摘要
储层预测是建立精确油气藏地质模型，准确估算油气储量，确定合理开发方案的基础工作，不仅可用于油气勘探，而且对于指导油气藏特别是复杂隐蔽油气藏或岩性油气藏的开发具有重要意义，已成为国内外学术界和工业界共同关注的关键科学问题。通过井间对比或插值外推对储层横向展布或储层参数予以精确描述是比较困难的。联合测井和地震信息的反演技术和地震属性技术作为重要的储层预测方法，已延伸至油气开发阶段，成为油气藏描述技术的重要组成部分。
反演的实质是求取非线性目标函数的极值问题，常规的线性反演有可能陷入局部极值，或依赖于初始模型的选择，从而影响反演的可靠程度。智能计算方法如遗传算法或模拟退火等为求解储层参数反演这样的非线性问题提供了新的思路和手段，但也存在不足，比如求解速度慢，或对于复杂反演问题，也可能会陷入局部极值等。智能计算方法中的神经网络技术常用来建立地震属性和储层参数间非线性映射关系，进而预测储层参数。误差反向传播网络学习算法实际上是梯度算法，收敛速度慢，也可能会陷入局部极值。
针对上述问题，论文以改善储层非线性反演的求解效率和寻优性能，寻求高效的学习算法以提高储层参数预测效果为目的，研究基于粒子群优化算法的储层参数非线性反演方法和基于混合学习法神经网络的多属性储层参数预测技术，并应用这些方法预测川东DCH构造飞仙关组鲕滩储层的空间展布规律和孔隙度等参数，取得了如下成果和认识：
1、深入地研究了粒子群优化算法原理、收敛性条件、参数设置原则等基本理论问题，针对优化问题求解，粒子群优化算法对解的更新更具目的性，收敛速度快。提出的混沌惯性权重调整策略的粒子群优化算法，进一步提高了算法的收敛速度；将多父体交叉算子和群体爬山思想融入粒子群优化算法中，很好地提高了粒子群优化算法的寻优性能，上述改进为解决储层参数反演问题提供了新的优化工具。在此基础上，研究开发了基于粒子群优化算法及其改进算法的储层参数非线性反演方法，模型试算和实际资料处理结果表明新方法较传统非线性方法相比，在求解效率上有了较大的提高，效果较好。
2、深入地研究了误差反向传播网络和径向基函数网络及其学习算法。研究了粒子群优化算法训练误差反向传播网络和径向基函数网络。提出了融合梯度法和粒子群优化算法的径向基函数网络混合学习算法，在求解精度和效率方面有了较大的提升。在此基础上开发了基于混合学习法前向神经网络多属性储层参数预测方法，应用于储层孔隙度参数的横向预测，在收敛速度上有了较大的提升。
3、应用基于粒子群优化算法的储层参数非线性反演方法反演了川东DCH构造飞仙关组鲕滩储层速度，应用混合学习法神经网络多属性储层参数预测方法预测了该储层孔隙度。在此基础上制作了鲕滩储层厚度、孔隙度、储能系数预测图。综合地质、地震和测井信息研究，认为沉积相带控制了DCH构造飞仙关组鲕滩储层发育程度和范围，后生成岩改造作用是形成鲕滩储层的必要条件。
Reservoir prediction is a basic work to build an accurate geological model ofreservoir, to accurately estimate reserve, to determine proper development scheme, itis not only applicable in oil and gas exploration, but also in guiding development ofthe oil and gas reservoirs, especially complicated subtle reservoirs or lithologicreservoirs, and has become a key scientific issue concerned by both the academic andindustrial circles domestic and abroad. It is difficult to accurately describe thehorizontal distribution of reservoirs parameters by inter-well correlation orinterpolation, the inversion and seismic attribute techniques which joint logging andseismic information are important reservoir prediction method, have been extended tothe oil and gas development stage, become important component of reservoirdescription technology.
The essence of inversion technique is to find the solution of a nonlinear objectivefunction. However, the traditional linear inversion methods sometimes plunge intolocal optimum, or depend on the selection of the initial model, thus affecting thereliability of inversion. Intelligent computation methods such as genetic algorithm orsimulated annealing etc. provide a new way to solve reservoir parameters nonlinearinversion problem, but with shortcomings such as converging slowly or falling intolocal optimum, especially for complicated inversion problems. Neural network hasalso been used to build the nonlinear relationship between seismic attributes andreservoir parameters, and predict reservoir parameters. The essence of error backpropagation learning algorithm of neural network is a gradient method, whichconverges slowly to desirable solution, or may be trapped into local optimum.
In this dissertation, I propose a number of new ideas to improve the efficiencyand the optimizing performance of nonlinear inversion, the efficiency of neuralnetwork’s learning algorithm for reservoir parameters prediction. I have studiedreservoir parameters nonlinear inversion method based on improved particle swarmoptimization, and new learning algorithm of neural network which hybrids gradient method and particle swarm optimization, in order to predict reservoir parametersthrough multi-attributes. At the same time, I applied the new methods to predictoolitic reservoir, Feixianguan formation, DCH structure of Eastern Sichuan Basin, andobtain the following results:
1, in-depth study of the principles of particle swarm optimization, convergenceconditions, parameters setting etc. basic theoretical problem, particle swarmoptimization algorithm updates the solution more purposely, converges more rapidly.A new chaotic inertia weight adjustment strategy is proposed to further improve thealgorithm’s convergence speed. At the same time, I built the multi-parent crossoveroperator and adopt the group hill climbing idea to improve the performance of particleswarm optimization algorithm. On these bases, I develop new reservoir parametersnonlinear inversion methods based on particle swarm optimization algorithm, and themodel simulations and practical data processing results demonstrate that the newmethod is highly efficient with much improved performance over the traditionalnon-linear methods.
2, in-depth study of the error back propagation network, radial basis functionnetwork and their learning algorithm. I have applied the particle swarm optimizationas the train algorithm of back-propagation network and radial basis function networks.Fusion gradient method and the particle swarm optimization are developed to form anew hybrid learning algorithm of radial basis function network, and the accuracy andefficiency of new hybrid algorithm have been greatly improved. On this basis, Ideveloped a new reservoir parameters prediction technique by seismic multi-attributewhich based on hybrid learning algorithm neural network, and applied the techniqueto predict porosity parameters which indicates that the hybrid learning algorithm hasshort training time and high efficiency.
3, applying new reservoir parameters nonlinear inversion method based onparticle swarm optimization and new reservoir parameters prediction technique ofhybrid learning algorithm neural network to predict oolitic reservoir, Feixianguanformation, DCH structure of Eastern Sichuan Basin. I have drawn the prediction mapfor reservoir thickness, porosity, and storage coefficient. Based on the comprehensivegeological, seismic and log information conclude that the sedimentary facies controlsoolitic reservoir’s level and scope, and the anadiagenesis is the necessary conditionsfor oolitic reservoir development.
引文
[1]王允诚.油气储层评价[M].北京:石油工业出版社,1999.
[2] Roethe, G.., Tarandtola, A. Use of neural networks for inversion of seismic dada[C].61stAnnual international meeting, Society Exploration Geophysics, Expand Abstracts:302-305,1991.
[3] Roethe, G.., Tarandtola, A. Neural networks and inversion of seismic data[J]. JournalGeophysics Prospecting,1994,99:6753-6768.
[4] Fu, L. Application of the Caianiello neuron-based network to joint inversion[C].67thAnnualinternational meeting, Society Exploration Geophysics, Expand Abstracts:1624-1627,1997.
[5]杨文采.神经网络算法在地球物理反演中的应用[J].石油物探,1995,34(2):114-120.
[6]吴大奎,李亚林,伍志明等.地震、测井资料联合反演的神经网络算法研究[J].天然气工业,2004,24(3):55-57.
[7] Berg, E. Genetic Algorithm for Inversion of Multiparameter Data[C].60thAnnual internationalmeeting, Society Exploration Geophysics, Expand Abstracts:302-305,1990.
[8] Sen, M.K., Stoffa, P.L. Simulated annealing, genetic algorithm and seismic waveforminversion[C].61stAnnual international meeting, Society Exploration Geophysics, ExpandAbstracts:945-947,1991.
[9] Stoffa, P.L., Sen, M.K. Nonlinear multiparameter optimization using genetic algorithm:inversion of plane-wave seismograms[J]. Geophysics.1991,56(11):1794-1810.
[10] Mallick, S. Inversion of amplitude-variations with offset data using genetic algorithm[C].62ndAnnual international meeting, Society Exploration Geophysics, Expand Abstracts:844-847,1992.
[11] Mallick, S. Waveform inversion of amplitude-variations with offset data using geneticalgorithm[C].63rdAnnual international meeting, Society Exploration Geophysics, ExpandAbstracts:750-753,1993.
[12] Mallick, S. Model-based inversion of amplitude-variations with offset data using geneticalgorithm. Geophysics[J],1995,60(4):939-954.
[13]陶春辉,何樵登,牛滨华.用遗传算法反演一维声波介质[J].长春地质学院学报,1993,23(4):447-454.
[14]张厚柱,杨慧珠,徐秉业.用遗传算法反演层速度[J].石油地球物理勘探,1995,30(5):633-944.
[15]郭宝琦,郭惠娟,金大勇等.双相介质中孔隙率反演的遗传算法[J].哈尔滨工业大学学报,1995,27(2):1-3.
[16]杨文采.地球物理反演的遗传算法[J].石油物探,1995,34(1):116-123.
[17]王宝珍,杨文采.用改进的遗传算法进行地震波阻抗反演研究[J].石油地球物理勘探,1998,33(2):258-264.
[18] Sen, M.K., Stoffa, P.L. Nonlinear one-dimensional seismic waveform inversion usingsimulated annealing[J]. Geophysics,1991,56(10):1624-1638.
[19]赵改善.用模拟退火法作AVA反演[J].石油物探,1992,31(3):1-10.
[20]陈均,钱泉,唐权钧.用模拟退火法作叠后层速度计算[J].石油物探,1994,33(2):11-20.
[21]王山山,李灿平,李青仁等.快速模拟退火地震反演[J].地球物理学报,1995,38(S1):123-134.
[22] Ma, X.Q. Simultaneous inversion of prestack seismic data for rock properties using simulatedannealing[J].Geophysics,2002,67(6):1877-1885.
[23] Kennedy, J., Eberhart, R.C. Particle swarm optimization[C]. Proceedings of IEEEInternational Conference on Neural Networks, Piscataway, N.J.,1942-1948,1995.
[24] McCulloch W.S, Pitts W. A logical calculus of the ideas immanent in nervous activity[J].Bulletin of Mathematical Biophysics,1943,5(10):115～133.
[25] Hebb D.O. The organization of behavior [M]. New York: John Wiley,1949.
[26] Rosenblatt, F. The perceptron: A probabilistic model for information storage and organizationin the brain[J]. Psychological Review,1958,(65):386-458.
[27] Minsky, M., Papert, S. Perceptron[M]. Cambridge: MIT Press,1969.
[28] Grossberg, S. Adaptive pattern classification and universal recording, I: Parallel developmentand coding of neural feature detectors[J]. Biological Cybernetics,1976,(23):121-134.
[29] Grossberg, S. Adaptive pattern classification and universal recording, II: Feedback,expectation, olfaction, and illusions[J]. Biological Cybernetics,1976,(23):187-202.
[30] Kohoen, T. Self-Organizing Maps, ser. Information Science,3rded., New York: Springer-Verlag,2001.
[31] Hopfield, J.J. Neural networks and physical systems with emergent collective computationalabilities[J]. Proceedings of the National academy of Science,1982,(79):2554-2558.
[32] Rumelhart, D.E., Hinton, G. E., Williams, R. J. Learning representation by back-propagationerror[J]. Nature,1986,(323):533-536.
[33] Broomhead, D.S., Lowe, D. Multivarable functional interpolation and adaptive networks[J].Complex System,1988,2(3):321-355.
[34] Specht, D., Probabilistic neural network[J]. Neural Networks,1990,3:109-118.
[35] Zhang Q., Benveniste A. Wavelet Network[J]. IEEE Trans. Neural Network,1992,3(6):889-898.
[36]王小平,曹立明.遗传算法——理论、应用与软件实现[M].西安:西安交通大学出版社,2002.
[37]Kirkpatrick, S., Gelatt, C.D., Jr.,Vecchi,M.P. Optimization by simulating annealing[J]. Science,1983,220:671-680.
[38] Szu, H.H., Hartley, R.L. Nonconvex. Optimization by fast simulating annealing[J]. Proceedings IEEE,1987,75:1538-1540.
[39] Ingber, L. Very fast simulated re-annealling[J]. Journal of mathematical andcomputational modeling,1989,12:967-973.
[40] 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.
[41] Trelea, I. C., The particle swarm optimization algorithm: convergence analysis and parameterselection[J]. Information Processing Letters,2003,85(6):317-325.
[42] Frans van den Bergh. An Analysis of Particle Swarm Optimizers [D]. Pretoria: University ofPretoria,2006.
[43] Shi, Y., Eberhart, R. C. A modified particle swarm optimizer[C]. Proceedings of the IEEECongress on Evolutionary Computation (CEC1998), Piscataway, N.J.,69-73,1998.
[44] Chatterjee, A., Siarry, P. Nonlinear inertia weight variation for dynamic adaptation in particleswarm optimization[J]. Computer&Operations Research,2006,33(3):859-871.
[45] Shi, Y.H., Eberhart, R.C. Fuzzy adaptive particle swarm optimization[C]. Proceedings of theIEEE Congress on Evolutionary Computation (CEC2001), Seoul, Korea,101-106,2001.
[46]张丽平,俞欢军等.粒子群优化算法的分析与改进.信息与控制,2004,33(5):513-517.
[47] Krink, T, Vesterstrom, J.S., Riget, J. Particle swarm optimization with spatial particleextension[C]. Proceedings of the fourth Congress on Evolutionary Computation(CEC2002),Honolulu, HI, USA,1474-1479,2002.
[48] AI-Kazemi, B., Mohan, C.K., Multiphase generalization of particle swarm optimizationalgorithm[C]. Proceedings of the fourth Congress on Evolutionary Computation(CEC2002),Honolulu, HI, USA,489-494,2002.
[49] Kennedy, J., Mendes, R. Population structure and particle swarm performance[C].Proceedings of the IEEE Congress on Evolutionary Computation (CEC2002), Honolulu, HI USA.1671-1676,2002.
[50] Kennedy, J., Mendes,R. Neighborhood topologies in fully-informed and best-of-neighbor-hood particle swarms[C]. Proceedings of the2003IEEE International Workshop on SoftComputing in Industrial Applications2003(SMCia/03),45-50,2003.
[51] L vbjerg, M., Rasmussen, T. K., Krink, T. Hybrid particle swarm optimiser with breeding andsubpopulations[C]. Proceedings of the Genetic and Evolutionary Computation Conference2001(GECCO2001),2001.
[52] Krink, T. and L vbjerg, M. The life cycle model: combining particle swarm optimisation,genetic algorithms and hill climbers[C]. Lecture Notes in Computer Science (LNCS) No.2439:Proceedings of Parallel Problem Solving from Nature VII (PPSN2002),621-630,2002.
[53] Robinson, J., Sinton, S., and Rahmat-Samii, Y. Particle swarm, genetic algorithm, and theirhybrids: optimization of a profiled corrugated horn antenna[C].2002IEEE Antennas andPropagation Society International Symposium and URSI National Radio Science Meeting, SanAntonio, TX.2002.
[54] Higashi, N., Iba, H., Particle swarm optimization with Gaussian mutation[C]. SwarmIntelligence Symposium, SIS '03. Proceedings of the2003IEEE,72-79,2003.
[55] Kennedy, J., Eberhart, R. C. A discrete binary version of the particle swarm algorithm[C].Proceedings of the World Multi-conference on Systemics, Cybernetics and Informatics1997,Piscataway, NJ.4104-4109,1997.
[56] Clerc, M., Discrete Particle Swarm Optimization. New Optimization Techniques inEngineering [M]. Springer-Verlag,2004.
[57] Eberhart, R. C., Hu, X. Human tremor analysis using particle swarm optimization[C].Proceedings of the IEEE Congress on evolutionary computation (CEC1999), Washington D.C.1927-1930,1999.
[58] El-Gallad, A. I., El-Hawary, M. E., Sallam, A. A., and Kalas, A. Swarm-intelligently trainedneural network for power transformer protection[C]. Canadian Conference on Electrical andComputer Engineering,265-269,2001.
[59] Lu, W. Z., Fan, H.-Y., Lo, S. M., Application of evolutionary neural network method inpredicting pollutant levels in downtown area of Hong Kong[J]. Neurocomputing,2003,51:387-400.
[60] Yoshida, H., Fukuyama, Y., Takayama, S., and Nakanishi, Y. A particle swarm optimizationfor reactive power and voltage control in electric power systems considering voltage securityassessment[C]. Proceedings of IEEE International Conference on Systems, Man, and Cybernetics502-506,1999.
[61]李爱国,覃征等.粒子群优化算法[J].计算机工程与应用.2001,37(21):1-3.
[62]谢晓峰,张文俊等.微粒群算法综述[J].控制与决策,2003,18(2):129-134.
[63]陈贵敏,贾建援等.粒子群优化算法的惯性权值递减策略研究[J].西安交通大学学报,2006,40(1):53-56.
[64]俞欢军,许宁等.混合粒子群优化算法研究[J].信息与控制,2005,34(4):500-504.
[65]王存睿,段晓东等.改进的基本粒子群优化算法[J].计算机工程,2004,30(21):35-37.
[66]高尚,杨靖宇等.基于模拟退火算法思想的粒子群优化算法[J].计算机应用与软件,2005,22(1):103-104.
[67]谭皓,沈春林等.混合粒子群算法在高维复杂函数寻优中的应用[J].系统工程与电子技术,2005,27(8):1471-1474.
[68]高鹰,谢胜利.免疫粒子群优化算法[J].计算机工程与应用,2004,40(6):4-6.
[69]戴冬雪,王祁等.基于混沌思想的粒子群优化算法及其应用[J].华中科技大学学报(自然科学版),2005,33(10):53-55.
[70]侯云鹤,鲁丽娟等.广义蚁群算法与粒子群结合算法在电力系统经济负荷分配中的应用[J].电网技术,2004,28(21):34-38.
[71]李宁,刘飞等.基于带变异算子粒子群优化算法的约束布局优化研究[J].计算机学报,2004,27(7):897-903.
[72]张丽平.粒子群优化算法的理论及实践[D].杭州:浙江大学,2005.
[73]丁华.非直井井迹优化设计与决策分析应用研究[D].大连:大连理工大学,2004.
[74]田明俊.智能反演算法及其应用研究[D].大连:大连理工大学,2005.
[75]高尚,杨靖宇.求解聚类问题的混合粒子群优化算法[J].科学技术与工程,2005,5(23):1792-1795.
[76] Ranjit Shaw, Shalivahan Srivastava. Particle swarm optimization: A new tool to invertgeophysical data[J]. Geophysics,2007,72(2):75-83.
[77]易远元,袁三一,黄凯等.地震波阻抗反演的粒子群算法实现[J].石油天然气学报,2007,29(3):79-81.
[78] Yuan Sanyi, Wang Shangxu, Tian nan. Swarm intelligence optimization and its application ingeophysical data inversion[J]. Applied Geophysics,2009,6(2):166-174.
[79]聂茹,岳建华,邓帅奇.地震波阻抗反演的免疫粒子群优化算法[J].中国矿业大学学报,2010,39(5):733-739.
[80]严哲,顾汉明.量子行为的粒子群算法在叠前AVO反演中的应用[J].石油地球物理勘探,2010,45(4):516-519.
[81] Bladewin,J.L. Bateman, R.M., Wheatley,C.L. Application of Neural network to the problemof mineral identification from well logs[J]. Log Analyst,1990,3:279-293.
[82] Winer J.M., Rogers J.A. Rogers J.R. et al. Predicting carbonate permeabilities form wirelinelogs using a back-propagation neural network[C].61stAnnual international meeting, SocietyExploration Geophysics, Expand Abstracts:285-288,1991.
[83]肖慈珣,罗继红,蔡永香.神经网络在油藏描述关键井研究中的应用[J].测井技术,1993,17(1):36-41.
[84]肖慈珣,罗继红,肖梅等.应用神经网络技术预测碳酸盐岩储层孔隙度[J].天然气工业,1993,13(6):31-34.
[85]刘争平,何永富.人工神经网络在测井解释中的应用[J].地球物理学报,1995,38(S1):323-330.
[86] Hampson, D.P., Schuelke, J.S.,Quirein, J.A.Use of multiattribute transforms to predict logproperties from seismic data[J]. Geophysics,2001,66(1):220-236.
[87]黄真萍,王晓华,王云专.地震信息的属性参数提取和砂体预测方法[J].石油地球物理勘探,1997,32(5):669-682.
[88]宋维琪,王小马,杜玉民等.综合应用地震属性、测井数据反演储层参数[J].石油地球物理勘探,2002,37(5):491-494.
[89]乐友喜,刘雯林.非线性方法在储层参数平面分布预测中的应用[J].石油大学学报(自然科学版),2002,26(3):26-29.
[90]何琰,彭文,殷军.利用地震属性预测渗透率[J].石油学报,2001,22(6):34-36.
[91]徐旺林,庞位奇,吕淑英等.动态概率神经网络及油气概率分布预测[J].石油地球物理勘探,2005,40(1):65-70.
[92]杜红斌,郭巧占.概率神经网络及其在储层产能预测中的应用[J].石油仪器,2005,19(4):54-56.
[93]冉启全,周雪峰,胡永乐.基于神经网络的多属性火成岩岩性反演技术[J].西南石油学院学报,2006,28(1):5-8.
[94]江文荣,张科.径向基函数神经网络在孔隙度预测中的应用[J].中国海上油气,2008,20(5):305-307.
[95]李安东,宁俊瑞,刘振峰.用神经网络和地质统计学综合多元信息进行储层预测[J].石油与天然气地质,2010,31(4):493-498.
[96]黄绪德.反褶积与地震道反演[M].北京:石油工业出版社,1992.
[97]安鸿伟,李正文等.稀疏脉冲波阻抗反演在YX油田开发中的应用[J].石油物探,200241(1):56-60.
[98] Cooke, D.A., Schneider, W.A. Generalized linear inversion of reflection seismic data[J].Geophysics,1983,48(6):665-676.
[99]周竹生,周熙襄.宽带约束反演方法[J].石油地球物理勘探,1993,28(5):523-536.
[100]张宏彬,何樵登.宽带约束反演[J].石油物探,1995,34(1):1-10.
[101]杨谦,李正文.地震资料宽带约束反演方法及应用[J].石油物探,1996,35(4):37-42.
[102] Connolly, P. Elastic impedance[J]. The leading edge,1999,18(4):438-452.
[103] Whitcombe, D.N. Elastic impedance normalization[J]. Geophysics,2002,67(1):60-62.
[104] Whitcombe, D.N. Extended elastic impedance for fluid and lithology prediction[J].Geophysics,2002,67(1):63-67.
[105]马劲风.地震勘探中广义弹性阻抗的正反演[J].地球物理学报,2003,46(3):118～124.
[106] Mallick, S. AVO and elastic impedance[J]. The Leading Edge,2001,20(10):1094-1104.
[107] Wang, Y.H. Approximations to Zoeppritz equations and their use in AVO analysis[J].Geophysics,1999,64(6):1920-1927.
[108] Duffaut, K., et al. Shear-wave elastic impedance[J]. The Leading Edge,2000,19(11):1222-1229.
[109] Ezequiel F., et al. Near and far offset P-to-S elastic impedance for discriminating fizz waterfrom commercial gas[J]. The Leading Edge,2003,22(10):1012-1015.
[110]倪逸.弹性波阻抗计算的一种新方法[J].石油地球物理勘探,2003,38(2):147-150.
[111]甘利灯等.弹性阻抗在流体与岩性预测中的潜力分析[J].石油物探,2005,44(5):504-508.
[112]王保丽,印兴耀,张繁昌.弹性阻抗反演及应用研究[J].地球物理学进展,2005,20(1):89-92.
[113]曹孟起,王九栓等.叠前弹性波阻抗反演技术及应用[J].石油地球物理勘探,2006,41(3):323-326.
[114]苑书金,于常青.各向异性介质中的弹性阻抗及其反演[J].地球物理学进展,2006,21(2):520-523.
[115] Guo, T., Kang, L.S. A new evolutionary algorithm for function optimization[J]. WuhanUniversity Journal of Natural Science,1999,4(4):409-414.
[116]贺毅朝,张翠军等.微粒群算法与郭涛算法在数值优化中的比较[J].计算机工程与应用,2007,43(11):100-103.
[117]贺毅朝,寇应展等.一种基于全局劣汰策略的混合粒子群优化算法[J].计算机应用研究,2007,24(8):75-78.
[118] Liner, C., Li, F. C.,Gersztenkorn, A., et al. SPICE: A new general seismic attribute[C].74thAnnual International Meeting, Society Exploration Geophysics, Expand Abstracts:750-753,2004.
[119]印兴耀,周静毅.地震属性优化方法综述[J].石油地球物理勘探,2005,40(4):482-489.
[120]王永刚,刘伟等.地震属性的GA_BP优化方法[J].石油地球物理勘探,2002,37(6):606-611.
[121]陈遵德.储层地震属性优化方法[M].北京:石油工业出版社,1998.
[122] Chopra, S., Marfurt, J.K.著,赵剑敏摘译,地震属性的历史回顾(上)[J].油气地球物理,2006,4(3):55-59.
[123] Chopra, S., Marfurt, J.K.著,赵剑敏摘译,地震属性的历史回顾(下)[J].油气地球物理,2006,4(4):53-63.
[124]邹文,陈爱萍等.地震信号的时频分析方法[J].世界地质,2004,23(1):95-99.
[125]刘企英.用频谱比法提取衰减吸收信息[J].石油地球物理勘探,1987,22(5):529-544.
[126]李正文,李琼,吴朝容.沉积盆地有效储集层综合识别技术[M].成都:四川科学技术出版社,2002.
[127] Taner, M. T., Schuelke, J. S., O’Doherty, R. et al. Seismic attributes revisited[C].64thAnnual International Meeting, Society Exploration Geophysics, Expand Abstracts:1104-1106,1994.
[128]Taner, M.T.著,隗寿东摘译地震属性[J].油气地球物理,2006,4(1):55-59.
[129] Brown, A.R. Seismic attributes and their classification[J].The Leading Edge,1996,15(10):1090.
[130] de Rooij, M., Tingdahl, H. Meta-attributes: the key to multi-volume, multi-attributeinterpretations[J]. The Leading Edge,2002,21(10):1050-1053.
[131] Russell, B.H. The application of multivariate statistics and neural networks to the predictionof reservoir parameters using seismic attributes [D]. Calgary: University of Calgary,2004.
[132]高海兵,高亮,周驰等.基于粒子群优化的神经网络训练算法研究[J].电子学报,2004,32(9):1572-1574.
[133] Zhang,J.R.,Zhang J., Lok T.M. et al, A Hybrid particle swarm optimization-back-propagation algorithm for feed-forward neural network training[J]. Applied Mathematics andComputation,2007,185(2):1026-1037.
[134]唐贤伦,庄陵,李银国等.混合粒子群优化算法优化前向神经网络结构和参数[J].计算机应用研究2007,24(12):91-93.
[135] Carvalho M., Ludermir T.B. Particle Swarm Optimization of neural network architecturesand weights[C].7thInternational Conference on Hybrid Intelligent Systems2007, Kaiseslautern,336-339,2007.
[136]魏海坤.神经网络结构设计的理论与方法[M].北京:国防工业出版社,2005.
[137] Orr, M. Introduction to radial basis function neural networks[R]. Research report for theinstitute of adaptive and neural computation, University of Edinburgh,1996.
[138] Powell, M.J.D. Radial basis functions for multivariable interpolation: a review. In Mason,J.C., Cox, M.G. Algorithm for Approximation[M]. Oxford: Clarendon Press,143-147,1987.
[139] Moody, J., Darken, C. Fasting learning in networks of locally-tuned processing units[J].Neural Computation,1989,(1):281-294.
[140] Poggio,T., Girosi, F. Networks for approximation and learning [J]. Proceeding of the IEEE,1990,78(9):1481-1497.
[141]曾云贤,刘微,李西宁.川东北地区飞仙关组构造演化与油气成藏研究[J].天然气工业,2005,25(增刊A):21-23.
[142]王一刚,刘划一,文应初等.川东北飞仙关组鲕滩储层分布规律、勘探方法与远景预测[J].天然气工业,2002,22(增刊):14-18.