基于智能计算的油田开发系统仿真模型及算法研究
|
摘要
油田开发是一个复杂的非线性动态系统,涉及油田开发与地质研究、开采过程模拟分析、油层生产状况判别等多方面的内容。由于地下油藏在形成过程中受复杂的地质沉积环境以及物理、化学条件的影响和约束,各种变量之间的作用关系十分复杂。目前,油藏地质和开发系统仿真主要存在两个方面的困难：一是建模对象复杂,实际油藏系统存在着多种不确定、不确知以及难以定量描述的非线性特性；二是油藏多学科精细研究和开发生产对系统建模提出了更高的精度要求,迫切需要提高油藏系统模型的描述能力和建模方法的灵活性、适用性以及智能化水平。
系统仿真是以计算机为主要工具,通过运行实际系统的仿真模型和算法,对系统输入/输出的信息进行分析与研究,以实现对实际系统运行状态和变化规律的综合评估与预测,是分析、评价系统运行状况或按照给定的性能和功能要求对新的系统进行优化设计的一种技术手段,已成为研究各种系统、特别是非线性动态系统的重要工具。
本课题针对油田地质和开发研究中的若干典型问题,研究基于智能计算理论的系统仿真模型建立方法、模型求解算法和应用技术。理论及模型研究部分主要针对油藏描述和油气开采过程中典型实际问题,研究基于动态神经网络信息处理机制的非线性时变系统建模方法、基于非线性规划理论的判别分析模型以及模型结构和参数的优化方法。论文建立和改进了动态输出过程神经网络、模糊过程神经网络、过程支持向量机等用于油田开发过程模拟与预测的仿真模型,并对模型的连续性、函数逼近能力和适用条件等性质进行了分析和研究；提出了进化算法与非线性规划相结合的地层对比和油井开采状况智能分析模型,以及基于过程神经元网络的动态识别与预测分析模型。学习算法部分主要针对所建立智能模型的结构特征和映射机制,研究具有较高效率和稳定性的学习算法,构建了基于LMS-CGA的混合学习算法、基于数值积分与粒子群相结合的学习算法和基于最优分段函数逼近学习算法等智能模型求解方法,较大提高了网络的学习效率、稳定性以及实际应用能力。在应用技术研究和实际应用方面,建立了针对不同信息处理问题的智能仿真模型应用方法和技术,并应用于油田开发动态系统过程模拟、开发动态指标预测、油藏参数优化计算、小层沉积微相和油层水淹状况自动判别、地层对比和异常井生产状况诊断分析等实际问题的求解,取得了良好的应用结果。
System simulation is a simulation model by running the actual system and using the computer as the main tool, which analyze and research the system10information to complete the comprehensive evaluation and prediction of actual system running state and change rule, it is a kind of technology measure for analyzing、evaluating system running status or carrying through optimization design for the new system according to the given performance and function requirement, has already become the important tool for analyzing、researching various system, especially complex system.
Oil field development is a complex nonlinear system, involving many facets, such as oil field development and geologic research、simulation analysis of exploitation process、 production status analysis of reservoir. Because the reservoir is restricted by complex strata sedimentary environment、physical and chemical condition in the form of reservoir, and the function relation among diversified influencing factors is very complex, the research method of reservoir mostly has two difficulties at present, one is that modeling object is complex, because there exists many uncertainty and nonlinear character which are difficult to quantificationally describe in actual reservoir system, the other is that the oil field development work need higher requirement for system modeling, and urgently need to improve the descriptive ability of reservoir system model and the flexibility、adaptability and intelligence level of modeling method.
In this paper, aiming at several typical problems in oil field geology and development, the modeling method, solving algorithm and application technology of system simulation model based on intelligent computing theory are researched. The theory and model part mainly research the nonlinear time-varying system modeling method based on dynamic ANN, the discriminant analysis model based on nonlinear programming theory, and the optimization method of model structure and parameters aimed at the concrete actual issues in reservoir description and oil gas exploitation. The simulation models for oilfield development process simulation and prediction based on time-varying input/output process neural network, feedback dynamic neural network, fuzzy neural network, process support vector machines are established and improved, and their natures such as continuity, approximation ability, applicable conditions and so on are reached in the paper. An intelligent analysis model based on evolutionary algorithm combined with nonlinear programming for stratigraphic correlation and oil exploitation, and a dynamic model identification model based on improved process neural network are presented at the same time. The learning algorithm part mainly researches learning algorithms with higher efficiency and stability aimed at the structure characteristics and mapping mechanism of intelligent model, builds the solving algorithms based on Fourier function transformation, on LMS-CGA hybrid learning algorithm, on numerical integration, and on optimal piecewise function approximation algorithm etc., and improves network learning efficiency, stability and practical application ability greatly. In the aspect of technology research and practical application, we establish intelligent simulation model application methods and techniques for different information processing problems, and they are applied practically into solving in oilfield development dynamic system simulation, dynamic index prediction, reservoir parameter optimization, automatic identification of small reservoir sedimentary microfacies and water-flooded situation, stratigraphic correlation, abnormal well production status diagnostic analysis and so on, and obtain the better application results.
系统仿真是以计算机为主要工具,通过运行实际系统的仿真模型和算法,对系统输入/输出的信息进行分析与研究,以实现对实际系统运行状态和变化规律的综合评估与预测,是分析、评价系统运行状况或按照给定的性能和功能要求对新的系统进行优化设计的一种技术手段,已成为研究各种系统、特别是非线性动态系统的重要工具。
本课题针对油田地质和开发研究中的若干典型问题,研究基于智能计算理论的系统仿真模型建立方法、模型求解算法和应用技术。理论及模型研究部分主要针对油藏描述和油气开采过程中典型实际问题,研究基于动态神经网络信息处理机制的非线性时变系统建模方法、基于非线性规划理论的判别分析模型以及模型结构和参数的优化方法。论文建立和改进了动态输出过程神经网络、模糊过程神经网络、过程支持向量机等用于油田开发过程模拟与预测的仿真模型,并对模型的连续性、函数逼近能力和适用条件等性质进行了分析和研究；提出了进化算法与非线性规划相结合的地层对比和油井开采状况智能分析模型,以及基于过程神经元网络的动态识别与预测分析模型。学习算法部分主要针对所建立智能模型的结构特征和映射机制,研究具有较高效率和稳定性的学习算法,构建了基于LMS-CGA的混合学习算法、基于数值积分与粒子群相结合的学习算法和基于最优分段函数逼近学习算法等智能模型求解方法,较大提高了网络的学习效率、稳定性以及实际应用能力。在应用技术研究和实际应用方面,建立了针对不同信息处理问题的智能仿真模型应用方法和技术,并应用于油田开发动态系统过程模拟、开发动态指标预测、油藏参数优化计算、小层沉积微相和油层水淹状况自动判别、地层对比和异常井生产状况诊断分析等实际问题的求解,取得了良好的应用结果。
System simulation is a simulation model by running the actual system and using the computer as the main tool, which analyze and research the system10information to complete the comprehensive evaluation and prediction of actual system running state and change rule, it is a kind of technology measure for analyzing、evaluating system running status or carrying through optimization design for the new system according to the given performance and function requirement, has already become the important tool for analyzing、researching various system, especially complex system.
Oil field development is a complex nonlinear system, involving many facets, such as oil field development and geologic research、simulation analysis of exploitation process、 production status analysis of reservoir. Because the reservoir is restricted by complex strata sedimentary environment、physical and chemical condition in the form of reservoir, and the function relation among diversified influencing factors is very complex, the research method of reservoir mostly has two difficulties at present, one is that modeling object is complex, because there exists many uncertainty and nonlinear character which are difficult to quantificationally describe in actual reservoir system, the other is that the oil field development work need higher requirement for system modeling, and urgently need to improve the descriptive ability of reservoir system model and the flexibility、adaptability and intelligence level of modeling method.
In this paper, aiming at several typical problems in oil field geology and development, the modeling method, solving algorithm and application technology of system simulation model based on intelligent computing theory are researched. The theory and model part mainly research the nonlinear time-varying system modeling method based on dynamic ANN, the discriminant analysis model based on nonlinear programming theory, and the optimization method of model structure and parameters aimed at the concrete actual issues in reservoir description and oil gas exploitation. The simulation models for oilfield development process simulation and prediction based on time-varying input/output process neural network, feedback dynamic neural network, fuzzy neural network, process support vector machines are established and improved, and their natures such as continuity, approximation ability, applicable conditions and so on are reached in the paper. An intelligent analysis model based on evolutionary algorithm combined with nonlinear programming for stratigraphic correlation and oil exploitation, and a dynamic model identification model based on improved process neural network are presented at the same time. The learning algorithm part mainly researches learning algorithms with higher efficiency and stability aimed at the structure characteristics and mapping mechanism of intelligent model, builds the solving algorithms based on Fourier function transformation, on LMS-CGA hybrid learning algorithm, on numerical integration, and on optimal piecewise function approximation algorithm etc., and improves network learning efficiency, stability and practical application ability greatly. In the aspect of technology research and practical application, we establish intelligent simulation model application methods and techniques for different information processing problems, and they are applied practically into solving in oilfield development dynamic system simulation, dynamic index prediction, reservoir parameter optimization, automatic identification of small reservoir sedimentary microfacies and water-flooded situation, stratigraphic correlation, abnormal well production status diagnostic analysis and so on, and obtain the better application results.
引文
[1]刘瑞叶,任洪林.计算机仿真技术基础.第1版.北京：电子工业出版社,2004
[2]王子才.仿真技术发展及应用.中国工程科学,2003,5(2)
[3]肖田元,张燕云,陈加栋.系统仿真导论.第1版.北京：清华大学出版社,2000
[4]李书臣,赵礼峰.仿真技术的现状及发展.自动化与仪表,1999,14(6)
[5]肖田元,韩向利,张林.虚拟制造内涵及其应用.系统仿真学报,2000,11(3)：118-123
[6]蒋平,谢道奎.仿真与国民经济.系统仿真学报,2001,11(3)：14-17
[7]常玉连,朱保国,任福深.油田注水生产过程仿真分布式协同建模系统设计.系统仿真学报,2004,16(6)
[8]任福深,常玉连,陈素丽,从日庆.油田供水管网系统仿真模型及其计算方法.大庆石油学院学报,2004,28(4)
[9]许少华,邵秀凤,张健.自动生成基于模糊神经网络及综合评判技术的油井压裂方案.微型电脑应用,2002,18(8)
[10]许少华,何新贵,梁久祯.一类正则模糊神经网络及在沉积微相识别中的应用.控制与决策,2002,17(3)
[11]王子才.关于仿真理论的探讨.系统仿真学报,2000,12(6)
[12]胡峰,孙国基,卫军胡.动态系统计算机仿真技术综述.计算机仿真,2000,17(1)
[13]McCulloch, W. S.; Pitts, W. H.. A logical calculus of the ideas immanent in neuron activity. Bulletin Mathematical Biophysics,1943,5(1):115-133
[14]Rosenblatt F. Principles of neuro-dynamics. Spartan, New York,1962
[15]Widrow B. Generalization and information storage in networks of adaline'neurons'. In: Self-organizing systems. New York, DC:Spartan Books,1962.435-461
[16]Grossberg S. Adaptive pattern classification and universal recoding. Ⅰ:Parallel development and coding of neural feature detectors, Biolog. Cybernetics,1976,23: 121-134
[17]Grossberg S. Adaptive pattern classification and universal recoding. Ⅱ:Feedback, expectation, olfaction, and illusion, Biology Cybernetics,1976,23:187-202
[18]Anderson J A. A simple neural network generating interactive memory. Mathematical Biosciences,1972,14:197-200
[19]Fukushima K. Cognitron:a self-organizing multi-layered neural network [J]. Biology Cybernetics,1975,20(3):121-136
[20]Kohonen T. Self-organization and associative memory. Springer-Verlag, Berlin,1984
[21]Hopfield J J. Neural networks and physical systems with emergent collective computational abilities. Proc. of the National Academy of Science, U.S.A.1983,79: 2554-2558
[22]Hinton G E.,Nowlan S J. How learning can guide evolution. Complex systems,1987(1): 495-502
[23]Hecht-Nielsen R. Theory of the back-propagation neural network. Proceedings of International Joint Conference on of Neural Networks.1989,1:593-599
[24]Hornik, K.; Stinchcombe, M.; White, H.. Universal approximation of an unknown mapping and its derivatives using multilayer feedforword networks. Neural Networks, 1990,3:551-560
[25]Funahashi, K. On the approximate realization of continuous mappings by neural networks. Neural Networks,1989,2:183-192
[26]Hinton G H. Sejnowskii T J, Ackley D H. Boltzmann machine:constraint satisfaction networks that learn. CMU-CS-84-119, Carnegie-Millon Uni.,1984
[27]Powell M J D. Radial basis functions for multivariate interpolation:a review. Department of App. Math. and Theoretical Physics, Cambridge University. Cambridge, England. 1985
[28]Albus J. S. A new approach to manipulator control:The cerebellar model articulation controller (CMAC). Trans. of the ASME Journal of Dynamic Systems. Measurement and Control,1975,97:220-227
[29]欧阳楷,刘卫芳.基于生物的神经网络的理论框架—神经元模型.北京生物医学工程,1997,16(2)：93-101
[30]Zhang Li I, Tao Huizhong W, Holt C E,et al. A critical window for cooperation and competition among developing retinotectal synapses. Nature,1998,395:37-44
[31]Draye J S,et al. Dynamic Recurrent NN:A Dynamical Analysis. IEEE Trans SMC(B),1996,26:692-706
[32]何新贵,梁久祯.过程神经元网络的若干理论问题.中国工程科学,2000,2(12)：40-44
[33]He Xin-Gui, Liang Jiu-Zhen. Process neural networks. In:World Computer Congress 2000, Proceedings of Conference on Intelligent Information Processing. Beijing,2000: 143-146
[34]刘晓鸿,戴汝为.线性阈值单元神经元网络的图灵等价性.神经元网络理论模型及应用方法研究论文集(二),中科院生物物理所及自动化所,1993：104-109
[35]Hecht-Nielsen R. Theory of the back-propagation neural network. Proceedings of International Joint Conference on of Neural Networks.1989,1:593-599
[36]Hornik, K.; Stinchcombe, M.; White, H.. Universal approximation of an unknown mapping and its derivatives using multilayer feedforword networks. Neural Networks, 1990,3:551-560
[37]Hornik, K.; Stinchcombe, M.; White, H.. Multilayer feedforword networks are universal approximators. Neural Networks,1989,2:359-366
[38]Funahashi, K. On the approximate realization of continuous mappings by neural networks. Neural Networks,1989,2:183-192
[39]German S.et al. Neural Networks and the Bias/Variance Dilemma. Neural Computation, 1992,4:1-58
[40]Sandeep Adwankar, Ravi N Banavar. A recurrent network for dynamic system identification [J].International Journal of Systems Science,1997,28(12):1239-1250
[41]George A Rovithakis.Tracking control of multi-input affine nonlinear dynamical systems with unknown nonlinearities using dynamical neural networks [J]. IEEE Transactions on Systems, Man and Cybernetics-Part B:Cybernetics,1999,29(2):179-189
[42]魏剑平,李华德,余达太等.基于回归神经网络的复杂工业对象的建模.北京科技大学学报,1999,21(4)：406-408
[43]Hopfield J J. Neural networks and physical systems with emergent collective computational Abilities [A]. Proceedings of the Academy of Science [C],US,1982,79:2554-2558
[44]Pham D T, etal. Dynamic system identification using Elman and Jordan Networks [A]. Neural Networks for Chemical Engineers [C]. Elsevier Sciense Publishers,1995, 573-592.
[45]Bhat N, McAvoy T J. Use of neural nets for dynamic modeling and control of chemical process systems [J]. Computers Chem. Eng.,1990,14(4/5),573-583.
[46]Narendra K S, et. al. Identification and control for dynamic systems using neural networks [J]. IEEE Transactions on Neural Networks,1990,1(1):4-27.
[47]KuCC, LeeK Y. Diagonal recurrent neural networks for dynamic systems control [J]. IEEE Transactions on Neural Networks.1995,6(1):144-155
[48]Elman J L. Finding structure in time [J]. CognitiveScience,1990,14:179-211.
[49]Jordan M I. Attractor dynamics and parallelism in a connectionist sequential machines [A].Proceedings of the 8th Annual Conference of the Cognitive Science Society[C], 1986,531-546.
[50]Waibel A T, et al. Phoneme Recognition using time-delay NN, IEEE Trans ASSP-37, 1989,328-329.
[51]Chen S,et al. NN for Nonlinear Dynamic System Modelling and Identification, Int. J.Control,1992,56,319-346.
[52]Mozec M C, Neural Net Architectures for Temporal Sequence Processing. In:Weigend A S, et al ed. Time Series Prediction:Forecasting the Future and Understanding the Past, Addison-Wesley,1993
[53]Hertz J, et al. Introduction to the Theory of Nerual Computation. Reading, MA, Addison-Wesley,1991
[54]王攀,苏智,冯珊.局部回归Elman网络学习算法的注记.武汉理工大学学报,2002,24(2)
[55]丛爽,高雪鹏.几种递归神经网络及其在系统辨识中的应用.系统工程与电子技术,2003,25(2)
[56]Pham D T, Liu X.. Training of Elman Networks and Dynamic System Modeling[J]. International Journal of System Science,1996,27(2):221-226
[57]时小虎,梁艳春,徐旭.改进的Elman模型与递归反传控制神经网络.软件学报,2003,14(6)
[58]Narendra Kumpati S,Kanan Parthasarathy. Gradient Methods for the Op2timization of Dynamical System Containing Neural Networks[J]. IEEETrans. On Neural Networks, 1991,2(2):252-262.
[59]Williams R J, et al. An Efficient Gradient-Based Algorithm for on Line Training of Recurrent Network Trajectiories. Neural Computation,1990,2:490-501
[60]Williams R J, et al. A Learning Algorithm for Continually Running Fully Recurrent NN. Neural Computation,1989,1:270-280
[61]Bersin H, et al. A simplification of the Backpropagation Through Time Algorithm for Optimal Neurlcontrol. TEEE Trans NN,1997,2:437-441
[62]赵奇,刘开第,庞彦军.Elman神经网络训练方法及其在非线性系统辨识中的应用. 煤矿机械,2005,(5)
[63]张丽红,王艳.基于回归神经网络自适应快速BP算法.计算机测量与控制.2004,12(5)
[64]Simon. Haykin. Neural networks—A comprehensive foundation(second edition). Beij ing:Tinghua University Press,2001.
[65]Tsoi A C,et al. Exploring the Nonlinear Dynamic Behavior of ANN, Proc, IJCNN'94, 1994,1000-1005.
[66]许少华,何新贵.基于函数正交基展开的过程神经网络学习算法.计算机学报,2004,27(5)
[67]柳重堪.正交函数及其应用.北京：国防工业出版社,1982
[68]何新贵,许少华.过程神经网络的训练及其应用.中国工程科学,2001,3(4)
[69]徐丽娜.神经网络控制.北京：电子工业出版社,2002
[70]张乃尧,阎平凡.神经网络与模糊控制.北京：清华大学出版社,1998
[71]王京慧,李宏光.动态模糊神经网络研究.北京化工大学学报,2003,30(2)：78
[72]张友旺,桂卫华,赵泉明.基于动态递归模糊神经网络的自适应电液位置跟踪系统.控制理论与应用,2005,22(4)
[73]赵永胜,李风林,黄伏生.油藏动态系统辨识及预测论文集.北京：石油工业出版社,1999
[74]陈元千.水驱曲线关系式的推导.石油学报,1985(2)
[74]F.F.克雷格.油田注水开发工程方法.北京：石油化学工业出版社,1997
[75]H.C.斯利德著.实用油藏工程方法.北京：石油化学工业出版社,1982
[76]葛家礼主编.油气层渗流力学.北京：石油化学工业出版社,1982
[77]顾克金编译.礁灰岩底水油藏开发指标预测.油气田开发工程译丛,1990(4)
[78]金荪主编.采油地质工程.北京：石油工业出版社,1985
[79]翁文波著.预测论基础.北京：石油工业出版社,1984
[80]齐与峰,朱国金.注水开发油田中后期动态预测方法和应用软件.石油勘探与开发,1990(1)
[81]方凌云,万新德.砂岩油藏注水开发动态分析.北京：石油工业出版社,1998
[82]宋考平,宋洪才,吴文祥主编.油藏数值模拟理论基础.北京：石油工业出版社,1996
[83]何新贵,梁久祯.过程神经元网络的若干理论问题.中国工程科学,2000,2(12).
[84]许少华,何新贵等.关于连续过程神经元网络的一些理论问题.电子学报,2006,34(10)
[85]马瑞新,刘宇,覃征.求解约束优化问题的动量粒子群算法[J].系统仿真学报,2010,22(11)：2485-2488.
[86]丰镇平,李军,沈祖达.遗传算法及其在透平机械化设计中的应用[J].燃气轮机技术,1997,11(2)：13-22.
[87]Li Jun, Feng Zhenping. Aerodynamic Optimum Design of Transonic Turbine Cascades Using Genetic Algorithms [J]. Journal of Thermal Science,1997,6(2):364-368.
[88]童彤,丰镇平,李军.遗传算法在透平叶栅多目标优化设计中的应用[J].中国电机工程学报,1999,19(6)：74-76.
[89]缪明非,张永良,马吉明.基于多目标进化算法的差动式调压室优化研究[J].水力发电学报,2010,29(1)：57-61.
[90]公茂果,焦李成,杨咚咚,马文萍.进化多目标优化算法研究[J].软件学报,2009,20(2)：271-289.
[91]许少华,肖红.基于离散Walsh变换的过程神经元网络学习算法[J].大庆石油学院学报,2003,27(4)：59-61..
[92]陈炳瑞,杨成祥.自适应混沌遗传混合算法及其参数敏感性分析[J].东北大学学报,2006,27(6)：689-692.
[93]李兵,蒋慰孙.混沌优化方法及其应用[J].控制理论与应用,1997,14(4)：613-615
[94]许少华,何新贵.过程神经网络一种基于函数正交基展开的学习算法[J].计算机学报,2004,27(5)：645-649
[95]郑向伟,刘宏.多目标进化算法研究进展.计算机科学,2007,34(7)：187-192.
[96]陈炳瑞,杨成祥.自适应混沌遗传混合算法及其参数敏感性分析[J].东北大学学报,2006,27(6)：689-692.
[97]潘峰,陈杰.粒子群优化算法模型分析[J].自动化学报,2006,32(3)：369-378.
[98]伍铁斌,成运,周桃云.基于混沌遗传算法的PID参数优化[J].计算机仿真,2009,26(5)：202-205
[99]李欣然.粒子群优化算法研究[J].计算机与现代化,2010,11(6)：6-8.
[100]Liu, D., Tan, KC., Goh, CK., and Ho, WK. A Multiobjective Memetic Algorithm Based on Particle Swarm Optimization. IEEE Transactions on Systems, Man and Cybernetics, Part B,2007,37(1):42-50.
[101]Li, X. Better spread and convergence:Particle swarm multiobjective optimization using the maximin fitness function. In Proceeding of the Genetic and Evolutionary Computation, Springer,2004:117-128.
[102]Balling, R. The maximin fitness function; multiobjective city and regional planning. In Second International Conference on Evolutionary Multi-Criterion Optimization, EMO, Springer,2003:1-15.
[103]Mahfouf, M., Chen, M.Y., and Linkens, D.A. Adaptive weighted particle swarm optimisation for multi-objective optimal design of alloy steels. In Proceedings of Parallel Problem Solving from Nature-PPSN VIII, Springer,2004:762-771.
[104]F. van den Bergh,A.P.Engelbrecht.Effects of swarm size on cooperative particle swarm optimisers[C].Proceedings of the Genetic and Evolutionary Computation Conference,San Francisco,USA,2001
[105]A. Ratnaweera,S.K. Halgamuge,H.C. Watson. Self-organizing hierarchical particle swarm optimizer with time-varying acceleration coefficients [J]. Evolutionary Computation, IEEE Transactions on,2004.8(3):240-255
[106]Mendes R.Population Topologies and Their Influence in Particle Swarm Performance[D].Lisbon,Portugal:University of Minho,2004
[107]Mikki S.,Kishk A.A.Investigation of the quantum Partiele swarm optimization technique for electromagnetic applications[C].2005 IEEE Antennas and Propagation Society International Symposium, Volume:2A:45-48
[108]Ho, SL., Yang, S., Ni, G, Lo, EWC., and Wong, HC. A particle swarm optimization-based method for multiobjective design optimizations[J]. IEEE Transactions on Magnetics,2005,41(5):1756-1759
[109]X. Hu, R. Eberhart. Multiobjective optimization using dynamic neighborhood particle swarm optimization[J]. Proceedings of the Evolutionary Computation on,2002: 1677-1681.
[110]X. Hu, R.C. Eberhart,Y. Shi. Particle swarm with extended memory for multiobjective optimization[J].2003:IEEE.
[111]Parsopoulos, K.E., Tasoulis, D.K., and Vrahatis, M.N. Multiobjective optimization using parallel vector evaluated particle swarm optimization. In Proceedings of the IASTED International Conference on Artificial Intelligence and Applications,2004,volume 2, 823-828.
[112]Chow, C. and Tsui, H. Autonomous agent response learning by a multi-species particle swarm optimization. In Congress on Evolutionary Computation, CEC2004,2004,volume 1,778-785.
[113]Coello, C.A.C., Pulido, GT., and Lechuga, MS. Handling multiple objectives with particle swarm optimization[J]. IEEE Transactions on Evolutionary Computation, 2004,8(3):256-279
[114]Fieldsend, J. and Singh, S. A multi-objective algorithm based upon particle swarm optimization, an efficient data structure and turbulence [C]. Proceedings of The UK Workshop on Computational Intelligence,2002:34-44
[114]Mostaghim, S. and Teich, J. The role of e-dominance in multi objective particle swarm optimization methods[C]. Proceedings of the 2003 Congress on Evolutionary Computation,2003:1764-1771
[116]Sierra, M.R. and Coello, C.A.C. Improving pso-based multi-objective optimization using crowding, mutation and ε-dominance[C]. The Third International Conference on Evolutionary Multi-Criterion Optimization,EMO 2005,2005:505-519
[117]Kennedy J, Eberhart R C. Particle swarms optimization[C]. Proceedings of IEEE international conference on Neural Networks. USA,1995:1942-1948
[118]Lin S W, Ying K C, Chen S C, et al. Particle swarm optimization for parameter determination and feature selection of support vector machines [J]. Expert Systems with Applications,2008,35(4):1817-1824
[119]Eberhart R C, Shi Y, Comparing inertia weights and constriction factors in particle swarm optimization, in:Proceedings of the IEEE Congress on Evolutionary Computation, San Diego, USA,2000, pp.84-88
[120]张干清,龚宪生.变量相关情况下基于杂交GA-PSO算法的结构协同优化[J].机械工程学报,2012,48(15)：113-125
[121]Bergh F, Engelbrecht A P. A study of particle swarm optimization particle trajectories [J]. Information Science,2006,176(8):937-971
[122]Clerc M, Kennedy J. The particle swarm-explosion, stability, and convergence in a multidimensional complex space [J]. IEEE Transactions on Evolutionary Computation 2002,6(1):58-73
[123]Jiang Y, Hu T S, Huang C C, et al. An improved particle swarm optimization algorithm [J]. Applied Mathematics and Computation,2007,193(1):231-239
[124]HAN K H, PARK K H. Parallel quantum-inspired genetic algorithm for combinatorial optimization problems[C]. Proceeding of IEEE Conf on Evolutionary Computation. Piscataway:IEEE Press,2001:1442-1429
[125]张淑清,贾健,高敏,韩叙.混沌时间序列重构相空间参数选取研究[J].物理学报,2010,59(3)：1576-1582
[126]Swagatam D, Ajith A, Amit K. Automatic kernel clustering with a multi-elitist particle swarm optimization algorithm. [J]. Pattern Recognition Letters,2008,29(5):688-699
[127]Jarboui B, Cheikh M, Siarry P, et al. Combinatorial particle swarm optimization for partitional clustering problem [J]. Applied Mathematics and Computation,2007,192(2): 337-345
[128]赵淑清,郑薇.随机信号分析.第1版,哈尔滨：哈尔滨工业大学出版社,1999：54-56
[2]王子才.仿真技术发展及应用.中国工程科学,2003,5(2)
[3]肖田元,张燕云,陈加栋.系统仿真导论.第1版.北京：清华大学出版社,2000
[4]李书臣,赵礼峰.仿真技术的现状及发展.自动化与仪表,1999,14(6)
[5]肖田元,韩向利,张林.虚拟制造内涵及其应用.系统仿真学报,2000,11(3)：118-123
[6]蒋平,谢道奎.仿真与国民经济.系统仿真学报,2001,11(3)：14-17
[7]常玉连,朱保国,任福深.油田注水生产过程仿真分布式协同建模系统设计.系统仿真学报,2004,16(6)
[8]任福深,常玉连,陈素丽,从日庆.油田供水管网系统仿真模型及其计算方法.大庆石油学院学报,2004,28(4)
[9]许少华,邵秀凤,张健.自动生成基于模糊神经网络及综合评判技术的油井压裂方案.微型电脑应用,2002,18(8)
[10]许少华,何新贵,梁久祯.一类正则模糊神经网络及在沉积微相识别中的应用.控制与决策,2002,17(3)
[11]王子才.关于仿真理论的探讨.系统仿真学报,2000,12(6)
[12]胡峰,孙国基,卫军胡.动态系统计算机仿真技术综述.计算机仿真,2000,17(1)
[13]McCulloch, W. S.; Pitts, W. H.. A logical calculus of the ideas immanent in neuron activity. Bulletin Mathematical Biophysics,1943,5(1):115-133
[14]Rosenblatt F. Principles of neuro-dynamics. Spartan, New York,1962
[15]Widrow B. Generalization and information storage in networks of adaline'neurons'. In: Self-organizing systems. New York, DC:Spartan Books,1962.435-461
[16]Grossberg S. Adaptive pattern classification and universal recoding. Ⅰ:Parallel development and coding of neural feature detectors, Biolog. Cybernetics,1976,23: 121-134
[17]Grossberg S. Adaptive pattern classification and universal recoding. Ⅱ:Feedback, expectation, olfaction, and illusion, Biology Cybernetics,1976,23:187-202
[18]Anderson J A. A simple neural network generating interactive memory. Mathematical Biosciences,1972,14:197-200
[19]Fukushima K. Cognitron:a self-organizing multi-layered neural network [J]. Biology Cybernetics,1975,20(3):121-136
[20]Kohonen T. Self-organization and associative memory. Springer-Verlag, Berlin,1984
[21]Hopfield J J. Neural networks and physical systems with emergent collective computational abilities. Proc. of the National Academy of Science, U.S.A.1983,79: 2554-2558
[22]Hinton G E.,Nowlan S J. How learning can guide evolution. Complex systems,1987(1): 495-502
[23]Hecht-Nielsen R. Theory of the back-propagation neural network. Proceedings of International Joint Conference on of Neural Networks.1989,1:593-599
[24]Hornik, K.; Stinchcombe, M.; White, H.. Universal approximation of an unknown mapping and its derivatives using multilayer feedforword networks. Neural Networks, 1990,3:551-560
[25]Funahashi, K. On the approximate realization of continuous mappings by neural networks. Neural Networks,1989,2:183-192
[26]Hinton G H. Sejnowskii T J, Ackley D H. Boltzmann machine:constraint satisfaction networks that learn. CMU-CS-84-119, Carnegie-Millon Uni.,1984
[27]Powell M J D. Radial basis functions for multivariate interpolation:a review. Department of App. Math. and Theoretical Physics, Cambridge University. Cambridge, England. 1985
[28]Albus J. S. A new approach to manipulator control:The cerebellar model articulation controller (CMAC). Trans. of the ASME Journal of Dynamic Systems. Measurement and Control,1975,97:220-227
[29]欧阳楷,刘卫芳.基于生物的神经网络的理论框架—神经元模型.北京生物医学工程,1997,16(2)：93-101
[30]Zhang Li I, Tao Huizhong W, Holt C E,et al. A critical window for cooperation and competition among developing retinotectal synapses. Nature,1998,395:37-44
[31]Draye J S,et al. Dynamic Recurrent NN:A Dynamical Analysis. IEEE Trans SMC(B),1996,26:692-706
[32]何新贵,梁久祯.过程神经元网络的若干理论问题.中国工程科学,2000,2(12)：40-44
[33]He Xin-Gui, Liang Jiu-Zhen. Process neural networks. In:World Computer Congress 2000, Proceedings of Conference on Intelligent Information Processing. Beijing,2000: 143-146
[34]刘晓鸿,戴汝为.线性阈值单元神经元网络的图灵等价性.神经元网络理论模型及应用方法研究论文集(二),中科院生物物理所及自动化所,1993：104-109
[35]Hecht-Nielsen R. Theory of the back-propagation neural network. Proceedings of International Joint Conference on of Neural Networks.1989,1:593-599
[36]Hornik, K.; Stinchcombe, M.; White, H.. Universal approximation of an unknown mapping and its derivatives using multilayer feedforword networks. Neural Networks, 1990,3:551-560
[37]Hornik, K.; Stinchcombe, M.; White, H.. Multilayer feedforword networks are universal approximators. Neural Networks,1989,2:359-366
[38]Funahashi, K. On the approximate realization of continuous mappings by neural networks. Neural Networks,1989,2:183-192
[39]German S.et al. Neural Networks and the Bias/Variance Dilemma. Neural Computation, 1992,4:1-58
[40]Sandeep Adwankar, Ravi N Banavar. A recurrent network for dynamic system identification [J].International Journal of Systems Science,1997,28(12):1239-1250
[41]George A Rovithakis.Tracking control of multi-input affine nonlinear dynamical systems with unknown nonlinearities using dynamical neural networks [J]. IEEE Transactions on Systems, Man and Cybernetics-Part B:Cybernetics,1999,29(2):179-189
[42]魏剑平,李华德,余达太等.基于回归神经网络的复杂工业对象的建模.北京科技大学学报,1999,21(4)：406-408
[43]Hopfield J J. Neural networks and physical systems with emergent collective computational Abilities [A]. Proceedings of the Academy of Science [C],US,1982,79:2554-2558
[44]Pham D T, etal. Dynamic system identification using Elman and Jordan Networks [A]. Neural Networks for Chemical Engineers [C]. Elsevier Sciense Publishers,1995, 573-592.
[45]Bhat N, McAvoy T J. Use of neural nets for dynamic modeling and control of chemical process systems [J]. Computers Chem. Eng.,1990,14(4/5),573-583.
[46]Narendra K S, et. al. Identification and control for dynamic systems using neural networks [J]. IEEE Transactions on Neural Networks,1990,1(1):4-27.
[47]KuCC, LeeK Y. Diagonal recurrent neural networks for dynamic systems control [J]. IEEE Transactions on Neural Networks.1995,6(1):144-155
[48]Elman J L. Finding structure in time [J]. CognitiveScience,1990,14:179-211.
[49]Jordan M I. Attractor dynamics and parallelism in a connectionist sequential machines [A].Proceedings of the 8th Annual Conference of the Cognitive Science Society[C], 1986,531-546.
[50]Waibel A T, et al. Phoneme Recognition using time-delay NN, IEEE Trans ASSP-37, 1989,328-329.
[51]Chen S,et al. NN for Nonlinear Dynamic System Modelling and Identification, Int. J.Control,1992,56,319-346.
[52]Mozec M C, Neural Net Architectures for Temporal Sequence Processing. In:Weigend A S, et al ed. Time Series Prediction:Forecasting the Future and Understanding the Past, Addison-Wesley,1993
[53]Hertz J, et al. Introduction to the Theory of Nerual Computation. Reading, MA, Addison-Wesley,1991
[54]王攀,苏智,冯珊.局部回归Elman网络学习算法的注记.武汉理工大学学报,2002,24(2)
[55]丛爽,高雪鹏.几种递归神经网络及其在系统辨识中的应用.系统工程与电子技术,2003,25(2)
[56]Pham D T, Liu X.. Training of Elman Networks and Dynamic System Modeling[J]. International Journal of System Science,1996,27(2):221-226
[57]时小虎,梁艳春,徐旭.改进的Elman模型与递归反传控制神经网络.软件学报,2003,14(6)
[58]Narendra Kumpati S,Kanan Parthasarathy. Gradient Methods for the Op2timization of Dynamical System Containing Neural Networks[J]. IEEETrans. On Neural Networks, 1991,2(2):252-262.
[59]Williams R J, et al. An Efficient Gradient-Based Algorithm for on Line Training of Recurrent Network Trajectiories. Neural Computation,1990,2:490-501
[60]Williams R J, et al. A Learning Algorithm for Continually Running Fully Recurrent NN. Neural Computation,1989,1:270-280
[61]Bersin H, et al. A simplification of the Backpropagation Through Time Algorithm for Optimal Neurlcontrol. TEEE Trans NN,1997,2:437-441
[62]赵奇,刘开第,庞彦军.Elman神经网络训练方法及其在非线性系统辨识中的应用. 煤矿机械,2005,(5)
[63]张丽红,王艳.基于回归神经网络自适应快速BP算法.计算机测量与控制.2004,12(5)
[64]Simon. Haykin. Neural networks—A comprehensive foundation(second edition). Beij ing:Tinghua University Press,2001.
[65]Tsoi A C,et al. Exploring the Nonlinear Dynamic Behavior of ANN, Proc, IJCNN'94, 1994,1000-1005.
[66]许少华,何新贵.基于函数正交基展开的过程神经网络学习算法.计算机学报,2004,27(5)
[67]柳重堪.正交函数及其应用.北京：国防工业出版社,1982
[68]何新贵,许少华.过程神经网络的训练及其应用.中国工程科学,2001,3(4)
[69]徐丽娜.神经网络控制.北京：电子工业出版社,2002
[70]张乃尧,阎平凡.神经网络与模糊控制.北京：清华大学出版社,1998
[71]王京慧,李宏光.动态模糊神经网络研究.北京化工大学学报,2003,30(2)：78
[72]张友旺,桂卫华,赵泉明.基于动态递归模糊神经网络的自适应电液位置跟踪系统.控制理论与应用,2005,22(4)
[73]赵永胜,李风林,黄伏生.油藏动态系统辨识及预测论文集.北京：石油工业出版社,1999
[74]陈元千.水驱曲线关系式的推导.石油学报,1985(2)
[74]F.F.克雷格.油田注水开发工程方法.北京：石油化学工业出版社,1997
[75]H.C.斯利德著.实用油藏工程方法.北京：石油化学工业出版社,1982
[76]葛家礼主编.油气层渗流力学.北京：石油化学工业出版社,1982
[77]顾克金编译.礁灰岩底水油藏开发指标预测.油气田开发工程译丛,1990(4)
[78]金荪主编.采油地质工程.北京：石油工业出版社,1985
[79]翁文波著.预测论基础.北京：石油工业出版社,1984
[80]齐与峰,朱国金.注水开发油田中后期动态预测方法和应用软件.石油勘探与开发,1990(1)
[81]方凌云,万新德.砂岩油藏注水开发动态分析.北京：石油工业出版社,1998
[82]宋考平,宋洪才,吴文祥主编.油藏数值模拟理论基础.北京：石油工业出版社,1996
[83]何新贵,梁久祯.过程神经元网络的若干理论问题.中国工程科学,2000,2(12).
[84]许少华,何新贵等.关于连续过程神经元网络的一些理论问题.电子学报,2006,34(10)
[85]马瑞新,刘宇,覃征.求解约束优化问题的动量粒子群算法[J].系统仿真学报,2010,22(11)：2485-2488.
[86]丰镇平,李军,沈祖达.遗传算法及其在透平机械化设计中的应用[J].燃气轮机技术,1997,11(2)：13-22.
[87]Li Jun, Feng Zhenping. Aerodynamic Optimum Design of Transonic Turbine Cascades Using Genetic Algorithms [J]. Journal of Thermal Science,1997,6(2):364-368.
[88]童彤,丰镇平,李军.遗传算法在透平叶栅多目标优化设计中的应用[J].中国电机工程学报,1999,19(6)：74-76.
[89]缪明非,张永良,马吉明.基于多目标进化算法的差动式调压室优化研究[J].水力发电学报,2010,29(1)：57-61.
[90]公茂果,焦李成,杨咚咚,马文萍.进化多目标优化算法研究[J].软件学报,2009,20(2)：271-289.
[91]许少华,肖红.基于离散Walsh变换的过程神经元网络学习算法[J].大庆石油学院学报,2003,27(4)：59-61..
[92]陈炳瑞,杨成祥.自适应混沌遗传混合算法及其参数敏感性分析[J].东北大学学报,2006,27(6)：689-692.
[93]李兵,蒋慰孙.混沌优化方法及其应用[J].控制理论与应用,1997,14(4)：613-615
[94]许少华,何新贵.过程神经网络一种基于函数正交基展开的学习算法[J].计算机学报,2004,27(5)：645-649
[95]郑向伟,刘宏.多目标进化算法研究进展.计算机科学,2007,34(7)：187-192.
[96]陈炳瑞,杨成祥.自适应混沌遗传混合算法及其参数敏感性分析[J].东北大学学报,2006,27(6)：689-692.
[97]潘峰,陈杰.粒子群优化算法模型分析[J].自动化学报,2006,32(3)：369-378.
[98]伍铁斌,成运,周桃云.基于混沌遗传算法的PID参数优化[J].计算机仿真,2009,26(5)：202-205
[99]李欣然.粒子群优化算法研究[J].计算机与现代化,2010,11(6)：6-8.
[100]Liu, D., Tan, KC., Goh, CK., and Ho, WK. A Multiobjective Memetic Algorithm Based on Particle Swarm Optimization. IEEE Transactions on Systems, Man and Cybernetics, Part B,2007,37(1):42-50.
[101]Li, X. Better spread and convergence:Particle swarm multiobjective optimization using the maximin fitness function. In Proceeding of the Genetic and Evolutionary Computation, Springer,2004:117-128.
[102]Balling, R. The maximin fitness function; multiobjective city and regional planning. In Second International Conference on Evolutionary Multi-Criterion Optimization, EMO, Springer,2003:1-15.
[103]Mahfouf, M., Chen, M.Y., and Linkens, D.A. Adaptive weighted particle swarm optimisation for multi-objective optimal design of alloy steels. In Proceedings of Parallel Problem Solving from Nature-PPSN VIII, Springer,2004:762-771.
[104]F. van den Bergh,A.P.Engelbrecht.Effects of swarm size on cooperative particle swarm optimisers[C].Proceedings of the Genetic and Evolutionary Computation Conference,San Francisco,USA,2001
[105]A. Ratnaweera,S.K. Halgamuge,H.C. Watson. Self-organizing hierarchical particle swarm optimizer with time-varying acceleration coefficients [J]. Evolutionary Computation, IEEE Transactions on,2004.8(3):240-255
[106]Mendes R.Population Topologies and Their Influence in Particle Swarm Performance[D].Lisbon,Portugal:University of Minho,2004
[107]Mikki S.,Kishk A.A.Investigation of the quantum Partiele swarm optimization technique for electromagnetic applications[C].2005 IEEE Antennas and Propagation Society International Symposium, Volume:2A:45-48
[108]Ho, SL., Yang, S., Ni, G, Lo, EWC., and Wong, HC. A particle swarm optimization-based method for multiobjective design optimizations[J]. IEEE Transactions on Magnetics,2005,41(5):1756-1759
[109]X. Hu, R. Eberhart. Multiobjective optimization using dynamic neighborhood particle swarm optimization[J]. Proceedings of the Evolutionary Computation on,2002: 1677-1681.
[110]X. Hu, R.C. Eberhart,Y. Shi. Particle swarm with extended memory for multiobjective optimization[J].2003:IEEE.
[111]Parsopoulos, K.E., Tasoulis, D.K., and Vrahatis, M.N. Multiobjective optimization using parallel vector evaluated particle swarm optimization. In Proceedings of the IASTED International Conference on Artificial Intelligence and Applications,2004,volume 2, 823-828.
[112]Chow, C. and Tsui, H. Autonomous agent response learning by a multi-species particle swarm optimization. In Congress on Evolutionary Computation, CEC2004,2004,volume 1,778-785.
[113]Coello, C.A.C., Pulido, GT., and Lechuga, MS. Handling multiple objectives with particle swarm optimization[J]. IEEE Transactions on Evolutionary Computation, 2004,8(3):256-279
[114]Fieldsend, J. and Singh, S. A multi-objective algorithm based upon particle swarm optimization, an efficient data structure and turbulence [C]. Proceedings of The UK Workshop on Computational Intelligence,2002:34-44
[114]Mostaghim, S. and Teich, J. The role of e-dominance in multi objective particle swarm optimization methods[C]. Proceedings of the 2003 Congress on Evolutionary Computation,2003:1764-1771
[116]Sierra, M.R. and Coello, C.A.C. Improving pso-based multi-objective optimization using crowding, mutation and ε-dominance[C]. The Third International Conference on Evolutionary Multi-Criterion Optimization,EMO 2005,2005:505-519
[117]Kennedy J, Eberhart R C. Particle swarms optimization[C]. Proceedings of IEEE international conference on Neural Networks. USA,1995:1942-1948
[118]Lin S W, Ying K C, Chen S C, et al. Particle swarm optimization for parameter determination and feature selection of support vector machines [J]. Expert Systems with Applications,2008,35(4):1817-1824
[119]Eberhart R C, Shi Y, Comparing inertia weights and constriction factors in particle swarm optimization, in:Proceedings of the IEEE Congress on Evolutionary Computation, San Diego, USA,2000, pp.84-88
[120]张干清,龚宪生.变量相关情况下基于杂交GA-PSO算法的结构协同优化[J].机械工程学报,2012,48(15)：113-125
[121]Bergh F, Engelbrecht A P. A study of particle swarm optimization particle trajectories [J]. Information Science,2006,176(8):937-971
[122]Clerc M, Kennedy J. The particle swarm-explosion, stability, and convergence in a multidimensional complex space [J]. IEEE Transactions on Evolutionary Computation 2002,6(1):58-73
[123]Jiang Y, Hu T S, Huang C C, et al. An improved particle swarm optimization algorithm [J]. Applied Mathematics and Computation,2007,193(1):231-239
[124]HAN K H, PARK K H. Parallel quantum-inspired genetic algorithm for combinatorial optimization problems[C]. Proceeding of IEEE Conf on Evolutionary Computation. Piscataway:IEEE Press,2001:1442-1429
[125]张淑清,贾健,高敏,韩叙.混沌时间序列重构相空间参数选取研究[J].物理学报,2010,59(3)：1576-1582
[126]Swagatam D, Ajith A, Amit K. Automatic kernel clustering with a multi-elitist particle swarm optimization algorithm. [J]. Pattern Recognition Letters,2008,29(5):688-699
[127]Jarboui B, Cheikh M, Siarry P, et al. Combinatorial particle swarm optimization for partitional clustering problem [J]. Applied Mathematics and Computation,2007,192(2): 337-345
[128]赵淑清,郑薇.随机信号分析.第1版,哈尔滨：哈尔滨工业大学出版社,1999：54-56
© 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 |