粒子群优化算法改进及其在煤层气产能预测中的应用研究
|
摘要
煤层气产能是衡量煤层气井潜在产气能力的综合指标，产能的高低直接影响煤层气项目的经济效益。因此建立有效的煤层气产能预测模型，对煤层气井的勘探开发有着重要的指导意义。
煤层气赋存于煤储层中，其产出过程由多个地质因素决定且各因素之间关系复杂，难于建立精确的数学表达式来描述其动态的生产过程。因此本论文采用目前广泛应用于预测控制等领域的支持向量回归机以及改进的粒子群优化算法来建立地质因素与产能之间的非线性函数映射关系，以实现对煤层气井产能进行预测及控制的目的。
支持向量回归机模型的建立不仅需要一定数量的样本数据进行训练和测试，同时为了建立高质量的预测模型，需要对模型中的参数设定最优的取值，因此选用粒子群优化算法对参数进行优化。
粒子群优化算法目前已经广泛地应用于各个领域，但是由于它自身的进化特点导致其在寻优过程中容易陷入局部收敛。为了解决该算法易于陷入局部收敛的问题，本文主要提出了三个改进的粒子群优化算法。
（1）基于子维进化的粒子群优化算法从标准粒子群优化算法的进化策略入手，将种群中粒子的进化策略从粒子的整体进化改变为粒子的每一维依次进化。同时当种群陷入局部收敛时，采取对多样性较差的子维进行重新初始化的操作。无论是对简单的单峰函数还是复杂的多峰函数进行优化，相较于标准粒子群优化算法该算法均具有较好的寻优性能。
（2）基于免疫机制的混合粒子群优化算法融合了人工免疫算法和基于子维进化的粒子群优化算法，将进化过程分成两个阶段，第一阶段采取人工免疫优化算法进行全局寻优，为下一阶段的寻优提供质量较高的初始种群。第二阶段采取基于子维进化的粒子群优化算法在质量较高的初始种群的基础上进行进化寻优，因此该算法具有更高的寻优效率。
（3）多种群协同进化的粒子群优化算法在Agent的协同作用下，分别由人工免疫算法、混沌算法，子维进化的粒子群优化算法同时进化，在粒子群算法陷入局部收敛时，共享其他两个算法的最优值，以较高的质量跳出局部收敛，为进一步的寻优工作打下良好的基础，同样该算法也具有更高的寻优效率。
通过标准数据集Boston Housing作为数据样本，将两种改进的混合粒子群算法应用于优化支持向量回归机模型中的参数，结果表明多种群协同进化的粒子群优化算法更适用于优化模型参数。
通过选定沁水盆地南部樊庄区块的20口煤层气垂直井的相关数据，利用改进的粒子群优化算法优化支持向量回归机，建立煤层气产能预测模型，并与BP神经网络以及支持向量回归机的预测结果进行比较，结果表明改进的粒子群优化算法优化支持向量回归机建立的模型具有更高的预测精度。同时根据20组样本数据对参与建立模型的5个地质因素分别进行了实验，分析了它们对产能的影响。
CBMproductivity is the comprehensive indicatorfor measuring potential gasproduction of CBM wells, while the productivity directly affects the economicbenefits of CBM project. Therefore, development of effective CBM productivityprediction model has important guiding significance to the exploration anddevelopment of CBM Wells.
CBM is saved in the coal reservoir, and its productivity is determined by manygeological factors, and the relationship is complex, so it is difficult to establishaccurate mathematical expressions to describe the dynamic process. This paper adoptssupport vector regression machine which is widely used in predictive control andother areas currently and the improved Particle Swarm Optimization Algorithm tocreate the nonlinear function mapping relationship between geological factors andproductivity, so as to realize prediction and control of CBM well productivity.
The development of support vector regression machine model requires a certainamount of sample data for the training and test of structure. In order to develop thehigh quality prediction model, it is required to set the optimum value of theparameters in the model. Therefore, in order to optimize the parameters in the model,particle swarm optimization algorithm is selected for the optimization of parameters.
Although particle swarm optimization algorithm is widely used in various fields,its evolution characteristics easily lead to local convergence. In order to solve theproblem that the algorithm easily falls into local convergence, this paper basicallyproposes three improved particle swarm optimization algorithms.
Particle swarm optimization based on the evolution of sub-dimensions startsfrom the evolutionary strategy of standard particle swarm optimization algorithm, andit changes the evolutionary strategy of particles of the population from overallevolution of the particles to each dimension of the particles for successive evolution.When the particle is trapped in local convergence, the sub-dimensions with poordiversity valueis are reinitialized. Regardless of whether they are used in simpleunimodal function or complex multimodal function optimization, compared withStandard Particle Swarm Optimization Algorithm, this algorithm has betteroptimization performance.
Hybrid Particle Swarm Optimization based on immune mechanism integratesArtificial Immune Algorithm and Particle Swarm Optimization Algorithm which is based on sub-dimensional evolution, the evolution process is divided into twostages.The first stage is to use Artificial Immune Optimization Algorithm for globaloptimization, so as to provide high quality initial population for the next phaseoptimization. The second stage is to use Particle Swarm Optimization Algorithmwhich is based on sub-dimensional evolution for evolutionary optimization based onmultiple high quality initial population, Therefore, it has higher efficiency ofoptimization.
Hybrid particle swarm optimization algorithm of multiple-populationCooperating evolution can be evolved at the same time by Artificial ImmuneAlgorithm, Chaos Algorithm and Particle Swarm Optimization Algorithm of sub-imensional evolution. Agent records current global optimal value obtained from thesethree algorithms. When Particle Swarm Optimization Algorithm gets into localconvergence, it jumps out of local convergence with high quality through the recordedcurrent global optimal value, so as to lay a good foundation for further optimizationwork. Meanwhile, the algorithm also has higher efficiency of optimization.
The standard data set Boston Housing is selected as data samples. Two improvedhybrid particle swarm algorithms are applied to optimizing support vector regressionmachine parameters.The results show that the Particle Swarm Optimization Algorithmof multiple-population synergy is more applicable for optimizing model parameters.
Through selecting20groups of related data for the20CBM vertical wells ofFanzhuang block to the south of Qinshui basin o develop CBM productivityprediction model with the Particle Swarm Optimization Algorithm Optimizationoptimized by using the support vector machine regression model. Compares with theprediction result of BP neural network and support vector regression machine, theresults show that the improved Particle Swarm Optimization Algorithm Optimizationand support vector machine regression model has higher precision of prediction.Meanwhile, five geological factors which are involved in model development aretested respectively according to the20groups of sample data, the impact of fivegeological factors on CBM productivity are analyzed.
煤层气赋存于煤储层中，其产出过程由多个地质因素决定且各因素之间关系复杂，难于建立精确的数学表达式来描述其动态的生产过程。因此本论文采用目前广泛应用于预测控制等领域的支持向量回归机以及改进的粒子群优化算法来建立地质因素与产能之间的非线性函数映射关系，以实现对煤层气井产能进行预测及控制的目的。
支持向量回归机模型的建立不仅需要一定数量的样本数据进行训练和测试，同时为了建立高质量的预测模型，需要对模型中的参数设定最优的取值，因此选用粒子群优化算法对参数进行优化。
粒子群优化算法目前已经广泛地应用于各个领域，但是由于它自身的进化特点导致其在寻优过程中容易陷入局部收敛。为了解决该算法易于陷入局部收敛的问题，本文主要提出了三个改进的粒子群优化算法。
（1）基于子维进化的粒子群优化算法从标准粒子群优化算法的进化策略入手，将种群中粒子的进化策略从粒子的整体进化改变为粒子的每一维依次进化。同时当种群陷入局部收敛时，采取对多样性较差的子维进行重新初始化的操作。无论是对简单的单峰函数还是复杂的多峰函数进行优化，相较于标准粒子群优化算法该算法均具有较好的寻优性能。
（2）基于免疫机制的混合粒子群优化算法融合了人工免疫算法和基于子维进化的粒子群优化算法，将进化过程分成两个阶段，第一阶段采取人工免疫优化算法进行全局寻优，为下一阶段的寻优提供质量较高的初始种群。第二阶段采取基于子维进化的粒子群优化算法在质量较高的初始种群的基础上进行进化寻优，因此该算法具有更高的寻优效率。
（3）多种群协同进化的粒子群优化算法在Agent的协同作用下，分别由人工免疫算法、混沌算法，子维进化的粒子群优化算法同时进化，在粒子群算法陷入局部收敛时，共享其他两个算法的最优值，以较高的质量跳出局部收敛，为进一步的寻优工作打下良好的基础，同样该算法也具有更高的寻优效率。
通过标准数据集Boston Housing作为数据样本，将两种改进的混合粒子群算法应用于优化支持向量回归机模型中的参数，结果表明多种群协同进化的粒子群优化算法更适用于优化模型参数。
通过选定沁水盆地南部樊庄区块的20口煤层气垂直井的相关数据，利用改进的粒子群优化算法优化支持向量回归机，建立煤层气产能预测模型，并与BP神经网络以及支持向量回归机的预测结果进行比较，结果表明改进的粒子群优化算法优化支持向量回归机建立的模型具有更高的预测精度。同时根据20组样本数据对参与建立模型的5个地质因素分别进行了实验，分析了它们对产能的影响。
CBMproductivity is the comprehensive indicatorfor measuring potential gasproduction of CBM wells, while the productivity directly affects the economicbenefits of CBM project. Therefore, development of effective CBM productivityprediction model has important guiding significance to the exploration anddevelopment of CBM Wells.
CBM is saved in the coal reservoir, and its productivity is determined by manygeological factors, and the relationship is complex, so it is difficult to establishaccurate mathematical expressions to describe the dynamic process. This paper adoptssupport vector regression machine which is widely used in predictive control andother areas currently and the improved Particle Swarm Optimization Algorithm tocreate the nonlinear function mapping relationship between geological factors andproductivity, so as to realize prediction and control of CBM well productivity.
The development of support vector regression machine model requires a certainamount of sample data for the training and test of structure. In order to develop thehigh quality prediction model, it is required to set the optimum value of theparameters in the model. Therefore, in order to optimize the parameters in the model,particle swarm optimization algorithm is selected for the optimization of parameters.
Although particle swarm optimization algorithm is widely used in various fields,its evolution characteristics easily lead to local convergence. In order to solve theproblem that the algorithm easily falls into local convergence, this paper basicallyproposes three improved particle swarm optimization algorithms.
Particle swarm optimization based on the evolution of sub-dimensions startsfrom the evolutionary strategy of standard particle swarm optimization algorithm, andit changes the evolutionary strategy of particles of the population from overallevolution of the particles to each dimension of the particles for successive evolution.When the particle is trapped in local convergence, the sub-dimensions with poordiversity valueis are reinitialized. Regardless of whether they are used in simpleunimodal function or complex multimodal function optimization, compared withStandard Particle Swarm Optimization Algorithm, this algorithm has betteroptimization performance.
Hybrid Particle Swarm Optimization based on immune mechanism integratesArtificial Immune Algorithm and Particle Swarm Optimization Algorithm which is based on sub-dimensional evolution, the evolution process is divided into twostages.The first stage is to use Artificial Immune Optimization Algorithm for globaloptimization, so as to provide high quality initial population for the next phaseoptimization. The second stage is to use Particle Swarm Optimization Algorithmwhich is based on sub-dimensional evolution for evolutionary optimization based onmultiple high quality initial population, Therefore, it has higher efficiency ofoptimization.
Hybrid particle swarm optimization algorithm of multiple-populationCooperating evolution can be evolved at the same time by Artificial ImmuneAlgorithm, Chaos Algorithm and Particle Swarm Optimization Algorithm of sub-imensional evolution. Agent records current global optimal value obtained from thesethree algorithms. When Particle Swarm Optimization Algorithm gets into localconvergence, it jumps out of local convergence with high quality through the recordedcurrent global optimal value, so as to lay a good foundation for further optimizationwork. Meanwhile, the algorithm also has higher efficiency of optimization.
The standard data set Boston Housing is selected as data samples. Two improvedhybrid particle swarm algorithms are applied to optimizing support vector regressionmachine parameters.The results show that the Particle Swarm Optimization Algorithmof multiple-population synergy is more applicable for optimizing model parameters.
Through selecting20groups of related data for the20CBM vertical wells ofFanzhuang block to the south of Qinshui basin o develop CBM productivityprediction model with the Particle Swarm Optimization Algorithm Optimizationoptimized by using the support vector machine regression model. Compares with theprediction result of BP neural network and support vector regression machine, theresults show that the improved Particle Swarm Optimization Algorithm Optimizationand support vector machine regression model has higher precision of prediction.Meanwhile, five geological factors which are involved in model development aretested respectively according to the20groups of sample data, the impact of fivegeological factors on CBM productivity are analyzed.
引文
[1]戴金星.我国煤成气资源勘探开发和研究的重大意义[J].天然气工业,1993，13(2):7-12.
[2]田永东.沁水盆地南部煤储层参数及其对煤层气井产能的控制[D].北京:中国矿业大学（北京）图书馆,2009.
[3]李世臻,曲英杰.美国煤层气和页岩气勘探开发现状及对我国的启示[J].中国矿业,2010，19(12):17-21.
[4]煤层气国外研究现状[EB/OL]. http://www.docin.com/p-456699138.html.
[5]姚国欣,王建明.国外煤层气生产概况及对加速我国煤层气产业发展的思考[J].中外能源,2010,15(04):25-33.
[6]罗金辉.煤层气运移LBM模型与井间干扰模拟研究[D].徐州：中国矿业大学图书馆,2012.
[7]陈玉华.基于DEA的煤层气经济评价模型研究[D].徐州：中国矿业大学图书馆,2010.
[8]国家发展和改革委员会,国家能源局.煤层气（煤矿瓦斯）开发利用“十二五”规划[R].2011.
[9] Gandhi A B, Joshi J B, Jayaraman V K, et al. Development of support vector regression(SVR)-based correlation for prediction of overall gas hold-up in bubble column reactors forvarious gas–liquid systems[J]. Chemical Engineering Science,2007,62(24):7078-7089.
[10] R K G, M E T. A survey of mathematical models related to methane production from coalseams, Part I: Empirical&equilibrium sorption models[C]: Proceedings of the1989CoalbedMethane Symposium, the University of Alabama/Tuscaloosa,1989:125-138.
[11] M A E. Gas emission from broken coal: an experimental and theoretical investigation[J].International Journal of Rock Mechanics and Mining sciences,1968(5):474-494.
[12] R K G, M E T. A survey of mathematical models related to methane production from coalseams, Part II: Non-equilibrium sorption models[C]: Proceedings of the1989CoalbedMethane Symposium, the University of Alabama/Tuscaloosa,1989.139-153.
[13]周世宁,林柏泉.煤层瓦斯赋存与流动理论[M].北京:煤炭工业出版社,1999.
[14]郭勇义,周世宁.煤层瓦斯一维流场流动规律的完全解[J].中国矿业学院学报,1984(02):22-31.
[15]谭学术,袁静.矿井煤层真实瓦斯渗流方程的研究[J].重庆建筑工程学院学报,1986(01):106-112.
[16]余楚新,鲜学福,谭学术.煤层瓦斯流动理论及渗流控制方程的研究[J].重庆大学学报(自然科学版),1989,12(05):1-10.
[17]赵阳升.煤体-瓦斯耦合理论及其应用[D].上海：同济大学图书馆,1992.
[18]章梦涛,潘一山,梁冰等.煤岩流体力学[M].北京:科学出版社,1995.
[19]孙可明,梁冰,王锦山.煤层气开采中两相流阶段的流固耦合渗流[J].辽宁工程技术大学学报(自然科学版),2001,20(01):36-39.
[20]李梦溪,刘庆昌,张建国,等.构造模式与煤层气井产能的关系——以晋城煤区为例[J].天然气工业,2010，30(11):10-13.
[21]张艳玉,孙晓飞,尚凡杰,等.沁水煤层气井产能预测及其影响因素研究[J].石油天然气学报,2012,34(11):118-122.
[22]蒋裕强,李成勇,李志军.基于模糊综合评判和BP神经网络的气井产能预测新模型[J].油气田地面工程,2009,28(10):5-7.
[23]叶双江,姜汉桥,陈民锋.基于灰色关联与神经网络技术的水平井产能预测[J].大庆石油学院学报,2009，33(03):53-55.
[24]童凯军,单钰铭,李海鹏,等.支持向量回归机在气井产能预测中的应用[J].新疆石油地质,2008,29(03):382-384.
[25]吕玉民,汤达祯,李治平,等.煤层气井动态产能拟合与预测模型[J].煤炭学报,2011，36(09):1481-1485.
[26]任广磊,李治平,张跃磊,等.渗透率应力敏感性对煤层气井产能的影响[J].煤炭科学技术,2012，40(04):104-107.
[27] Yong-guo Y, Yu-hua C, Yong Q, et al. Monte-Carlo Method for Coalbed Methane ResourceAssessment in Key Coal Mining Areas of China[J]. Journal of China University ofGeosciences,2008,19(4):429-435.
[28] Chen Y, Yang Y, Luo J. Uncertainty Analysis of Coalbed Methane Economic Assessmentwith Montecarlo Method[J]. Procedia Environmental Sciences,2012(12):640-645.
[29] Jinhui L, Yongguo Y, Yuhua C. Optimizing the drilled well patterns for CBM recovery vianumerical simulations and data envelopment analysis[J]. International Journal of MiningScience and Technology,2012,22(4):503-507.
[30] Karacan C. Development and application of reservoir models and artificial neuralnetworks for optimizing ventilation air requirements in development mining of coal seams[J].International Journal of Coal Geology,2007,72(3–4):221-239.
[31] Karacan C. Modeling and prediction of ventilation methane emissions of U.S. longwallmines using supervised artificial neural networks[J]. International Journal of Coal Geology,2008,73(3–4):371-387.
[32] Karacan C. Forecasting gob gas venthole production performances using intelligentcomputing methods for optimum methane control in longwall coal mines[J]. InternationalJournal of Coal Geology,2009,79(4):131-144.
[33] Vapnik V. The Nature of Statistieal Learning Theory[M]. New York: SPringer-Verla,1995.
[34] Vapnik V. Statistical Learning Theory[M]. New York: John Wiley&Son,1998.
[35] Kecman V. Learning and Soft Computing: Support Vector Machines, Neural Networks, andFuzzy Logic Models[M]. MIT Press,2001.
[36] Hadzic I, Kecman V. Support vector machines trained by linear programming: theory andapplication in image compression and data classification[C]: Proceedings of the5th Seminaron Neural Network Applications in Electrical Engineering, Belgrade,2000:18-23.
[37] Yuh-Jye L, Su-Yun H. Reduced Support Vector Machines: A Statistical Theory[J]. NeuralNetworks, IEEE Transactions on,2007,18(1):1-13.
[38] Iplikci S. Support vector machines based neuro-fuzzy control of nonlinear systems[J].Neurocomputing,2010,73(10–12):2097-2107.
[39] Chaudhuri A, De K. Fuzzy Support Vector Machine for bankruptcy prediction[J]. AppliedSoft Computing,2011,11(2):2472-2486.
[40]唐浩,廖与禾,孙峰,等.具有模糊隶属度的模糊支持向量机算法[J].西安交通大学学报,2009，43(07):40-43.
[41] Turkoglu I, Avci E. Comparison of wavelet-SVM and wavelet-adaptive network basedfuzzy inference system for texture classification[J]. Digital Signal Processing,2008,18(1):15-24.
[42] Du P, Tan K, Xing X. Wavelet SVM in Reproducing Kernel Hilbert Space for hyperspectralremote sensing image classification[J]. Optics Communications,2010,283(24):4978-4984.
[43] Gumus E, Kilic N, Sertbas A, et al. Evaluation of face recognition techniques using PCA,wavelets and SVM[J]. Expert Systems with Applications,2010,37(9):6404-6408.
[44] Fonseca E S, Guido R C, Scalassara P R, et al. Wavelet time-frequency analysis and leastsquares support vector machines for the identification of voice disorders[J]. Computers inBiology and Medicine,2007,37(4):571-578.
[45] Ismail S, Shabri A, Samsudin R. A hybrid model of self-organizing maps (SOM) and leastsquare support vector machine (LSSVM) for time-series forecasting[J]. Expert Systems withApplications,2011,38(8):10574-10578.
[46] Carvalho B P R, Braga A P. IP-LSSVM: A two-step sparse classifier[J]. Pattern RecognitionLetters,2009,30(16):1507-1515.
[47] Suykens J A K, Vandewalle J. Recurrent least squares support vector machines[J]. IEEETransactions on Circuits and Systems I: Fundamental Theory and Applications,2000,47(7):1109-1114.
[48] Suykens J A K, Lukas L, Vandewalle J. Sparse approximation using least squares supportvector machines[C]: The2000IEEE International Symposium on Circuits and SystemsProceedings, Geneva,2000:757-760.
[49] K. R. Müller A S G R. Predicting time series with support vector machines[C]: InProceedings of the International Conference on Artificial Neural Networks,1997:999-1004.
[50] Francis E. H. Tay L C. Application of support vector machines in financial time seriesforecasting[J]. Omega,2001,29(4):309-317.
[51] Gretton A, Doucet A, Herbrich R, et al. Support vector regression for black-box systemidentification[C]: Proceedings of the11th IEEE Signal Processing Workshop on StatisticalSignal Processing,2001:341-344.
[52] S C, M W. Seeking multi-thresholds directly from support vectors for imagesegmentation[J]. Neurocomputing,2005,14(1):335-344.
[53] Suykens J A K, Vandewalle J, De Moor B. Optimal control by least squares support vectormachines[J]. Neural Networks,2001,14(1):23-35.
[54] Yanjie H, Juanjuan P. Financial crisis early-warning based on support vector machine[C]:IEEE International Joint Conference on Neural Networks, Hong Kong,2008:2435-2440.
[55] M M. Support vector machines for short-term electrical load forecasting[J]. InternationalJournal of Energy Research,2002,26(4):335-345.
[56] Hong W. Electric load forecasting by seasonal recurrent SVR (support vector regression)with chaotic artificial bee colony algorithm[J]. Energy,2011,36(9):5568-5578.
[57] Hong W. Application of chaotic ant swarm optimization in electric load forecasting[J].Energy Policy,2010,38(10):5830-5839.
[58] Hong W. Chaotic particle swarm optimization algorithm in a support vector regressionelectric load forecasting model[J]. Energy Conversion and Management,2009,50(1):105-117.
[59] Hong W. Electric load forecasting by support vector model[J]. Applied MathematicalModelling,2009,33(5):2444-2454.
[60] Meiying Q, Xiaoping M, Jianyi L, et al. Time-series gas prediction model using LS-SVRwithin a Bayesian framework[J]. Mining Science and Technology (China),2011,21(1):153-157.
[61] Hong W. Traffic flow forecasting by seasonal SVR with chaotic simulated annealingalgorithm[J]. Neurocomputing,2011,74(12–13):2096-2107.
[62] Gandhi A B, Joshi J B, Kulkarni A A, et al. SVR-based prediction of point gas hold-up forbubble column reactor through recurrence quantification analysis of LDA time-series[J].International Journal of Multiphase Flow,2008,34(12):1099-1107.
[63] Castro-Neto M, Jeong Y, Jeong M, et al. Online-SVR for short-term traffic flow predictionunder typical and atypical traffic conditions[J]. Expert Systems with Applications,2009,36(3,Part2):6164-6173.
[64] Yang Y, Fuli R, Huiyou C, et al. SVR mathematical model and methods for saleprediction[J]. Journal of Systems Engineering and Electronics,2007,18(4):769-773.
[65] Mohandes M A. Modeling global solar radiation using Particle Swarm Optimization(PSO)[J]. Solar Energy,2012,86(11):3137-3145.
[66] Xue L, Cai J, Li J, et al. Application of Particle Swarm Optimization (PSO) Algorithm toDetermine Dichlorvos Residue on the Surface of Navel Orange with Vis-NIRSpectroscopy[J]. Procedia Engineering,2012,29(0):4124-4128.
[67] Khouadjia M R, Sarasola B, Alba E, et al. A comparative study between dynamic adaptedPSO and VNS for the vehicle routing problem with dynamic requests[J]. Applied SoftComputing,2012,12(4):1426-1439.
[68] Behrang M A, Assareh E, Noghrehabadi A R, et al. New sunshine-based models forpredicting global solar radiation using PSO (particle swarm optimization) technique[J].Energy,2011,36(5):3036-3049.
[69] Taher S A, Karimian A, Hasani M. A new method for optimal location and sizing ofcapacitors in distorted distribution networks using PSO algorithm[J]. Simulation ModellingPractice and Theory,2011,19(2):662-672.
[70] Clerc M, Kennedy J. The particle swarm-explosion, stability, and convergence in amultidimensional complex space[J]. IEEE Transactions on Evolutionary Computation,2002,6(1):58-73.
[71]唐贤伦.混沌粒子群优化算法理论及应用[D].重庆：重庆大学图书馆,2007.
[72] Ozcan E, Mohan C K. Particle swarm optimization: surfing the waves[C]: Proceedings ofthe1999Congress on Evolutionary Computation, Washington, DC,1999:1943-1944.
[73] Yuhui S, Eberhart R. A modified particle swarm optimizer[C]: The1998IEEE InternationalConference on Evolutionary Computation Proceedings, Anchorage, AK,1998:69-73.
[74]崔红梅,朱庆保.微粒群算法的参数选择及收敛性分析[J].计算机工程与应用,2007，43(23):89-91.
[75]王丽,王晓凯.一种非线性改变惯性权重的粒子群算法[J].计算机工程与应用,2007，43(04):47-48.
[76]延丽平,曾建潮.具有自适应随机惯性权重的PSO算法[J].计算机工程与设计,2006，27(24):4677-4679.
[77]刘建华,樊晓平,瞿志华.一种惯性权重动态调整的新型粒子群算法[J].计算机工程与应用,2007，43(07):68-70.
[78] Yuhui S, Eberhart R C. Fuzzy adaptive particle swarm optimization[C]: Proceedings of the2001Congress on Evolutionary Computation,2001:101-106.
[79] Ratnaweera A, Halgamuge S, Watson H C. Self-organizing hierarchical particle swarmoptimizer with time-varying acceleration coefficients[J]. IEEE Transactions on EvolutionaryComputation,2004,8(3):240-255.
[80]陈水利,蔡国榕,郭文忠,等. PSO算法加速因子的非线性策略研究[J].长江大学学报(自科版)理工卷,2007，4(04):1-4.
[81]田玉玲,杨朋樽.基于KRTG的动态拓扑结构的粒子群算法研究[J].计算机与数字工程,2010，38(02):25-27.
[82]韩立娜,熊盛武.基于动态邻域的粒子群算法的研究[J].计算机工程与应用,2009，45(06):60-62.
[83]王雪飞,王芳,邱玉辉.一种具有动态拓扑结构的粒子群算法研究[J].计算机科学,2007，34(03):205-207.
[84]Urade H S, Patel R. Dynamic Particle Swarm Optimization to Solve Multi-objectiveOptimization Problem[J]. Procedia Technology,2012,6(0):283-290.
[85] Liang J J, Suganthan P N. Dynamic multi-swarm particle swarm optimizer[C]:2005IEEESwarm Intelligence Symposium Proceedings,2005:124-129.
[86] Yu S, Zhu K, Zhang X. Energy demand projection of China using a path-coefficient analysisand PSO–GA approach[J]. Energy Conversion and Management,2012,53(1):142-153.
[87] Nanda S J, Panda G. Automatic clustering algorithm based on multi-objective ImmunizedPSO to classify actions of3D human models[J]. Engineering Applications of ArtificialIntelligence,2012(0).
[88] Liu B, Wang L, Jin Y. An effective hybrid PSO-based algorithm for flow shop schedulingwith limited buffers[J]. Computers&Operations Research,2008,35(9):2791-2806.
[89] Cai X, Zhang N, Venayagamoorthy G K, et al. Time series prediction with recurrent neuralnetworks trained by a hybrid PSO–EA algorithm[J]. Neurocomputing,2007,70(13–15):2342-2353.
[90] Guo Q, Yu H, Xu A. A hybrid PSO-GD based intelligent method for machine diagnosis[J].Digital Signal Processing,2006,16(4):402-418.
[91] Lu H, Sriyanyong P, Song Y H, et al. Experimental study of a new hybrid PSO withmutation for economic dispatch with non-smooth cost function[J]. International Journal ofElectrical Power&Energy Systems,2010,32(9):921-935.
[92] Chen K, Li T, Cao T. Tribe-PSO: A novel global optimization algorithm and its applicationin molecular docking[J]. Chemometrics and Intelligent Laboratory Systems,2006,82(1–2):248-259.
[93] Madhubanti Maitra A C. A hybrid cooperative–comprehensive learning based PSOalgorithm for image segmentation using multilevel thresholding[J]. Expert Systems withApplications,2008,34(2):1341-1350.
[94] Nima Hamta S M T F. A hybrid PSO algorithm for a multi-objective assembly linebalancing problem with flexible operation times, sequence-dependent setup times andlearning effect[J]. International Journal of Production Economics,2013,141(1):99-111.
[95] Niknam T, Azadfarsani E, Jabbari M. A new hybrid evolutionary algorithm based on newfuzzy adaptive PSO and NM algorithms for Distribution Feeder Reconfiguration[J]. EnergyConversion and Management,2012,54(1):7-16.
[96] E. B, M. D, Theraulaz G. Swarm Intelligence: Form Natural to Artificial Systems[M].Oxford University Press,1999.
[97] A. C, M. D, V. M. Distributed Optimization by Ant Colonies[C]: Proceedings of the1stEuropean Conf on Artificial Life,1991:134-142.
[98]李晓磊,邵之江,钱积新.一种基于动物自治体的寻优模式:鱼群算法[J].系统工程理论与实践,2002(11):32-38.
[99] Passino K M. Biomimicry of bacterial foraging for distributed optimization and control[J].Control Systems, IEEE,2002,22(3):52-67.
[100] Karaboga D, Basturk B. On the performance of artificial bee colony (ABC) algorithm[J].Applied Soft Computing,2008,8(1):687-697.
[101] Eberhart R, Kennedy J. A new optimizer using particle swarm theory[C]: Proceedings of theSixth International Symposium on Micro Machine and Human Science, Nagoya,1995:39-43.
[102] M. A. Potter K A D J. A cooperative coevolutionary approach to function optimization[C]:The Third Parallel Problem Solving From Nature, Berlin, Germany,1994:249-257.
[103] van den Bergh F, Engelbrecht A P. A Cooperative approach to particle swarmoptimization[J]. IEEE Transactions on Evolutionary Computation,2004,8(3):225-239.
[104]付国江,王少梅,刘舒燕,等.含维变异算子的粒子群算法[J].武汉大学学报(工学版),2005，38(9):79-84.
[105] Xu H, Yang Y, Mao L, et al. Improvement on PSO with Dimension Update and Mutation[J].JOURNAL OF SOFTWARE,2013,8(4):827-833.
[106] Eberhart R C, Yuhui S. Tracking and optimizing dynamic systems with particle swarms[C]:Proceedings of the2001Congress on Evolutionary Computation,2001:94-100.
[107]陈宇,孙帆,张健.基于自适应权重粒子群的电容层析成像边界灰度补偿算法[J].哈尔滨理工大学学报,2010，15(6)：44-49.
[108] Iwamatsu M. Locating All the Global Minima Using Multi-Species Particle SwarmOptimizer: The Inertia Weight and The Constriction Factor Variants[C]: IEEE Congress onEvolutionary Computation, Vancouver, BC,2006:816-822.
[109] Jang-Ho S, Chang-Hwan I, Chang-Geun H, et al. Multimodal function optimization basedon particle swarm optimization[J]. IEEE Transactions on Magnetics,2006,42(4):1095-1098.
[110] Kitayama S, Yasuda K. A method for mixed integer Programming problems by particleswarm optimization [J]. Electrical Engineering in Japan,2006,157(2):40-49.
[111] Farmer J D, Packard N H, Perelson A S. The immune system, adaptation, and machinelearning[J]. Physica D: Nonlinear Phenomena,1986,22(1–3):187-204.
[112] Leandro Nunes De Castro F J V Z. ARTIFICIAL IMMUNE SYSTEMS:PART I–BASICTHEORY AND APPLICATIONS[R].1999.
[113] Leandro Nunes De Castro F J V Z. Artificial Immune Systems: Part II–A Survey ofApplications[R].2000.
[114] Leandro Nunes De Castro F J V Z. The Clonal Selection Algorithm with EngineeringApplications[C]: Workshop Proceedings of GECCO, Las Vegas, USA,2000:36-37.
[115] de Castro L N, Von Zuben F J. Learning and optimization using the clonal selectionprinciple[J]. IEEE Transactions on Evolutionary Computation,2002,6(3):239-251.
[116] de Castro L N, Timmis J. An artificial immune network for multimodal functionoptimization[C]: Proceedings of the2002Congress on Evolutionary Computation,2002:699-704.
[117]葛红,毛宗源.免疫算法几个参数的研究[J].华南理工大学学报(自然科学版),2002，30(12):15-18.
[118]吴秋逸,焦李成,李阳阳,等.自适应量子免疫克隆算法及其收敛性分析[J].模式识别与人工智能,2008，21(05):592-597.
[119]吴秋逸,焦李成,魏峻,等.量子协同免疫动态优化算法[J].模式识别与人工智能,2009，22(06):862-868.
[120] Acan A. Clonal selection algorithm with operator multiplicity[C]: Congress on EvolutionaryComputation,2004:1909-1915.
[121]凌军,曹阳,尹建华,等.基于小生境技术的多样性抗体生成算法[J].电子学报,2003，31(08):1130-1133.
[122] Timmis J, Edmonds C, Kelsey J. Assessing the performance of two immune inspiredalgorithms and a hybrid genetic algorithm for function optimisation[C]: Congress onEvolutionary Computation,2004:1044-1051.
[123] M O, S F. How the immune system generates diversity: Pathogen space coverage withrandom and evolved antibody libraries[C]: Genetic and Evolutionary ComputationConference,1999:1651-1656.
[124]焦李成,杜海峰.人工免疫系统进展与展望[J].电子学报,2003，31(10):1540-1548.
[125]罗印升,李人厚,张雷,等.人工免疫算法在函数优化中的应用[J].西安交通大学学报,2003，37(08):840-843.
[126] Xu H, Yang Y, Mao L. Study and Improvement on Particle Swarm Algorithm[J].JOURNAL OF COMPUTERS,2013,8(4):937-942.
[127] Potter M A, De Jong K A. Cooperative coevolution:An architecture for evolving coadaptedsubcomponents[J]. Evolutionary Computation,2000,8(1):1-29.
[128]郭圆平.动态种群规模的协同进化算法模型、理论与应用[D].北京：中国科学技术大学图书馆,2008.
[129] Ficici S G. Solution concepts in coevolutionary algorithms[D]. Brandeis University,2004.
[130] Cowling P I, Naveed M H, Hossain M A. A Coevolutionary Model for The Virus Game[C]:IEEE Symposium on Computational Intelligence and Games, Reno, NV,2006:45-51.
[131] Pratas N, Prasad N R, Rodrigues A, et al. Cooperative spectrum sensing: State of the artreview[C]:2nd International Conference on Wireless Communication, Vehicular Technology,Chennai,2011:1-6.
[132] Jun-Yuan T, De-Sheng L. Cooperative Strategy Learning in Multi-Agent Environment withContinuous State Space[C]:2006International Conference on Machine Learning andCybernetics, Dalian, China,2006:2107-2111.
[133] Zhao J, Weiyi L, Jian J. State-Clusters shared cooperative multi-agent reinforcementlearning[C]: Asian Control Conference, Hong Kong,2009:129-135.
[134] Kleeman M P, Lamont G B. Coevolutionary Multi-Objective EAs: The Next Frontier?[C]:IEEE Congress on Evolutionary Computation,2006:1726-1735.
[135] Tan K C, Yang Y J, Goh C K. A distributed Cooperative coevolutionary algorithm formultiobjective optimization[J].IEEE Transactions on Evolutionary Computation,2006,10(5):527-549.
[136] Wloldridge M, Jenning N R. Intelligent Agent:Theory and Pracitce[J]. The KnowledgeEngineering Review,1995,2(10):115-152.
[137]孙辉,刘前进.一种新型MAS的配电网保护和控制方案[J].电力系统保护与控制,2010，38(16):24-29.
[138]蒋国银,胡斌,王缓缓.基于MAS的移动服务链协同工作机制研究[J].管理工程学报,2010，24(01):82-89.
[139] García Ansola P, de Las Morenas J, García A, et al. Distributed decision support system forairport ground handling management using WSN and MAS[J]. Engineering Applications ofArtificial Intelligence,2012,25(3):544-553.
[140]严建峰,李伟华,刘明.基于混合蚁群算法的MAS任务分配[J].计算机应用研究,2009，26(01):68-70.
[141] Lorenz E N. Deterministic non-period flow[J]. Atmos. Sci.,1963,20:130-141.
[142]吕金虎,陆君安,陈士华.混沌时间序列分析及其应用[M].武汉:武汉大学出版社,2002.
[143] Slutzky M W, Cvitanovic P, Mogul D J. Manipulating epileptiform bursting in the rathippocampus using chaos control and adaptive techniques[J].IEEE Transactions onBiomedical Engineering,2003,50(5):559-570.
[144] Cong-Hui H, Chia-Hung L, Chao-Lin K. Chaos Synchronization-Based Detector forPower-Quality Disturbances Classification in a Power System[J].IEEE Transactions onPower Delivery,2011,26(2):944-953.
[145] Ma X, Guo L. Optimization of PID Parameters for Mine Hoisting DTC System Based onChaos Theory[C]: International Conference on Artificial Intelligence and ComputationalIntelligence, Shanghai,2009:128-131.
[146]罗金辉,杨永国,秦勇,等.基于组合权重的煤层气有利区块模糊优选[J].煤炭学报,2012，37(02):242-246.
[147]贾东立,张家树.基于混沌变异的小生境粒子群算法[J].控制与决策,2007，22(01):117-120.
[148]胥小波,郑康锋,李丹,等.新的混沌粒子群优化算法[J].通信学报,2012，33(01):24-30.
[149]陈如清,俞金寿.混沌粒子群混合优化算法的研究与应用[J].系统仿真学报,2008，20(03):685-688.
[150]袁晓辉,袁艳斌,王乘,等.一种新型的自适应混沌遗传算法[J].电子学报,2006，34(04):708-712.
[151] Aihara K. Chaos and Its Applications[J]. Procedia IUTAM,2012,5(0):199-203.
[152] Ding W. A New Method for Image Noise Removal using Chaos-PSO and Nonlinear ICA[J].Procedia Engineering,2011,24(0):111-115.
[153]杨永国,陈玉华.矿井涌水量混沌特征与预测[J].地球科学(中国地质大学学报),2009，34(02):258-262.
[154]徐慧,杨永国.多Agent协同处理模型的研究与设计[J].计算机工程,2010，36(05):67-69.
[155] Hui X, Yongguo Y. Research and Design on Dynamic Multi-agent Cooperative ProcessingModel[C]: International Conference on Web Information Systems and Mining, Shanghai,2009:432-436.
[156]邓乃扬,田英杰.支持向量机-理论、算法与拓展[M].北京:科学出版社,2009.
[157] Li J, Jia Y, Du Junping, et al. Optimal regularization parameters selection for Laplaciansupport vector machine[C]:27th Chinese Control Conference, Kunming,2008:464-468.
[158] Klaus S. Optimal parameter selection in support vector machines[J]. Journal of Industrialand Management Optimization,2005,1(4):465-476.
[159] de Miranda P B C, Prudencio R B C, Carvalho A C P L, et al. Combining a multi-objectiveoptimization approach with meta-learning for SVM parameter selection[C]:IEEEInternational Conference on Systems, Man, and Cybernetics (SMC), Seoul,2012:2909-2914.
[160] Abdi M J, Giveki D. Automatic detection of erythemato-squamous diseases usingPSO–SVM based on association rules[J]. Engineering Applications of Artificial Intelligence,2013,26(1):603-608.
[161] C. C C, J. L C. LIBSVM: A Library for Support Vector Machines (Version2.3)[EB/OL].http://www.csie.ntu.edu.tw/~cjlin/papers/libsvm.pdf.
[162]闫宝珍.沁水盆地煤层气富集机理及主控特征[D].北京：中国矿业大学（北京）图书馆,2008.
[163]贾承造等.煤层气资源储量评估方法[G].石油工业出版社,2007.
[164]陈振宏,王一兵,杨焦生,等.影响煤层气井产量的关键因素分析——以沁水盆地南部樊庄区块为例[J].石油学报,2009，30(03):409-412.
[165]刘人和,刘飞,周文,等.沁水盆地煤岩储层特征及有利区预测[J].油气地质与采收率,2008，15(04):16-19.
[166]倪小明,苏现波,王庆伟,等.恩村井田煤层气垂直井产能地质主控因素分析[J].煤矿安全,2009(07):79-82.
[167]陶树,汤达祯,许浩,等.沁南煤层气井产能影响因素分析及开发建议[J].煤炭学报,2011，36(02):194-198.
[168]林然,倪小明,王延斌.山西沁水盆地樊庄区块煤层气高产区预测[J].高校地质学报,2012，18(03):558-562.
[169]王向浩,王延斌,袁钧,等.煤层气资源赋存条件与垂直井产能关系研究[J].煤炭科学技术,2012，40(12):104-105.
[2]田永东.沁水盆地南部煤储层参数及其对煤层气井产能的控制[D].北京:中国矿业大学（北京）图书馆,2009.
[3]李世臻,曲英杰.美国煤层气和页岩气勘探开发现状及对我国的启示[J].中国矿业,2010，19(12):17-21.
[4]煤层气国外研究现状[EB/OL]. http://www.docin.com/p-456699138.html.
[5]姚国欣,王建明.国外煤层气生产概况及对加速我国煤层气产业发展的思考[J].中外能源,2010,15(04):25-33.
[6]罗金辉.煤层气运移LBM模型与井间干扰模拟研究[D].徐州：中国矿业大学图书馆,2012.
[7]陈玉华.基于DEA的煤层气经济评价模型研究[D].徐州：中国矿业大学图书馆,2010.
[8]国家发展和改革委员会,国家能源局.煤层气（煤矿瓦斯）开发利用“十二五”规划[R].2011.
[9] Gandhi A B, Joshi J B, Jayaraman V K, et al. Development of support vector regression(SVR)-based correlation for prediction of overall gas hold-up in bubble column reactors forvarious gas–liquid systems[J]. Chemical Engineering Science,2007,62(24):7078-7089.
[10] R K G, M E T. A survey of mathematical models related to methane production from coalseams, Part I: Empirical&equilibrium sorption models[C]: Proceedings of the1989CoalbedMethane Symposium, the University of Alabama/Tuscaloosa,1989:125-138.
[11] M A E. Gas emission from broken coal: an experimental and theoretical investigation[J].International Journal of Rock Mechanics and Mining sciences,1968(5):474-494.
[12] R K G, M E T. A survey of mathematical models related to methane production from coalseams, Part II: Non-equilibrium sorption models[C]: Proceedings of the1989CoalbedMethane Symposium, the University of Alabama/Tuscaloosa,1989.139-153.
[13]周世宁,林柏泉.煤层瓦斯赋存与流动理论[M].北京:煤炭工业出版社,1999.
[14]郭勇义,周世宁.煤层瓦斯一维流场流动规律的完全解[J].中国矿业学院学报,1984(02):22-31.
[15]谭学术,袁静.矿井煤层真实瓦斯渗流方程的研究[J].重庆建筑工程学院学报,1986(01):106-112.
[16]余楚新,鲜学福,谭学术.煤层瓦斯流动理论及渗流控制方程的研究[J].重庆大学学报(自然科学版),1989,12(05):1-10.
[17]赵阳升.煤体-瓦斯耦合理论及其应用[D].上海：同济大学图书馆,1992.
[18]章梦涛,潘一山,梁冰等.煤岩流体力学[M].北京:科学出版社,1995.
[19]孙可明,梁冰,王锦山.煤层气开采中两相流阶段的流固耦合渗流[J].辽宁工程技术大学学报(自然科学版),2001,20(01):36-39.
[20]李梦溪,刘庆昌,张建国,等.构造模式与煤层气井产能的关系——以晋城煤区为例[J].天然气工业,2010，30(11):10-13.
[21]张艳玉,孙晓飞,尚凡杰,等.沁水煤层气井产能预测及其影响因素研究[J].石油天然气学报,2012,34(11):118-122.
[22]蒋裕强,李成勇,李志军.基于模糊综合评判和BP神经网络的气井产能预测新模型[J].油气田地面工程,2009,28(10):5-7.
[23]叶双江,姜汉桥,陈民锋.基于灰色关联与神经网络技术的水平井产能预测[J].大庆石油学院学报,2009，33(03):53-55.
[24]童凯军,单钰铭,李海鹏,等.支持向量回归机在气井产能预测中的应用[J].新疆石油地质,2008,29(03):382-384.
[25]吕玉民,汤达祯,李治平,等.煤层气井动态产能拟合与预测模型[J].煤炭学报,2011，36(09):1481-1485.
[26]任广磊,李治平,张跃磊,等.渗透率应力敏感性对煤层气井产能的影响[J].煤炭科学技术,2012，40(04):104-107.
[27] Yong-guo Y, Yu-hua C, Yong Q, et al. Monte-Carlo Method for Coalbed Methane ResourceAssessment in Key Coal Mining Areas of China[J]. Journal of China University ofGeosciences,2008,19(4):429-435.
[28] Chen Y, Yang Y, Luo J. Uncertainty Analysis of Coalbed Methane Economic Assessmentwith Montecarlo Method[J]. Procedia Environmental Sciences,2012(12):640-645.
[29] Jinhui L, Yongguo Y, Yuhua C. Optimizing the drilled well patterns for CBM recovery vianumerical simulations and data envelopment analysis[J]. International Journal of MiningScience and Technology,2012,22(4):503-507.
[30] Karacan C. Development and application of reservoir models and artificial neuralnetworks for optimizing ventilation air requirements in development mining of coal seams[J].International Journal of Coal Geology,2007,72(3–4):221-239.
[31] Karacan C. Modeling and prediction of ventilation methane emissions of U.S. longwallmines using supervised artificial neural networks[J]. International Journal of Coal Geology,2008,73(3–4):371-387.
[32] Karacan C. Forecasting gob gas venthole production performances using intelligentcomputing methods for optimum methane control in longwall coal mines[J]. InternationalJournal of Coal Geology,2009,79(4):131-144.
[33] Vapnik V. The Nature of Statistieal Learning Theory[M]. New York: SPringer-Verla,1995.
[34] Vapnik V. Statistical Learning Theory[M]. New York: John Wiley&Son,1998.
[35] Kecman V. Learning and Soft Computing: Support Vector Machines, Neural Networks, andFuzzy Logic Models[M]. MIT Press,2001.
[36] Hadzic I, Kecman V. Support vector machines trained by linear programming: theory andapplication in image compression and data classification[C]: Proceedings of the5th Seminaron Neural Network Applications in Electrical Engineering, Belgrade,2000:18-23.
[37] Yuh-Jye L, Su-Yun H. Reduced Support Vector Machines: A Statistical Theory[J]. NeuralNetworks, IEEE Transactions on,2007,18(1):1-13.
[38] Iplikci S. Support vector machines based neuro-fuzzy control of nonlinear systems[J].Neurocomputing,2010,73(10–12):2097-2107.
[39] Chaudhuri A, De K. Fuzzy Support Vector Machine for bankruptcy prediction[J]. AppliedSoft Computing,2011,11(2):2472-2486.
[40]唐浩,廖与禾,孙峰,等.具有模糊隶属度的模糊支持向量机算法[J].西安交通大学学报,2009，43(07):40-43.
[41] Turkoglu I, Avci E. Comparison of wavelet-SVM and wavelet-adaptive network basedfuzzy inference system for texture classification[J]. Digital Signal Processing,2008,18(1):15-24.
[42] Du P, Tan K, Xing X. Wavelet SVM in Reproducing Kernel Hilbert Space for hyperspectralremote sensing image classification[J]. Optics Communications,2010,283(24):4978-4984.
[43] Gumus E, Kilic N, Sertbas A, et al. Evaluation of face recognition techniques using PCA,wavelets and SVM[J]. Expert Systems with Applications,2010,37(9):6404-6408.
[44] Fonseca E S, Guido R C, Scalassara P R, et al. Wavelet time-frequency analysis and leastsquares support vector machines for the identification of voice disorders[J]. Computers inBiology and Medicine,2007,37(4):571-578.
[45] Ismail S, Shabri A, Samsudin R. A hybrid model of self-organizing maps (SOM) and leastsquare support vector machine (LSSVM) for time-series forecasting[J]. Expert Systems withApplications,2011,38(8):10574-10578.
[46] Carvalho B P R, Braga A P. IP-LSSVM: A two-step sparse classifier[J]. Pattern RecognitionLetters,2009,30(16):1507-1515.
[47] Suykens J A K, Vandewalle J. Recurrent least squares support vector machines[J]. IEEETransactions on Circuits and Systems I: Fundamental Theory and Applications,2000,47(7):1109-1114.
[48] Suykens J A K, Lukas L, Vandewalle J. Sparse approximation using least squares supportvector machines[C]: The2000IEEE International Symposium on Circuits and SystemsProceedings, Geneva,2000:757-760.
[49] K. R. Müller A S G R. Predicting time series with support vector machines[C]: InProceedings of the International Conference on Artificial Neural Networks,1997:999-1004.
[50] Francis E. H. Tay L C. Application of support vector machines in financial time seriesforecasting[J]. Omega,2001,29(4):309-317.
[51] Gretton A, Doucet A, Herbrich R, et al. Support vector regression for black-box systemidentification[C]: Proceedings of the11th IEEE Signal Processing Workshop on StatisticalSignal Processing,2001:341-344.
[52] S C, M W. Seeking multi-thresholds directly from support vectors for imagesegmentation[J]. Neurocomputing,2005,14(1):335-344.
[53] Suykens J A K, Vandewalle J, De Moor B. Optimal control by least squares support vectormachines[J]. Neural Networks,2001,14(1):23-35.
[54] Yanjie H, Juanjuan P. Financial crisis early-warning based on support vector machine[C]:IEEE International Joint Conference on Neural Networks, Hong Kong,2008:2435-2440.
[55] M M. Support vector machines for short-term electrical load forecasting[J]. InternationalJournal of Energy Research,2002,26(4):335-345.
[56] Hong W. Electric load forecasting by seasonal recurrent SVR (support vector regression)with chaotic artificial bee colony algorithm[J]. Energy,2011,36(9):5568-5578.
[57] Hong W. Application of chaotic ant swarm optimization in electric load forecasting[J].Energy Policy,2010,38(10):5830-5839.
[58] Hong W. Chaotic particle swarm optimization algorithm in a support vector regressionelectric load forecasting model[J]. Energy Conversion and Management,2009,50(1):105-117.
[59] Hong W. Electric load forecasting by support vector model[J]. Applied MathematicalModelling,2009,33(5):2444-2454.
[60] Meiying Q, Xiaoping M, Jianyi L, et al. Time-series gas prediction model using LS-SVRwithin a Bayesian framework[J]. Mining Science and Technology (China),2011,21(1):153-157.
[61] Hong W. Traffic flow forecasting by seasonal SVR with chaotic simulated annealingalgorithm[J]. Neurocomputing,2011,74(12–13):2096-2107.
[62] Gandhi A B, Joshi J B, Kulkarni A A, et al. SVR-based prediction of point gas hold-up forbubble column reactor through recurrence quantification analysis of LDA time-series[J].International Journal of Multiphase Flow,2008,34(12):1099-1107.
[63] Castro-Neto M, Jeong Y, Jeong M, et al. Online-SVR for short-term traffic flow predictionunder typical and atypical traffic conditions[J]. Expert Systems with Applications,2009,36(3,Part2):6164-6173.
[64] Yang Y, Fuli R, Huiyou C, et al. SVR mathematical model and methods for saleprediction[J]. Journal of Systems Engineering and Electronics,2007,18(4):769-773.
[65] Mohandes M A. Modeling global solar radiation using Particle Swarm Optimization(PSO)[J]. Solar Energy,2012,86(11):3137-3145.
[66] Xue L, Cai J, Li J, et al. Application of Particle Swarm Optimization (PSO) Algorithm toDetermine Dichlorvos Residue on the Surface of Navel Orange with Vis-NIRSpectroscopy[J]. Procedia Engineering,2012,29(0):4124-4128.
[67] Khouadjia M R, Sarasola B, Alba E, et al. A comparative study between dynamic adaptedPSO and VNS for the vehicle routing problem with dynamic requests[J]. Applied SoftComputing,2012,12(4):1426-1439.
[68] Behrang M A, Assareh E, Noghrehabadi A R, et al. New sunshine-based models forpredicting global solar radiation using PSO (particle swarm optimization) technique[J].Energy,2011,36(5):3036-3049.
[69] Taher S A, Karimian A, Hasani M. A new method for optimal location and sizing ofcapacitors in distorted distribution networks using PSO algorithm[J]. Simulation ModellingPractice and Theory,2011,19(2):662-672.
[70] Clerc M, Kennedy J. The particle swarm-explosion, stability, and convergence in amultidimensional complex space[J]. IEEE Transactions on Evolutionary Computation,2002,6(1):58-73.
[71]唐贤伦.混沌粒子群优化算法理论及应用[D].重庆：重庆大学图书馆,2007.
[72] Ozcan E, Mohan C K. Particle swarm optimization: surfing the waves[C]: Proceedings ofthe1999Congress on Evolutionary Computation, Washington, DC,1999:1943-1944.
[73] Yuhui S, Eberhart R. A modified particle swarm optimizer[C]: The1998IEEE InternationalConference on Evolutionary Computation Proceedings, Anchorage, AK,1998:69-73.
[74]崔红梅,朱庆保.微粒群算法的参数选择及收敛性分析[J].计算机工程与应用,2007，43(23):89-91.
[75]王丽,王晓凯.一种非线性改变惯性权重的粒子群算法[J].计算机工程与应用,2007，43(04):47-48.
[76]延丽平,曾建潮.具有自适应随机惯性权重的PSO算法[J].计算机工程与设计,2006，27(24):4677-4679.
[77]刘建华,樊晓平,瞿志华.一种惯性权重动态调整的新型粒子群算法[J].计算机工程与应用,2007，43(07):68-70.
[78] Yuhui S, Eberhart R C. Fuzzy adaptive particle swarm optimization[C]: Proceedings of the2001Congress on Evolutionary Computation,2001:101-106.
[79] Ratnaweera A, Halgamuge S, Watson H C. Self-organizing hierarchical particle swarmoptimizer with time-varying acceleration coefficients[J]. IEEE Transactions on EvolutionaryComputation,2004,8(3):240-255.
[80]陈水利,蔡国榕,郭文忠,等. PSO算法加速因子的非线性策略研究[J].长江大学学报(自科版)理工卷,2007，4(04):1-4.
[81]田玉玲,杨朋樽.基于KRTG的动态拓扑结构的粒子群算法研究[J].计算机与数字工程,2010，38(02):25-27.
[82]韩立娜,熊盛武.基于动态邻域的粒子群算法的研究[J].计算机工程与应用,2009，45(06):60-62.
[83]王雪飞,王芳,邱玉辉.一种具有动态拓扑结构的粒子群算法研究[J].计算机科学,2007，34(03):205-207.
[84]Urade H S, Patel R. Dynamic Particle Swarm Optimization to Solve Multi-objectiveOptimization Problem[J]. Procedia Technology,2012,6(0):283-290.
[85] Liang J J, Suganthan P N. Dynamic multi-swarm particle swarm optimizer[C]:2005IEEESwarm Intelligence Symposium Proceedings,2005:124-129.
[86] Yu S, Zhu K, Zhang X. Energy demand projection of China using a path-coefficient analysisand PSO–GA approach[J]. Energy Conversion and Management,2012,53(1):142-153.
[87] Nanda S J, Panda G. Automatic clustering algorithm based on multi-objective ImmunizedPSO to classify actions of3D human models[J]. Engineering Applications of ArtificialIntelligence,2012(0).
[88] Liu B, Wang L, Jin Y. An effective hybrid PSO-based algorithm for flow shop schedulingwith limited buffers[J]. Computers&Operations Research,2008,35(9):2791-2806.
[89] Cai X, Zhang N, Venayagamoorthy G K, et al. Time series prediction with recurrent neuralnetworks trained by a hybrid PSO–EA algorithm[J]. Neurocomputing,2007,70(13–15):2342-2353.
[90] Guo Q, Yu H, Xu A. A hybrid PSO-GD based intelligent method for machine diagnosis[J].Digital Signal Processing,2006,16(4):402-418.
[91] Lu H, Sriyanyong P, Song Y H, et al. Experimental study of a new hybrid PSO withmutation for economic dispatch with non-smooth cost function[J]. International Journal ofElectrical Power&Energy Systems,2010,32(9):921-935.
[92] Chen K, Li T, Cao T. Tribe-PSO: A novel global optimization algorithm and its applicationin molecular docking[J]. Chemometrics and Intelligent Laboratory Systems,2006,82(1–2):248-259.
[93] Madhubanti Maitra A C. A hybrid cooperative–comprehensive learning based PSOalgorithm for image segmentation using multilevel thresholding[J]. Expert Systems withApplications,2008,34(2):1341-1350.
[94] Nima Hamta S M T F. A hybrid PSO algorithm for a multi-objective assembly linebalancing problem with flexible operation times, sequence-dependent setup times andlearning effect[J]. International Journal of Production Economics,2013,141(1):99-111.
[95] Niknam T, Azadfarsani E, Jabbari M. A new hybrid evolutionary algorithm based on newfuzzy adaptive PSO and NM algorithms for Distribution Feeder Reconfiguration[J]. EnergyConversion and Management,2012,54(1):7-16.
[96] E. B, M. D, Theraulaz G. Swarm Intelligence: Form Natural to Artificial Systems[M].Oxford University Press,1999.
[97] A. C, M. D, V. M. Distributed Optimization by Ant Colonies[C]: Proceedings of the1stEuropean Conf on Artificial Life,1991:134-142.
[98]李晓磊,邵之江,钱积新.一种基于动物自治体的寻优模式:鱼群算法[J].系统工程理论与实践,2002(11):32-38.
[99] Passino K M. Biomimicry of bacterial foraging for distributed optimization and control[J].Control Systems, IEEE,2002,22(3):52-67.
[100] Karaboga D, Basturk B. On the performance of artificial bee colony (ABC) algorithm[J].Applied Soft Computing,2008,8(1):687-697.
[101] Eberhart R, Kennedy J. A new optimizer using particle swarm theory[C]: Proceedings of theSixth International Symposium on Micro Machine and Human Science, Nagoya,1995:39-43.
[102] M. A. Potter K A D J. A cooperative coevolutionary approach to function optimization[C]:The Third Parallel Problem Solving From Nature, Berlin, Germany,1994:249-257.
[103] van den Bergh F, Engelbrecht A P. A Cooperative approach to particle swarmoptimization[J]. IEEE Transactions on Evolutionary Computation,2004,8(3):225-239.
[104]付国江,王少梅,刘舒燕,等.含维变异算子的粒子群算法[J].武汉大学学报(工学版),2005，38(9):79-84.
[105] Xu H, Yang Y, Mao L, et al. Improvement on PSO with Dimension Update and Mutation[J].JOURNAL OF SOFTWARE,2013,8(4):827-833.
[106] Eberhart R C, Yuhui S. Tracking and optimizing dynamic systems with particle swarms[C]:Proceedings of the2001Congress on Evolutionary Computation,2001:94-100.
[107]陈宇,孙帆,张健.基于自适应权重粒子群的电容层析成像边界灰度补偿算法[J].哈尔滨理工大学学报,2010，15(6)：44-49.
[108] Iwamatsu M. Locating All the Global Minima Using Multi-Species Particle SwarmOptimizer: The Inertia Weight and The Constriction Factor Variants[C]: IEEE Congress onEvolutionary Computation, Vancouver, BC,2006:816-822.
[109] Jang-Ho S, Chang-Hwan I, Chang-Geun H, et al. Multimodal function optimization basedon particle swarm optimization[J]. IEEE Transactions on Magnetics,2006,42(4):1095-1098.
[110] Kitayama S, Yasuda K. A method for mixed integer Programming problems by particleswarm optimization [J]. Electrical Engineering in Japan,2006,157(2):40-49.
[111] Farmer J D, Packard N H, Perelson A S. The immune system, adaptation, and machinelearning[J]. Physica D: Nonlinear Phenomena,1986,22(1–3):187-204.
[112] Leandro Nunes De Castro F J V Z. ARTIFICIAL IMMUNE SYSTEMS:PART I–BASICTHEORY AND APPLICATIONS[R].1999.
[113] Leandro Nunes De Castro F J V Z. Artificial Immune Systems: Part II–A Survey ofApplications[R].2000.
[114] Leandro Nunes De Castro F J V Z. The Clonal Selection Algorithm with EngineeringApplications[C]: Workshop Proceedings of GECCO, Las Vegas, USA,2000:36-37.
[115] de Castro L N, Von Zuben F J. Learning and optimization using the clonal selectionprinciple[J]. IEEE Transactions on Evolutionary Computation,2002,6(3):239-251.
[116] de Castro L N, Timmis J. An artificial immune network for multimodal functionoptimization[C]: Proceedings of the2002Congress on Evolutionary Computation,2002:699-704.
[117]葛红,毛宗源.免疫算法几个参数的研究[J].华南理工大学学报(自然科学版),2002，30(12):15-18.
[118]吴秋逸,焦李成,李阳阳,等.自适应量子免疫克隆算法及其收敛性分析[J].模式识别与人工智能,2008，21(05):592-597.
[119]吴秋逸,焦李成,魏峻,等.量子协同免疫动态优化算法[J].模式识别与人工智能,2009，22(06):862-868.
[120] Acan A. Clonal selection algorithm with operator multiplicity[C]: Congress on EvolutionaryComputation,2004:1909-1915.
[121]凌军,曹阳,尹建华,等.基于小生境技术的多样性抗体生成算法[J].电子学报,2003，31(08):1130-1133.
[122] Timmis J, Edmonds C, Kelsey J. Assessing the performance of two immune inspiredalgorithms and a hybrid genetic algorithm for function optimisation[C]: Congress onEvolutionary Computation,2004:1044-1051.
[123] M O, S F. How the immune system generates diversity: Pathogen space coverage withrandom and evolved antibody libraries[C]: Genetic and Evolutionary ComputationConference,1999:1651-1656.
[124]焦李成,杜海峰.人工免疫系统进展与展望[J].电子学报,2003，31(10):1540-1548.
[125]罗印升,李人厚,张雷,等.人工免疫算法在函数优化中的应用[J].西安交通大学学报,2003，37(08):840-843.
[126] Xu H, Yang Y, Mao L. Study and Improvement on Particle Swarm Algorithm[J].JOURNAL OF COMPUTERS,2013,8(4):937-942.
[127] Potter M A, De Jong K A. Cooperative coevolution:An architecture for evolving coadaptedsubcomponents[J]. Evolutionary Computation,2000,8(1):1-29.
[128]郭圆平.动态种群规模的协同进化算法模型、理论与应用[D].北京：中国科学技术大学图书馆,2008.
[129] Ficici S G. Solution concepts in coevolutionary algorithms[D]. Brandeis University,2004.
[130] Cowling P I, Naveed M H, Hossain M A. A Coevolutionary Model for The Virus Game[C]:IEEE Symposium on Computational Intelligence and Games, Reno, NV,2006:45-51.
[131] Pratas N, Prasad N R, Rodrigues A, et al. Cooperative spectrum sensing: State of the artreview[C]:2nd International Conference on Wireless Communication, Vehicular Technology,Chennai,2011:1-6.
[132] Jun-Yuan T, De-Sheng L. Cooperative Strategy Learning in Multi-Agent Environment withContinuous State Space[C]:2006International Conference on Machine Learning andCybernetics, Dalian, China,2006:2107-2111.
[133] Zhao J, Weiyi L, Jian J. State-Clusters shared cooperative multi-agent reinforcementlearning[C]: Asian Control Conference, Hong Kong,2009:129-135.
[134] Kleeman M P, Lamont G B. Coevolutionary Multi-Objective EAs: The Next Frontier?[C]:IEEE Congress on Evolutionary Computation,2006:1726-1735.
[135] Tan K C, Yang Y J, Goh C K. A distributed Cooperative coevolutionary algorithm formultiobjective optimization[J].IEEE Transactions on Evolutionary Computation,2006,10(5):527-549.
[136] Wloldridge M, Jenning N R. Intelligent Agent:Theory and Pracitce[J]. The KnowledgeEngineering Review,1995,2(10):115-152.
[137]孙辉,刘前进.一种新型MAS的配电网保护和控制方案[J].电力系统保护与控制,2010，38(16):24-29.
[138]蒋国银,胡斌,王缓缓.基于MAS的移动服务链协同工作机制研究[J].管理工程学报,2010，24(01):82-89.
[139] García Ansola P, de Las Morenas J, García A, et al. Distributed decision support system forairport ground handling management using WSN and MAS[J]. Engineering Applications ofArtificial Intelligence,2012,25(3):544-553.
[140]严建峰,李伟华,刘明.基于混合蚁群算法的MAS任务分配[J].计算机应用研究,2009，26(01):68-70.
[141] Lorenz E N. Deterministic non-period flow[J]. Atmos. Sci.,1963,20:130-141.
[142]吕金虎,陆君安,陈士华.混沌时间序列分析及其应用[M].武汉:武汉大学出版社,2002.
[143] Slutzky M W, Cvitanovic P, Mogul D J. Manipulating epileptiform bursting in the rathippocampus using chaos control and adaptive techniques[J].IEEE Transactions onBiomedical Engineering,2003,50(5):559-570.
[144] Cong-Hui H, Chia-Hung L, Chao-Lin K. Chaos Synchronization-Based Detector forPower-Quality Disturbances Classification in a Power System[J].IEEE Transactions onPower Delivery,2011,26(2):944-953.
[145] Ma X, Guo L. Optimization of PID Parameters for Mine Hoisting DTC System Based onChaos Theory[C]: International Conference on Artificial Intelligence and ComputationalIntelligence, Shanghai,2009:128-131.
[146]罗金辉,杨永国,秦勇,等.基于组合权重的煤层气有利区块模糊优选[J].煤炭学报,2012，37(02):242-246.
[147]贾东立,张家树.基于混沌变异的小生境粒子群算法[J].控制与决策,2007，22(01):117-120.
[148]胥小波,郑康锋,李丹,等.新的混沌粒子群优化算法[J].通信学报,2012，33(01):24-30.
[149]陈如清,俞金寿.混沌粒子群混合优化算法的研究与应用[J].系统仿真学报,2008，20(03):685-688.
[150]袁晓辉,袁艳斌,王乘,等.一种新型的自适应混沌遗传算法[J].电子学报,2006，34(04):708-712.
[151] Aihara K. Chaos and Its Applications[J]. Procedia IUTAM,2012,5(0):199-203.
[152] Ding W. A New Method for Image Noise Removal using Chaos-PSO and Nonlinear ICA[J].Procedia Engineering,2011,24(0):111-115.
[153]杨永国,陈玉华.矿井涌水量混沌特征与预测[J].地球科学(中国地质大学学报),2009，34(02):258-262.
[154]徐慧,杨永国.多Agent协同处理模型的研究与设计[J].计算机工程,2010，36(05):67-69.
[155] Hui X, Yongguo Y. Research and Design on Dynamic Multi-agent Cooperative ProcessingModel[C]: International Conference on Web Information Systems and Mining, Shanghai,2009:432-436.
[156]邓乃扬,田英杰.支持向量机-理论、算法与拓展[M].北京:科学出版社,2009.
[157] Li J, Jia Y, Du Junping, et al. Optimal regularization parameters selection for Laplaciansupport vector machine[C]:27th Chinese Control Conference, Kunming,2008:464-468.
[158] Klaus S. Optimal parameter selection in support vector machines[J]. Journal of Industrialand Management Optimization,2005,1(4):465-476.
[159] de Miranda P B C, Prudencio R B C, Carvalho A C P L, et al. Combining a multi-objectiveoptimization approach with meta-learning for SVM parameter selection[C]:IEEEInternational Conference on Systems, Man, and Cybernetics (SMC), Seoul,2012:2909-2914.
[160] Abdi M J, Giveki D. Automatic detection of erythemato-squamous diseases usingPSO–SVM based on association rules[J]. Engineering Applications of Artificial Intelligence,2013,26(1):603-608.
[161] C. C C, J. L C. LIBSVM: A Library for Support Vector Machines (Version2.3)[EB/OL].http://www.csie.ntu.edu.tw/~cjlin/papers/libsvm.pdf.
[162]闫宝珍.沁水盆地煤层气富集机理及主控特征[D].北京：中国矿业大学（北京）图书馆,2008.
[163]贾承造等.煤层气资源储量评估方法[G].石油工业出版社,2007.
[164]陈振宏,王一兵,杨焦生,等.影响煤层气井产量的关键因素分析——以沁水盆地南部樊庄区块为例[J].石油学报,2009，30(03):409-412.
[165]刘人和,刘飞,周文,等.沁水盆地煤岩储层特征及有利区预测[J].油气地质与采收率,2008，15(04):16-19.
[166]倪小明,苏现波,王庆伟,等.恩村井田煤层气垂直井产能地质主控因素分析[J].煤矿安全,2009(07):79-82.
[167]陶树,汤达祯,许浩,等.沁南煤层气井产能影响因素分析及开发建议[J].煤炭学报,2011，36(02):194-198.
[168]林然,倪小明,王延斌.山西沁水盆地樊庄区块煤层气高产区预测[J].高校地质学报,2012，18(03):558-562.
[169]王向浩,王延斌,袁钧,等.煤层气资源赋存条件与垂直井产能关系研究[J].煤炭科学技术,2012，40(12):104-105.
© 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 |