓦斯突出控制因素分析中的应用[J].煤炭科学技术,2004,32(2):69-71.
    [55]伍爱友,肖红飞,王从陆,等.煤与瓦斯突出控制因素加权灰色关联模型的建立与应用[J].煤炭学报,2005,30(1):58-62.
    [56]臧大进,王耀才.煤与瓦斯突出预测研究[J].计算机工程与设计,2007,28(12):2983-2987.
    [57]郭德勇,李念友,裴大文,等.煤与瓦斯突出预测灰色理论-神经网络方法[J].北京科技大学学报,2007,29(4):354-357.
    [58]桂祥友,郁钟铭.基于灰色关联分析的瓦斯突出危险性风险评价[J].采矿与安全工程学报,2006,23(4):464-467.
    [59]孙斌.应用灰色关联分析法评价瓦斯爆炸事故危险源[J].煤炭科学技术,2005,33(12):61-64.
    [60]李成武.煤与瓦斯突出危险性灰色分类方法实验研究[J].煤矿安全,2007,(6):1-4.
    [61]孙斌.瓦斯涌出量灰色预测[J].中国煤炭,2007,33(8):72-74.
    [62]谢万星,孙惠民.矿井瓦斯涌出量的灰色预测[J].煤矿安全,2002,33(4):32-33.
    [63]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):589-592.
    [64]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):461-465.
    [65]袁东升,杨运良,孙方田.三维灰趋势面分析法在瓦斯涌出量预测中应用[J].辽宁工程技术大学学报,2003,22(4):478-479.
    [66]张振文,高永利,代凤红,等.影响晓南矿未开采煤层瓦斯赋存的地质因素[J].煤炭学报,2007,32(9):950-954.
    [67]陶云奇,许江,李树春.瓦斯涌出量灰色预测法[J].重庆大学学报(自然科学版),2007,30(6):121-124.
    [68]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.
    [69]施式亮,伍爱友.GM(1,1)模型与线性回归组合方法在矿井瓦斯涌出量预测中的应用[J].煤炭学报,2008,04(33):415-418.
    [70]谷松,崔洪庆,冯文丽.基于灰色理论的小波神经网络对瓦斯涌出量的预测[J].煤炭学报,2007,9(32):964-966.
    [71]题正义,杨艳国,丁涛.瓦斯涌出量的模糊数学与灰色系统理论的预测[J].辽宁工程技术大学学报(自然科学版),2000,2(19):126-129.
    [72]桂祥友,郁钟铭,孟絮屹.贵州煤矿瓦斯涌出量灰色预测的应用[J].采矿与安全工程学报,2007,4(24):449-452.
    [73]张瑞林,刘晓,郑立军.基于灰色动态建模的瓦斯涌出量预测方法研究[J].中国矿业,2006,15(12):110-112.
    [74]Ikeguchi T,Aihara K,Genesio R,et al.Chaos prediction in nonlinear feedback systems,IEE Proceedings on Control Theory and Applications[J].1991,138(4):313-320.
    [75]Ikeguchi T,Aihara K.Nonlinear prediction on squid axon response[C],IEEEInternational on Neural Networks,1995: 3134-3139.
    [76]Gilli M,Maggio G.M.Predicting chaos through an harmonic balance technique: anapplication to the time-delayed Chua's circuit[J].IEEE Transactions on Circuits andSystems I: Fundamental Theory and Applications,1996,43(10):872-874.
    [77]Mackay A.Chaos theory and first-order ray tracing in ducts[J].Electronics Letters 1998,34(14): 1388 -1389.
    [78]Suarez A,Collantes J M.A new technique for chaos prediction in RF circuit design usingharmonic-balance commercial simulators[J].IEEE Transactions on Circuits and Systems I:Fundamental Theory and Applications,1999,46(11):1413-1415.
    [79]Han Min,Xi Jianhui,Xu Shiguo,et al.Prediction of chaotic time series based on therecurrent predictor neural network[J].IEEE Transactions on Signal Processing,2004,52(12): 3409-3416.
    [80]Cui Herui,Song Xiuli.Research on Electricity Price Forecasting Based on ChaosTheory[C].IEEE International Conference on Future Information Technology andManagement Engineering,2008: 398-401.
    [81]Shum D T F,Lee R S T,Liu J N K.Chaotic weatherman; the design and implementationof a chaotic weather prediction system. IEEE International Conference on EvolutionaryComputation,2008: 2186-2193.
    [82]Varadan V,Leung H,Bosse E.Dynamical model reconstruction and accurate predictionof power-pool time series[J].IEEE Transactions on Instrumentation and Measurement,2006,55(1): 327 -336.
    [83]Kaddoum G,Charge P,Roviras D.A generalized methodology for bit-error-rateprediction in correlation-based communication schemes using chaos[J].IEEECommunications Letters,2009,13(8): 567-569.
    [84]Shi Zhiwei,Han Min.Support Vector Echo-State Machine for Chaotic Time-SeriesPrediction[J].IEEE Transactions on Neural Networks,2007,18(2): 359 - 372.
    [85]Oguchi T,Nijmeijer H.Prediction of chaotic behavior[J].IEEE Transactions on Circuitsand Systems I: Regular Papers.2005,52(11): 2464– 2472.
    [86]何利文,施式亮,宋译,等.回采工作面瓦斯涌出的复杂性及其度量[J].煤炭学报,2008,33(5):547-550.
    [87]王凯,王轶波,卢杰.煤与瓦斯突出动态前兆的非线性特征研究[J].采矿与安全工程学报,2007,24(1):22-26.
    [88]何俊,王云刚,陈新生,等.煤与瓦斯突出前瓦斯涌出动态混沌特性[J].辽宁工程技术大学学报,2010,29(4):529-532.
    [89]高雷阜.煤与瓦斯突出的混沌动力系统演化规律研究[D].辽宁工程技术大学,2006,4.
    [90]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(02):231-235.
    [91]张剑英,程健,侯玉华,等.煤矿瓦斯浓度预测的ANFIS方法研究[J].中国矿业大学学报,2007,36(04):494-498.
    [92]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):1665-1668.
    [93]赵志刚.煤与瓦斯突出的耦合灾变机制及非线性分析[D].山东科技大学,2007.
    [94]赵志刚,谭云亮.基于混沌理论的煤与瓦斯突出前兆时序预测研究[J].岩土力学,2009,30(7):2186-2190
    [95]徐精彩,赵庆贤,邓军,等.矿井瓦斯涌出量时间序列的分形特性分析[J].辽宁工程技术大学学报,2004,23(01):2-4.
    [96]王汉斌,郝仲熙,牛冲槐.瓦斯涌出规律非线性系统模型理论与应用研究[J].金属矿山,2006,(358):59-61.
    [97]何俊,刘明举,颜爱华.煤田地质构造与瓦斯突出关系分形研究[J].煤炭学报,2002,6(358):59-61.
    [98]何俊,何学秋,刘明举.煤与瓦斯突出多尺度预测研究[J].岩石力学与工程学报,2004,23(18):3122-3126.
    [99]Mandelbrot B B.The fractal geometry of nature[M].San Fracisico,W.H.Freeman and Co,1982.
    [100]Falconer K J.Fractal geometry:Mathematical foundation and application[M].Wiley,NewYork,1990.
    [101]Dipti Srinivasan,Chang C S,Liew A C.Demand forecasting using fuzzy neuralcomputation,with special emphasis on weekend and public holiday forecasting[J].IEEETransactions on Power Systems,1995,10(4): 1897– 1903.
    [102]Dash P K,Liew A C,Rahman S.Fuzzy neural network and fuzzy expert system for loadforecasting[C].Generation,Transmission and Distribution,IEE Proceedings,1996,143(1): 106– 114.
    [103]Burr T.Comparison of fuzzy forecaster to a statistically motivated forecaster[C].IEEEInternational Conference on Systems,Man and Cybernetics,Part A: Systems andHumans,1998,28(1):121– 127.
    [104]Ben Ghalia M,Wang P P.Intelligent system to support judgmental business forecasting:the case of estimating hotel room demand[J].IEEE Transactions on Fuzzy Systems,2000,8(4): 380– 397.
    [105]Lee Liwei,Wang Lihui,Chen Shyming,et al.Handling forecasting problems basedon two-factors high-order fuzzy time serie[J].IEEE Transactions on Fuzzy Systems,2006,14(3): 468– 477.
    [106]Al-Hamadi H M,Soliman S A.Fuzzy short-term electric load forecasting using Kalmanfilter[C].Generation,Transmission and Distribution,IEE Proceedings,2006,21(2): 217– 227.
    [107]Lee Chiunghon Leon,Liu Alan,Chen Wensung.Pattern discovery of fuzzy time seriesfor financial prediction[J].IEEE Transactions on Knowledge and Data Engineering,2006,18(5): 613– 625.
    [108]Wang W,Vrbanek J.An Evolving Fuzzy Predictor for Industrial Applications[J].IEEETransactions on Fuzzy Systems,2008,16(6): 1439– 1449.
    [109]Amjady N.Day-ahead price forecasting of electricity markets by a new fuzzy neuralnetwork[J].IEEE Transactions on Power Systems,2006,21(2): 887– 896.
    [110]Mota L T M,Mota A A,Morelato A.Load behaviour prediction under blackoutconditions using a fuzzy expert system[J].Generation,Transmission & Distribution,IET,2007,1(3):379 - 387.
    [111]Pindoriya N M,Singh S N,Singh S K.An Adaptive Wavelet Neural Network-BasedEnergy Price Forecasting in Electricity Markets[J].IEEE Transactions on PowerSystems,2008,23(3): 1423 - 1432.
    [112]Ajil K S,Thapliyal P K,Shukla M V,et al .A New Technique for Temperature andHumidity Profile Retrieval From Infrared-Sounder Observations Using the AdaptiveNeuro-Fuzzy Inference System[J].IEEE Transactions on Geoscience and RemoteSensing,2010,48(4): 1650– 1659.
    [113]Hinojosa V H,Hoese A.Short-Term Load Forecasting Using Fuzzy Inductive Reasoningand Evolutionary Algorithms[J].IEEE Transactions on Power Systems,.2010,25(1): 565– 574.
    [114]Elias C N,Hatziargyriou N D.An Annual Midterm Energy Forecasting Model UsingFuzzy Logic[J].IEEE Transactions on Power Systems,2009,24(1):469 - 478.
    [115]Ji Aibing,Qiao Yanhua,Qiu Hongjie.Combination Forecasting of FuzzyForecast[C].IEEE International Conference on Fuzzy Systems and KnowledgeDiscovery,2009,2009: 262– 266.
    [116]杨莉娜,浑宝炬,张超.模糊综合评价法在矿井瓦斯事故危险源评价中的应用[J].煤矿安全,2007,2:22-24.
    [117]徐尚仲,朱传杰,高玉成,等.煤矿瓦斯爆炸重大危险源辨识与风险评价[J].煤矿安全,2007,2:11-14.
    [118]张甫仁,景国勋,顾志凡,等.论矿山重大危险源辨识、评价及控制[J].中国煤炭,2001,(10):41-43.
    [119]曹树刚,王艳平,刘延保,等.基于危险源理论的煤矿瓦斯爆炸风险评价模型[J].煤炭学报,2006,31(4):470-474.
    [120]杨飞龙,蒋承林,孙鑫,等.煤与瓦斯突出影响因素评价分析的模糊层次分析方法[J].中国安全生产科学技术,2009,5(6):53-56.
    [121]曹庆奎,任向阳,刘开第.矿井工作面瓦斯涌出量的未确知聚类研究[J].煤炭学报,2006,31(03):337-341.
    [122]代凤红,张振文,高永利,等.基于模糊综合评判理论的瓦斯突出危险性预测[J].辽宁工程技术大学学报,2006,25(S2).
    [123]孙艳玲,秦书玉,梁宏友.煤与瓦斯突出预报的模糊聚类关联分析法[J].辽宁工程技术大学学报,2003,22(4):492-493.
    [124]郭德勇,范金志,马世志,等.煤与瓦斯突出预测层次分析-模糊综合评判方法[J].北京科技大学学报,2007,29(7):660-664.
    [125]陈凤,申东日,陈义俊,等.模糊小波网络在煤与瓦斯突出预测中的应用[J].煤矿安全,2006,10:51-54.
    [126]秦汝祥,张国枢,杨应迪.瓦斯涌出异常预报煤与瓦斯突出[J].煤炭学报,2006,31(5):599-602.
    [127]李大鹏,王志亮.煤与瓦斯突出危险性预测技术的研究[J].矿业安全与环保,2007,34(5):10-12.
    [128]Maiti J,Bhattacherjee A.Predicting accident susceptibility: A logistic regression analysisof underground coal mine workers[J].South African Institute Of Mining AndMetallurgy,2001,101(4):203-208.
    [129]Hower James C,Greb Stephen F.Geologic hazards in coal mining: Prediction andprevention[J].Elsevier,Amsterdam,Netherlands,2005,64(1-2):1-2.
    [130]Frid V.Calculation of electromagnetic radiation criterion for rockburst hazard forecast incoal mines[J].Pure And Applied Geophysics,2001,158:931-944.
    [131]Mrlina J.Gravity monitoring of rock density changes caused by coal mining with regardto rock bursts forecasting[C].Proceedings Of the International ConferenceGeomechanics'93,1994:75-79.
    [132]Ohga K,Shimada S,Ishh E.Gas emission prediction and control in deep coalmines[J].World Sci Publ Co Pte Ltd,Singapore,2000,9(2):239-254.
    [133]Alsaab D,Eliea M,Izart A,et al.Distribution of thermogenic methane in carboniferouscoal seams of the donets basin(ukrainne):“applications to exploitation of methane andforecast of mining hazards”[J].International Journal Of Coal Geology,2009,78:27-37.
    [134]田水承,李红霞,王莉.3类危险源与煤矿事故防治[J].煤炭学报,2006,31(6):706-710.
    [135]罗新荣,夏宁宁,贾真真.煤矿重大危险源辨识理论与方法研究[J].中国煤炭,2006,32(3):60-74.
    [136]王建国.煤矿生产系统危险源结构及煤矿事故预防[J].矿业安全与环保,2008,35(1):85-88.
    [137]王文超.煤矿瓦斯特征与风险评价[J].煤矿爆破,2005,3(70):5-8.
    [138]田水承,李红霞,王莉,等.从三类危险源理论看煤矿事故的频发[J].中国安全科学学报,2007,17(1):10-15.
    [139]江兵,白勤虎,何精梅.煤矿危险源分类分级与预警[J].中国安全科学学报,1999,9(4):70-74.
    [140]张甫仁,景国勋.矿山重大危险源评价及瓦斯爆炸事故伤害模型建立的若干研究[J].工业安全与环保,2002,28(1):42-45.
    [141]戴广龙,汪有清,张纯如,等.保护层开采工作面瓦斯涌出量预测[J].煤炭学报,2007,32(4):382-385.
    [142]贺明新,张占存,张连发.潞宁煤业公司掘进工作面瓦斯涌出规律探讨[J].煤矿安全,2006,(9):56-58.
    [143]曲方,刘克功,赵洪亮,等.基于煤壁瓦斯涌出初速度的综掘工作面瓦斯涌出量预测[J].煤矿安全,2004,35(8):1-4.
    [144]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,西安科技大学[D].2004.
    [145]鲁玉芬,陈萍,唐修义.淮南煤田潘一井田13-1煤层瓦斯含量特征[J].煤田地质与勘探,2006,34(2):29-32.
    [146]彭苏萍,段延娥,孟召平,等.Bayes逐步判别分析法在煤矿瓦斯分区评价中的应用(淮南煤田潘三矿)[J].煤田地质与勘探,2003,31(2):10-12.
    [147]张克,汪云甲.基于贝叶斯网络的煤与瓦斯突出预测研究[J].计算机工程与应用,2007,43(29):220-248.
    [148]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):234-239.
    [149]南存全,冯夏庭.基于SVM的煤与瓦斯突出区域预测研究[J].岩石力学与工程学报,2005,24(2):263-267.
    [150]秦法秋.煤层瓦斯赋存规律综合研究[J].煤炭工程,2007(8):69-71.
    [151]吴财芳,曾勇.基于专家系统的煤与瓦斯突出预测知识库研究[J].煤田地质与勘探,2004,32(1):17-20.
    [152]郝吉生,袁崇孚,韩德馨.煤与瓦斯突出区域预测集成专家系统的实现[J].辽宁工程技术大学学报(自然科学版),2000,19(3):240-243.
    [153]张许良.煤与瓦斯突出区域性预测的综合判据研究[J].煤炭学报,2003,28(3):251-255.
    [154]张许良,彭苏萍,张子戌,等.煤与瓦斯突出数学地质模型研究[J].煤田地质与勘探,2004,32(1):14-17.
    [155]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.
    [156]孙继平,李迎春,付兴建.煤与瓦斯突出预报数据关联性的聚类分析[J].湖南科技大学学报(自然科学版),2006,21(4):1-4.
    [157]郭德勇,郑茂杰,郭超,等.煤与瓦斯突出预测可拓聚类方法及应用[J].煤炭学报,2009,34(6):783-787.
    [158]卢宏伟.煤与瓦斯突出综合预测的集对分析模型与应用[J].矿业安全与环保,2007,34(1):3-5.
    [159]张瑞林,鲜学福,闫江伟,等.基于事故树分析的瓦斯突出控制因素研究[J].中国矿业,2005,14(5):14-16.
    [160]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):1095-1099.
    [161]朱莉,谷琼,蔡之华,等.基于Isomap的SMO算法及在煤与瓦斯突出预测中的应用[J].应用基础与工程科学学报,2009,17(6):958-963。
    [162]Vapnik V N.The nature of statistical learning theory[M].New York: Springer,1995.
    [163]Vapnik V N,GOLOWICH S E,SMOLA A J.Support vectormachine for functionapproximation.regression estimationand signal procession[J].Advanced NeuralInformationProcession System,1996,21(9):281-287.
    [164]Zhang Bailing,Richard Coggins.Multiresolution forecasting for future trading usingwavelet decomposition[J].Neural Networks,2001,12 (4):765-775.
    [165]Eberhart R C,SHI Yuhui.Particle swarm optimizaiton:developments,applicaitons andresources[C].Proceedings of the 2001 Congress on EvolutionaryComputation.Piscataway,NJ,USA:IEEE Press,2001,1:81-86.
    [166]Kennedy J,Eberhart R C.Particle swarm optimization [C].Proceedings of IEEEInternational Conference on Neural Networks.Piscataway,NJ:IEEE Service Center,1995:1942-1948.
    [167]唐晓初.小波分析及其应用[M].重庆:重庆大学出版社,2006.
    [168]吴大正,杨林耀,张永瑞.信号与线性系统分析[M].北京:高等教育出版社,1998.
    [169]姜园,张朝阳,仇佩亮,等.用于数据挖掘的聚类算法[J].电子与信息学报,2005,27(4):655-662.
    [170]Pal N R,Bezdek J C.On cluster validity for the fuzzy c-means model [J].IEEETransactions on Fuzzy Systems,1995,3(3):370-379.
    [171]Bezdek J C.Pattern recognition with fuzzy objective function algorithms [M].New York:Plenum Press,1981.
    [172]Dorigo M.The ant system: optimization by a colony of cooperating agents[J].IEEETransactions on System,Man,and Cybernetics-part B,1996,26 (1): 1~13.
    [173]Dorigo M,Stutzle T.Ant colony optimization[M].Cambridge: MIT Press,2004.
    [174]马良.全局优化的一种新方法[J].系统工程与电子技术,2000,22(9):61-63.
    [175]詹士昌,徐婕.用于多维函数优化的蚁群算法[J].应用基础与工程科学学报,2003,11(3):223-229.
    [176]曹洪民,张玉林,姜永鹏,等.基于小波神经网络的煤矿瓦斯涌出量预测[J].计算机应用与软件,2009,26(7):169-170.
    [177]刘开第,吴和琴.盲数的概念、运算与性质[J].运筹与管理,1998,7(3):14-17.
    [178]刘健,朱继萍,程红丽.相关因素不确定性对负荷预测结果的影响[J].中国电力,2005,38(10):20-24.
    [179]孙东玲,董钢峰,梁运培.煤与瓦斯突出预测指标临界值的选取对预测准确率的影响[J].煤炭学报,2001,26(1):71-75.
    [180]肖红飞,何学秋,刘黎明.改进BP算法在煤与瓦斯突出预测中的应用[J].中国安全科学学报,2003,13(9):59-61.
    [181]赵朝义,袁修干,孙金镖.遗传规划在采煤工作面瓦斯涌出量预测的应用[J].应用基础与工程科学学报,1999,7(4): 387-392
    [182]俞启香.矿井瓦斯防治[M].徐州:中国矿业大学出版社,1992
    [183]何利文,施式亮,宋译,等.回采工作面瓦斯涌出量的复杂性及其度量[J].煤炭学报,2008,33(5):547-550.
    [184]Paul Z,Howard M.Fundamentals of Kalman filtering: A practical approach[M].Virginia:Published by the American Institute of Aeronautics and Astronautics,2005.
    [185]邓自立.卡尔曼滤波与维纳滤波--现代时间序列分析方法[M].哈尔滨:哈尔滨工业大学出版社,2001.
    [186]Barana G,Tsuna I.A new method for computing Lyapunov exponents[J].Physica LetterA,1993,175:421-427.
    [187]Wolf A,Swift J B,Swinney H L,Vastano J A.Determining Lyapunov exponents froma time series [J].Physica,1985,16D:285-317.
    [188]王海燕,盛昭瀚.混沌时间序列相空间重构参数的选取方法[J].东南大学学报:自然科学版,2000,30(5):113-117.
    [189]孔超,李占才,王沁,等.一种基于FPGA的SOM神经网络算法的并行实现[J].计算机工程,2007,33(19):236-240
    [190]杨占华,杨燕.SOM神经网络算法的研究与进展[J].计算机工程,2006,32(16):200-203
    [191]韩敏.混沌时间预测理论与方法[M].北京:中国水利水电出版社,2007.
    [192]孙林,杨世元.基于LS-SVM的回采工作面瓦斯涌出量预测[J].煤炭学报,2008,33(12):1377-1380.

© 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