基于混合算法的神经网络辨识方法及其在油田中的应用
|
摘要
人工神经网络(NN)、遗传算法(GA)和模拟退火算法(SAA)的研究是当代信息科学的前沿和热点,也为非线性系统辨识理论的发展开辟了崭新的途径。文中围绕非线性系统辨识和预测方法及其在油田系统的应用,展开了深入研究,提出了基于混合算法的油田系统NN辨识和预测的一系列新方法。主要完成了如下工作。
首先,以油田试井解释为应用背景,以试井偏微分方程为依托,经过数学推导,给出了试井解释基函数神经网络(WTBFNN)模型,为试井系统辨识和预测奠定了理论基础。试井解释基函数是典型的复杂多峰函数。它的参数(地层参数)值是试井解释的依据,因而要求其估值应具有唯一性。为了解决这一难题,文中将系统辨识、GA、聚类算法等多项技术融于一体,提出了两种新型混合GA:种族遗传进化算法(SGEA)和启发式GA。仿真实验证明了SGEA的全局收敛性优于带共享机制的GA。文中以马尔可夫链为工具,证明了上述两种新型GA具有全局收敛性。在此基础上,提出了基于新型混合GA的WTBFNN辨识和预测新方法,其中以WTBFNN为模型框架,用F检验法确定模型结构参数,用最小二乘法辨识WTBFNN的权值,用上述两种新型混合GA之一辨识WTBFNN中的地层参数。新方案成功地用于低渗透油田试井问题,取得很好结果。对多组油井实测数据拟合和预测的平均相对误差均在1%以内,同时均得到了对应油井地层参数的全局最优估值,为试井解释提供了科学依据。并且新方案比传统方案显著减少了关井时间,因而具有重大的经济和社会效益。其次,为解决深层火山岩储层预测问题,提出了两种NN辨识器。用径向基函数神经网络(RBFNN)作第1种辨识器模型。用文中提出的新型混合算法对RBFNN的结构、参数和权值进行全面辨识。该混合算法由正交最小二乘法、带惯性项的梯度法和文中提出的优选模糊C均值聚类法组成。用多层前向网络作第2种辨识器模型。用文中所给出的混合SAA训练网络模型。该混合算法由Powell算法和文中给出的自适应SAA组成。由两种辨识器导出的预测器成功地用于火山岩储层预测,具有很高的精度,并且在收敛速度方面优于传统NN预测方案。最后,文中提出一种带Laplace隶属函数的新型模糊NN辨识器和预测器。并且应用微分中值定理和Weiestrass定理证明了该网络具有通用逼近性。在该方案中,采用文中提出的优选K均值聚类法辨识该网络的结构,用所给出的混合算法辨识该网络的前件参数和权值。仿真实验表明新方案优于传统模糊NN预测方案。将上述新方案用于油田积累产量预测,取得很好的结果,预测的平均相对误差在1%以内。特别,实现了对三个采油厂的不同类油井:基础油井,一次和二次加密油井累积产量的长期预测。这些预测结果,为是否继续打加密井的生产决策提供了科学依据。
The research of artificial neural networks(NN), genetic algorithms(GA), and simulated annealing algorithms(SAA) are the focus of modern information technology. It also opens a new route for the develop of nonlinear system identification. In this paper, we have made a thorough research in methods of nonlinear system identification and prediction of oil field systems. A set of NN identification and prediction methods can be obtained for oil field systems based on hybrid algorithms. We have finished the research as follows.
First, the oil field well test is taken an application example. On the bases of partial differential equations on well test interpretation,the model of well test interpretation basis function neural network(WTBFNN) has been given by mathematical induction, which is the theoretical bases of identification and prediction for well test systems. The well test interpretation basis function is a typical complex multimodal function. Its (stratigrsphic) parameters are the foundation of well test interpretation, so we request their unique estimate values. In order to solve the difficult problem, two new pattern hybrid GA have been put forward by means of technique synthesis for system identification ,GA and cluster algorithms and so on. The two algorithms are species genetic evolution algorithm(SGEA) and heuristic GA. It is shows from simulation experiment that SGEA has advantage over the GA with sharing on global convergence aspect. The global convergence of the two new GA have been proved by using Markovian chain theory. As a result, the new methods of WTBFNN identification and prediction can be got based on the above new hybrid GA. Where WTBFNN is taken as the model frame, the model structure parameters are determined by using F-test method, weight values of WTBFNN are identified by using least-squares(LS) method, and stratigraphic parameters in WTBFNN are estimated by using one of the above two hybrid algorithms. The new scheme can successful be applied to well test interpretation of low penetrability oil field, and excellent results be got. The average relative errors of fitting and predicting are within 1% for many set of oil well data. The global optimum estimate values of stratigraphic parameters can be obtained, which provides scientific basis for well test interpretation. And the new scheme can obviously reduce closing well time than normal well test schemes. Therefore it could bring great economic and social benefit. Second, in order to solve the problem of the prediction of deep volcanic rocks reservoir, the two NN identifiers can be given. radial basis function neural network(RBFNN) is taken as the first identifier model. The structure, parameters and weight values of RBFNN can totally be identified by using a new hybrid algorithm proposed in this paper. The hybrid algorithm is consists of orthogonal LS method, gradient method with inertia terms and optimal fuzzy C means cluster method posed in this paper. The multilayer feedforward NN is taken as second identifier model. The network model can be trained by using a new hybrid SAA given in this paper. The hybrid algorithm is consists of Powell algorithm and adaptive SAA posed in this paper. The high prediction precision is obtained, when the two new schemes are applied to the prediction of volcanic rocks reservoir. And they have advantage over the tradition NN prediction schemes on convergent speed. Last, a novel fuzzy NN identifier with Laplace membership function is posed by us in this paper. The universal approximation of the network can be proved by using differential median theorem and Weierstrass theorem. In the scheme, the structure of the network is determined by using the optimal K means cluster method posed in this paper, the premise parameters and the weight values are identified by the hybrid algorithms given in this paper. The very good results can be gained, when the above new scheme is applied to prediction of accumulative oil product. The prediction average relative errors are within 1%.Specially, the accumulative oil product long-term prediction of basis wells, first and twice thicken wells for three oil recovery plants can be done, and there prediction results can provide the scientific basis for production decision whether or not to drill new thicken wells.
首先,以油田试井解释为应用背景,以试井偏微分方程为依托,经过数学推导,给出了试井解释基函数神经网络(WTBFNN)模型,为试井系统辨识和预测奠定了理论基础。试井解释基函数是典型的复杂多峰函数。它的参数(地层参数)值是试井解释的依据,因而要求其估值应具有唯一性。为了解决这一难题,文中将系统辨识、GA、聚类算法等多项技术融于一体,提出了两种新型混合GA:种族遗传进化算法(SGEA)和启发式GA。仿真实验证明了SGEA的全局收敛性优于带共享机制的GA。文中以马尔可夫链为工具,证明了上述两种新型GA具有全局收敛性。在此基础上,提出了基于新型混合GA的WTBFNN辨识和预测新方法,其中以WTBFNN为模型框架,用F检验法确定模型结构参数,用最小二乘法辨识WTBFNN的权值,用上述两种新型混合GA之一辨识WTBFNN中的地层参数。新方案成功地用于低渗透油田试井问题,取得很好结果。对多组油井实测数据拟合和预测的平均相对误差均在1%以内,同时均得到了对应油井地层参数的全局最优估值,为试井解释提供了科学依据。并且新方案比传统方案显著减少了关井时间,因而具有重大的经济和社会效益。其次,为解决深层火山岩储层预测问题,提出了两种NN辨识器。用径向基函数神经网络(RBFNN)作第1种辨识器模型。用文中提出的新型混合算法对RBFNN的结构、参数和权值进行全面辨识。该混合算法由正交最小二乘法、带惯性项的梯度法和文中提出的优选模糊C均值聚类法组成。用多层前向网络作第2种辨识器模型。用文中所给出的混合SAA训练网络模型。该混合算法由Powell算法和文中给出的自适应SAA组成。由两种辨识器导出的预测器成功地用于火山岩储层预测,具有很高的精度,并且在收敛速度方面优于传统NN预测方案。最后,文中提出一种带Laplace隶属函数的新型模糊NN辨识器和预测器。并且应用微分中值定理和Weiestrass定理证明了该网络具有通用逼近性。在该方案中,采用文中提出的优选K均值聚类法辨识该网络的结构,用所给出的混合算法辨识该网络的前件参数和权值。仿真实验表明新方案优于传统模糊NN预测方案。将上述新方案用于油田积累产量预测,取得很好的结果,预测的平均相对误差在1%以内。特别,实现了对三个采油厂的不同类油井:基础油井,一次和二次加密油井累积产量的长期预测。这些预测结果,为是否继续打加密井的生产决策提供了科学依据。
The research of artificial neural networks(NN), genetic algorithms(GA), and simulated annealing algorithms(SAA) are the focus of modern information technology. It also opens a new route for the develop of nonlinear system identification. In this paper, we have made a thorough research in methods of nonlinear system identification and prediction of oil field systems. A set of NN identification and prediction methods can be obtained for oil field systems based on hybrid algorithms. We have finished the research as follows.
First, the oil field well test is taken an application example. On the bases of partial differential equations on well test interpretation,the model of well test interpretation basis function neural network(WTBFNN) has been given by mathematical induction, which is the theoretical bases of identification and prediction for well test systems. The well test interpretation basis function is a typical complex multimodal function. Its (stratigrsphic) parameters are the foundation of well test interpretation, so we request their unique estimate values. In order to solve the difficult problem, two new pattern hybrid GA have been put forward by means of technique synthesis for system identification ,GA and cluster algorithms and so on. The two algorithms are species genetic evolution algorithm(SGEA) and heuristic GA. It is shows from simulation experiment that SGEA has advantage over the GA with sharing on global convergence aspect. The global convergence of the two new GA have been proved by using Markovian chain theory. As a result, the new methods of WTBFNN identification and prediction can be got based on the above new hybrid GA. Where WTBFNN is taken as the model frame, the model structure parameters are determined by using F-test method, weight values of WTBFNN are identified by using least-squares(LS) method, and stratigraphic parameters in WTBFNN are estimated by using one of the above two hybrid algorithms. The new scheme can successful be applied to well test interpretation of low penetrability oil field, and excellent results be got. The average relative errors of fitting and predicting are within 1% for many set of oil well data. The global optimum estimate values of stratigraphic parameters can be obtained, which provides scientific basis for well test interpretation. And the new scheme can obviously reduce closing well time than normal well test schemes. Therefore it could bring great economic and social benefit. Second, in order to solve the problem of the prediction of deep volcanic rocks reservoir, the two NN identifiers can be given. radial basis function neural network(RBFNN) is taken as the first identifier model. The structure, parameters and weight values of RBFNN can totally be identified by using a new hybrid algorithm proposed in this paper. The hybrid algorithm is consists of orthogonal LS method, gradient method with inertia terms and optimal fuzzy C means cluster method posed in this paper. The multilayer feedforward NN is taken as second identifier model. The network model can be trained by using a new hybrid SAA given in this paper. The hybrid algorithm is consists of Powell algorithm and adaptive SAA posed in this paper. The high prediction precision is obtained, when the two new schemes are applied to the prediction of volcanic rocks reservoir. And they have advantage over the tradition NN prediction schemes on convergent speed. Last, a novel fuzzy NN identifier with Laplace membership function is posed by us in this paper. The universal approximation of the network can be proved by using differential median theorem and Weierstrass theorem. In the scheme, the structure of the network is determined by using the optimal K means cluster method posed in this paper, the premise parameters and the weight values are identified by the hybrid algorithms given in this paper. The very good results can be gained, when the above new scheme is applied to prediction of accumulative oil product. The prediction average relative errors are within 1%.Specially, the accumulative oil product long-term prediction of basis wells, first and twice thicken wells for three oil recovery plants can be done, and there prediction results can provide the scientific basis for production decision whether or not to drill new thicken wells.
引文
[1]赵永胜.油藏工程研究新途径的探讨[J].石油勘探与开发,1987(01):45-57.
[2]Al-Kaabi A U, Lee W J. Using artificial neural networks to identify the well test interpretation model[J]. SPE Formation Evaluation Journal, SPE, 1993, 233-240.
[3]邓远忠,陈钦雷.试井解释图版拟合分析的神经网络方法[J].石油勘探与开发,2000, 27(1):64-66.
[4] Sultan, Al-Kaabi. Application of neural network to the Determination of Well-Test Interpretation Model for Horizontal Wells[R]. SPE 77878, 2002.
[5] Baris, Horne. Automated Reservoir Model Selection in Well Test Interpretation[R]. SPE 71569, 2001.
[6]姚军,戴卫华,王子胜.变井筒储存的三重介质油藏试井解释方法研究[J].石油大学学报(自然科学版),2004,28(1):46-54.
[7]钱绍新,应用模式识别方法预测油气储集层[J].地球物理学报,1992,35(5):6-10.
[8]邱家骥,陶奎元,赵俊磊,等.火山岩[M].地质出版社,1996,1-58.
[9]庄成三,王培强.储层模式识别技术[J].石油地球物理学报,1994,29(5):630-636.
[10] Bois P. Autoregressive pattern recognition applied to the delimitation of oil and gas reservoirs[J]. Geophysical Prospecting,1980,28:572-591.
[11]迈斯内尔R,施特格奈L.实用地震勘探技术[M].地质出版社,1982.
[12]邓小力.利用多元统计判别法预测油气的效果[J],石油地球物理学报,1991,26(3):385- 394.
[13]刘国华,何勇兵,汪树玉.土石坝沉降预测中的多变量灰色预测模型[J].水利学报,2003,12:84~88.
[14]刘秀婷,杨军,程仲平,等.油田产量预测的新方法及应用[J].石油勘探与开发,2002,29(4):74~76.
[15] R.G.Donaldson, M. Kamstra. Forecast combining withneural networks[J]. J. Forecasting, 1996, 15: 49~61.
[16] Hanh H.Nguyen,Christine W.Chan,Malcolm Wilson. Prediction of oil well production multi-neural networks[A].Proceeding of the 2002 IEEE Canadian Conference on Electrical &Computer Engineering[C],2002:798~802.
[17] McCulloch W,Pitts W. A logic calculus of the ideas immanent in nervous acrivity[J] . Bulletin of Mathematical Biophysics,1943,5:115-133.
[18] Hebb O D. The Organization of Behavior [M]. New York:Wiley,1949.
[19] Rosenblatt F.The perceptron:A probabilistic model for information storage and organization in the brain[J]. Psychological Review,1985,65:388-408.
[20] Widrow B,Hoff E M. Adaptive switching circuits[R]. 1960 IRE WESCON Convention Record,New York:IRE Part4,1960:96-104.
[21] Minsky M,Papert S. Perceptrons[M],Canvridge,MA:MIT Press,1969.
[22] Kohonen T. Correlation matrix memories[J]. IEEE transactions on Computers,1972,21:353-359.
[23] Anderson A J. A simple neural network generation an interactive memory[J]. Mathematical Biosciences,1972,14:197-220.
[24] Grossberg S.Adaptive pattern classification and universal recording : I. Parallel development and coding of neural feature detectors[J]. Biological Cybernetics,1976,23:121-134.
[25] Hopfield J J. Neural networks and physical systems with emergent collective computation abilities[J]. Proceedings of the National Academy of Sciences,1982,79:2554-2558.
[26] Rumelhart D E,McClelland L J,eds.Parallel Distributed Processing:Exploration in the Micostructure of Cognition [M]. Cambridge,MA:MIT Press,1986,1.
[27]任伟建,段玉波,张正刚.基于紧框架小波神经网络的抽油机井故障诊断[J].控制与决策,2006,21(3):315-318.
[28]丛爽,王怡雯.随机神经网络发展现状综述[J].控制理论与应用,2004,21(6):975-980.
[29] Maeda K,Kanae S,Yang Z J,et al. Design of RBF network based on fuzzy clustering method for modeling of respiratory system[J]. Lecture Notes in Computer Science,2006,3973:746-753.
[30] Kim M W,Ryu J W,Kim E J. Speech recognition with multi-modal features based on neural networks[J]. Lecture Notes in Computer Science,2006,4233:489-498.
[31]王耀南,余群明,袁小芳.混沌神经网络模型及其应用研究综述[J].控制与决策,2006,21(2):121-128.
[32]邵旻,蒙培生.基于神经网络的油田注水泵站优化控制[J].自动化技术及应用, 2006,25(3):10-12.
[33]黄科,肖慈珣,张哨楠,等.基于神经网络的储层识别处理技术及在塔河油田的应用[J].物探化探计算技术,2006,28(1):18-21.
[34]邢明海,陈祥光,王渝.应用模糊神经网络预测油田产量[J].计算机仿真,2005,22(2):187-190.
[35]衣怀峰,陈新,匡立春.网络方法确定玛北油田岩性油藏含.神经油边界[J].石油大学学报,2005,29(4):15-20.
[36]丁刚,钟诗胜.基于过程神经网络的时间序列预测及其应用研究[J].控制与决策, 2006,21(9):1037-1041.
[37]张雁,柳成志,秦秋寒.利用人工神经网络预测砂岩储层渗透率[J].大庆石油学院学报,2005,29(4):10-11.
[38] Zurada J. Introduction to artificial neural systems[M]. West Publishing Company,1992.
[39]席裕庚,柴天佑,恽为民.遗传算法综述[J].控制理论与应用,1996,13(6):697-708.
[40] Fogel D B. A introduction to simulated evolutionary optimization[J]. IEEE Trans on Neural Networks,1994,5(1):3-14.
[41] Koza J R. Genetic programming:On the programming of computers by means of natural selection[M]. Cambridge,MA:MIT Press,1992.
[42] Yao X. A review of evolutionary artificial neural networks[J]. Int J Intelligent Systems, 1993,8:539-567.
[43] Tsu-Chang Lee. Structure level adaptation for ANN[M]. Kluwer Academic Publishers,1991.
[44] Hunt K J,Sbarbaro D,Zbikowski R,et al. Neural networks for control systems-A survey[J]. Automatica,1992,28(6):1083-1112.
[45] Yager R R. Implemeting fuzzy logic controller using a neural network framework [J]. Fuzzy S S,1992,48(1):53-64.
[46]陈国良,王煦法,庄镇泉,等.遗传算法及其应用[M].人民邮电出版社,1996,1~148.
[47] Begley J D. The behavior of adaptive system which employ genetic and coorelation algorithm[D]. Ph D Dissertation. University of Michigan,1967,68-7556.
[48] Rosenberg R S. A computer simulation of a biological population [M]. Unpublished Manuscrit, 1966.
[49] Weinberg R. Computer simulation of a living cell[D]. Doctoral Dissertation. Univ. Of Michigan,Dissertations Abstracts Int,1970,31(9).
[50] Hellstien R B. Artificial genetic adaptation in computer control systems[D]. ph D Dissertation. University of Michigan,1971,71-23773.
[51] Holland J H. Adaptation in nature and artificial systems[M]. The University of Michigan Press,1975,MIT Press,1992.
[52] De Jong K A. An analysis of the behaviour of a class of genetic adaptive systems[D]. ph D Dissertation. University of Michigan,1975,76~9381.
[53]戴晓晖,李敏强,寇纪淞.遗传算法理论研究综述[J].控制与决策,2000,15(3):263-268.
[54]郑立平,郝忠孝.遗传算法理论综述[J].计算机工程与应用,2003,21:50-53.
[55]吉根林.遗传算法研究综述[J].计算机应用与软件,2004,21(2):69-73.
[56]刘立平,牛熠.遗传算法综述[J].东莞理工学院学报,2005,12(3):48-52.
[57]康立山,谢云,尤矢勇,等.非数值并行算法—模拟退火算法[M].科学出版社,1997.
[58] Metropolis N,Rosenbluth A W,Rosenboluth M N,et al. Equations of state calculations by fast computing machines[J]. Journal of Chemical Physics,1953,21:1087-1092.
[59] Kirkpatrick S. Optimization by Simulated Annealing:Quantitative Studies[J]. J of Statistical Physics,1984,34(5/6):975-986.
[60]王凌,郑大钟.基于Cauchy和Gaussian分布状态发生器的模拟退火算法[J ].清华大学学报(自然科学版),2000,40 (9):109～1121.
[61]纪晨,振兴.用于地球物理反演的均匀设计优化算法[J].地球物理学报,1996,39(2):233～242.
[62] Basu A,Frazer L. Rapid determination of the critical temperature in simulated annealing inversion[J ]. Science,1990,249 (21):1409～1412.
[63] Press W H,Vetterling W T,Teukolsky S A,et al. Simulated annealing optimization over continus space [J ]. Computers in Physics,1991 (5):426～429.
[64]张霖斌,姚振兴,纪晨,等.快速模拟退火算法及应用[J].石油地球物理勘探,1997,32 (5):654～660.
[65]蒋龙聪,刘江平.模拟退火算法及其改进[J].工程地球物理学报,2007,4(2):135-140.
[66]徐雷.一种改进的模拟退火组合优化法[J].信息与控制,1990,19(3):1-7.
[67]范千,许承权,陈伟.单纯形-模拟退火混合算法及其在参数估计中的应用[J].地理空间信息,2005,3(3):57-59.
[68]赵晶,唐焕文,朱训芝.模拟退火算法的一种改进及其应用[J].大连理工大学学报,2006,46(5):776-780.
[69]胡声艳,王桂芝.模拟退火算法在模糊模式识别中的应用研究[J].湖北教育学院学报,2005,22(5):40-43.
[70]刘怀亮,刘淼.一种混合遗传模拟退火算法及其应用[J].广州大学学报(自然科学版),2005,4(2):141-145.
[71]郭建青,李彦,王洪胜,等.应用单纯形-模拟退火混合算法估计河流水质参数[J].水科学进展,2004,15(6):765-769.
[72]翟云芳,闫宝珍,刘义坤.渗流力学[M].石油工业出版社,1994,7~86.
[73]李笑平,张大为.数理方法与试井数学模型[M].石油工业出版社,1993,2~4..
[74]宋考平,宋洪才,吴文祥.油藏数值模拟理论基础[M].石油工业出版社,1996,9~19.
[75] Scrinvas M,Patnaik L M. Adaptive Probabilities of Crossover and Mutation in Genetic Algorithms[J]. IEEE Trans. SMC,1994,24(4):656~666.
[76] Goldberg D E. Genetic Algorithms with sharing for Multimodal Function Optimization [C]. in Proceeding of Second International Conference on Genetic Algorithms and on Their Application,1987:41~49.
[77] Yager R R,Filev D P. Approximate clustering via the mountain method[J]. IEEE Transon Neural Networks,Man,and Cybernetics,1994,24:1297-1284.
[78]朱向阳,熊有伦.一种改进的Powell共轭方向算法[J].控制与决策,1996,11(12):304- 308.
[79]王梓坤.随机过程[M].科学出版社,1965,50~64.
[80]鲁恩伯杰D G.社会动态系统引伦[M].袁天鑫,黄午阳.上海科学技术文献出版社,1985.
[81]恽为民,席裕庚.遗传算法的收敛性和计算效率分析[J].控制理论与应用,1996,13 (4):45~5459.
[82]王永骥,涂健.神经元网络控制[M].北京:机械工业出版社,1998.
[83] Park J,et al. Universal Approximations Using RBF Networks[J]. Neural Computation, 1991,3:246-257.
[84]张智星,孙春在,[日]水谷英二.神经-模糊和软计算[M].张平安,高春华等.西安交通大学出版社,2000.
[85] Szu H,Hartley R. Fast simulated annealing[J]. Physics Letters A,1987,122(3):157-162.
[86]代俊堂,钱绍新.地震资料的统计模式识别和神经网络模式识别[J],石油学报,1997,18(2):18-25.
[2]Al-Kaabi A U, Lee W J. Using artificial neural networks to identify the well test interpretation model[J]. SPE Formation Evaluation Journal, SPE, 1993, 233-240.
[3]邓远忠,陈钦雷.试井解释图版拟合分析的神经网络方法[J].石油勘探与开发,2000, 27(1):64-66.
[4] Sultan, Al-Kaabi. Application of neural network to the Determination of Well-Test Interpretation Model for Horizontal Wells[R]. SPE 77878, 2002.
[5] Baris, Horne. Automated Reservoir Model Selection in Well Test Interpretation[R]. SPE 71569, 2001.
[6]姚军,戴卫华,王子胜.变井筒储存的三重介质油藏试井解释方法研究[J].石油大学学报(自然科学版),2004,28(1):46-54.
[7]钱绍新,应用模式识别方法预测油气储集层[J].地球物理学报,1992,35(5):6-10.
[8]邱家骥,陶奎元,赵俊磊,等.火山岩[M].地质出版社,1996,1-58.
[9]庄成三,王培强.储层模式识别技术[J].石油地球物理学报,1994,29(5):630-636.
[10] Bois P. Autoregressive pattern recognition applied to the delimitation of oil and gas reservoirs[J]. Geophysical Prospecting,1980,28:572-591.
[11]迈斯内尔R,施特格奈L.实用地震勘探技术[M].地质出版社,1982.
[12]邓小力.利用多元统计判别法预测油气的效果[J],石油地球物理学报,1991,26(3):385- 394.
[13]刘国华,何勇兵,汪树玉.土石坝沉降预测中的多变量灰色预测模型[J].水利学报,2003,12:84~88.
[14]刘秀婷,杨军,程仲平,等.油田产量预测的新方法及应用[J].石油勘探与开发,2002,29(4):74~76.
[15] R.G.Donaldson, M. Kamstra. Forecast combining withneural networks[J]. J. Forecasting, 1996, 15: 49~61.
[16] Hanh H.Nguyen,Christine W.Chan,Malcolm Wilson. Prediction of oil well production multi-neural networks[A].Proceeding of the 2002 IEEE Canadian Conference on Electrical &Computer Engineering[C],2002:798~802.
[17] McCulloch W,Pitts W. A logic calculus of the ideas immanent in nervous acrivity[J] . Bulletin of Mathematical Biophysics,1943,5:115-133.
[18] Hebb O D. The Organization of Behavior [M]. New York:Wiley,1949.
[19] Rosenblatt F.The perceptron:A probabilistic model for information storage and organization in the brain[J]. Psychological Review,1985,65:388-408.
[20] Widrow B,Hoff E M. Adaptive switching circuits[R]. 1960 IRE WESCON Convention Record,New York:IRE Part4,1960:96-104.
[21] Minsky M,Papert S. Perceptrons[M],Canvridge,MA:MIT Press,1969.
[22] Kohonen T. Correlation matrix memories[J]. IEEE transactions on Computers,1972,21:353-359.
[23] Anderson A J. A simple neural network generation an interactive memory[J]. Mathematical Biosciences,1972,14:197-220.
[24] Grossberg S.Adaptive pattern classification and universal recording : I. Parallel development and coding of neural feature detectors[J]. Biological Cybernetics,1976,23:121-134.
[25] Hopfield J J. Neural networks and physical systems with emergent collective computation abilities[J]. Proceedings of the National Academy of Sciences,1982,79:2554-2558.
[26] Rumelhart D E,McClelland L J,eds.Parallel Distributed Processing:Exploration in the Micostructure of Cognition [M]. Cambridge,MA:MIT Press,1986,1.
[27]任伟建,段玉波,张正刚.基于紧框架小波神经网络的抽油机井故障诊断[J].控制与决策,2006,21(3):315-318.
[28]丛爽,王怡雯.随机神经网络发展现状综述[J].控制理论与应用,2004,21(6):975-980.
[29] Maeda K,Kanae S,Yang Z J,et al. Design of RBF network based on fuzzy clustering method for modeling of respiratory system[J]. Lecture Notes in Computer Science,2006,3973:746-753.
[30] Kim M W,Ryu J W,Kim E J. Speech recognition with multi-modal features based on neural networks[J]. Lecture Notes in Computer Science,2006,4233:489-498.
[31]王耀南,余群明,袁小芳.混沌神经网络模型及其应用研究综述[J].控制与决策,2006,21(2):121-128.
[32]邵旻,蒙培生.基于神经网络的油田注水泵站优化控制[J].自动化技术及应用, 2006,25(3):10-12.
[33]黄科,肖慈珣,张哨楠,等.基于神经网络的储层识别处理技术及在塔河油田的应用[J].物探化探计算技术,2006,28(1):18-21.
[34]邢明海,陈祥光,王渝.应用模糊神经网络预测油田产量[J].计算机仿真,2005,22(2):187-190.
[35]衣怀峰,陈新,匡立春.网络方法确定玛北油田岩性油藏含.神经油边界[J].石油大学学报,2005,29(4):15-20.
[36]丁刚,钟诗胜.基于过程神经网络的时间序列预测及其应用研究[J].控制与决策, 2006,21(9):1037-1041.
[37]张雁,柳成志,秦秋寒.利用人工神经网络预测砂岩储层渗透率[J].大庆石油学院学报,2005,29(4):10-11.
[38] Zurada J. Introduction to artificial neural systems[M]. West Publishing Company,1992.
[39]席裕庚,柴天佑,恽为民.遗传算法综述[J].控制理论与应用,1996,13(6):697-708.
[40] Fogel D B. A introduction to simulated evolutionary optimization[J]. IEEE Trans on Neural Networks,1994,5(1):3-14.
[41] Koza J R. Genetic programming:On the programming of computers by means of natural selection[M]. Cambridge,MA:MIT Press,1992.
[42] Yao X. A review of evolutionary artificial neural networks[J]. Int J Intelligent Systems, 1993,8:539-567.
[43] Tsu-Chang Lee. Structure level adaptation for ANN[M]. Kluwer Academic Publishers,1991.
[44] Hunt K J,Sbarbaro D,Zbikowski R,et al. Neural networks for control systems-A survey[J]. Automatica,1992,28(6):1083-1112.
[45] Yager R R. Implemeting fuzzy logic controller using a neural network framework [J]. Fuzzy S S,1992,48(1):53-64.
[46]陈国良,王煦法,庄镇泉,等.遗传算法及其应用[M].人民邮电出版社,1996,1~148.
[47] Begley J D. The behavior of adaptive system which employ genetic and coorelation algorithm[D]. Ph D Dissertation. University of Michigan,1967,68-7556.
[48] Rosenberg R S. A computer simulation of a biological population [M]. Unpublished Manuscrit, 1966.
[49] Weinberg R. Computer simulation of a living cell[D]. Doctoral Dissertation. Univ. Of Michigan,Dissertations Abstracts Int,1970,31(9).
[50] Hellstien R B. Artificial genetic adaptation in computer control systems[D]. ph D Dissertation. University of Michigan,1971,71-23773.
[51] Holland J H. Adaptation in nature and artificial systems[M]. The University of Michigan Press,1975,MIT Press,1992.
[52] De Jong K A. An analysis of the behaviour of a class of genetic adaptive systems[D]. ph D Dissertation. University of Michigan,1975,76~9381.
[53]戴晓晖,李敏强,寇纪淞.遗传算法理论研究综述[J].控制与决策,2000,15(3):263-268.
[54]郑立平,郝忠孝.遗传算法理论综述[J].计算机工程与应用,2003,21:50-53.
[55]吉根林.遗传算法研究综述[J].计算机应用与软件,2004,21(2):69-73.
[56]刘立平,牛熠.遗传算法综述[J].东莞理工学院学报,2005,12(3):48-52.
[57]康立山,谢云,尤矢勇,等.非数值并行算法—模拟退火算法[M].科学出版社,1997.
[58] Metropolis N,Rosenbluth A W,Rosenboluth M N,et al. Equations of state calculations by fast computing machines[J]. Journal of Chemical Physics,1953,21:1087-1092.
[59] Kirkpatrick S. Optimization by Simulated Annealing:Quantitative Studies[J]. J of Statistical Physics,1984,34(5/6):975-986.
[60]王凌,郑大钟.基于Cauchy和Gaussian分布状态发生器的模拟退火算法[J ].清华大学学报(自然科学版),2000,40 (9):109～1121.
[61]纪晨,振兴.用于地球物理反演的均匀设计优化算法[J].地球物理学报,1996,39(2):233～242.
[62] Basu A,Frazer L. Rapid determination of the critical temperature in simulated annealing inversion[J ]. Science,1990,249 (21):1409～1412.
[63] Press W H,Vetterling W T,Teukolsky S A,et al. Simulated annealing optimization over continus space [J ]. Computers in Physics,1991 (5):426～429.
[64]张霖斌,姚振兴,纪晨,等.快速模拟退火算法及应用[J].石油地球物理勘探,1997,32 (5):654～660.
[65]蒋龙聪,刘江平.模拟退火算法及其改进[J].工程地球物理学报,2007,4(2):135-140.
[66]徐雷.一种改进的模拟退火组合优化法[J].信息与控制,1990,19(3):1-7.
[67]范千,许承权,陈伟.单纯形-模拟退火混合算法及其在参数估计中的应用[J].地理空间信息,2005,3(3):57-59.
[68]赵晶,唐焕文,朱训芝.模拟退火算法的一种改进及其应用[J].大连理工大学学报,2006,46(5):776-780.
[69]胡声艳,王桂芝.模拟退火算法在模糊模式识别中的应用研究[J].湖北教育学院学报,2005,22(5):40-43.
[70]刘怀亮,刘淼.一种混合遗传模拟退火算法及其应用[J].广州大学学报(自然科学版),2005,4(2):141-145.
[71]郭建青,李彦,王洪胜,等.应用单纯形-模拟退火混合算法估计河流水质参数[J].水科学进展,2004,15(6):765-769.
[72]翟云芳,闫宝珍,刘义坤.渗流力学[M].石油工业出版社,1994,7~86.
[73]李笑平,张大为.数理方法与试井数学模型[M].石油工业出版社,1993,2~4..
[74]宋考平,宋洪才,吴文祥.油藏数值模拟理论基础[M].石油工业出版社,1996,9~19.
[75] Scrinvas M,Patnaik L M. Adaptive Probabilities of Crossover and Mutation in Genetic Algorithms[J]. IEEE Trans. SMC,1994,24(4):656~666.
[76] Goldberg D E. Genetic Algorithms with sharing for Multimodal Function Optimization [C]. in Proceeding of Second International Conference on Genetic Algorithms and on Their Application,1987:41~49.
[77] Yager R R,Filev D P. Approximate clustering via the mountain method[J]. IEEE Transon Neural Networks,Man,and Cybernetics,1994,24:1297-1284.
[78]朱向阳,熊有伦.一种改进的Powell共轭方向算法[J].控制与决策,1996,11(12):304- 308.
[79]王梓坤.随机过程[M].科学出版社,1965,50~64.
[80]鲁恩伯杰D G.社会动态系统引伦[M].袁天鑫,黄午阳.上海科学技术文献出版社,1985.
[81]恽为民,席裕庚.遗传算法的收敛性和计算效率分析[J].控制理论与应用,1996,13 (4):45~5459.
[82]王永骥,涂健.神经元网络控制[M].北京:机械工业出版社,1998.
[83] Park J,et al. Universal Approximations Using RBF Networks[J]. Neural Computation, 1991,3:246-257.
[84]张智星,孙春在,[日]水谷英二.神经-模糊和软计算[M].张平安,高春华等.西安交通大学出版社,2000.
[85] Szu H,Hartley R. Fast simulated annealing[J]. Physics Letters A,1987,122(3):157-162.
[86]代俊堂,钱绍新.地震资料的统计模式识别和神经网络模式识别[J],石油学报,1997,18(2):18-25.
© 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 |