基于概率神经网络信息融合的拟声波构建方法
|
摘要
本文介绍一种基于概率神经网络(PNN)的拟声波曲线构建方法。首先论述了基本PNN的数学模型,在此基础上,设计了适合于多源测井信息融合的多输入、单输出PNN网络拓扑结构,并利用PNN的插值功能以拟合误差最小为准则推导出新模型的输出;最后利用该模型对实际测井资料进行处理,能够快速、自适应构建拟声波曲线。通过对处理结果的分析,验证了该方法的合理性和有效性。
An approach to pseudo-acoustic log curve construction based on probabilistic neural networks(PNN) is presented in the paper.Firstly,the basic mathematical model of PNN is discussed.Then,a multi-input and single-output PNN network topology which is fit multi-source logging information fusion is designed on the basis of the model.After that,the output of the new model with the minimum fit error criterion is derived using PNN interpolation function.Finally,the actual logging data is processed by the model,and a fast pseudo-acoustic curve construction is adaptively obtained.The processing results show the rationality and effectiveness of the method.
An approach to pseudo-acoustic log curve construction based on probabilistic neural networks(PNN) is presented in the paper.Firstly,the basic mathematical model of PNN is discussed.Then,a multi-input and single-output PNN network topology which is fit multi-source logging information fusion is designed on the basis of the model.After that,the output of the new model with the minimum fit error criterion is derived using PNN interpolation function.Finally,the actual logging data is processed by the model,and a fast pseudo-acoustic curve construction is adaptively obtained.The processing results show the rationality and effectiveness of the method.
引文
[1]许正龙.曲线重构技术在储层横向预测工作中的应用.石油实验地质,2002,24(4):377～380Xu Zhenglong.Application of the curve recomposi-tion technology to the lateral prediction of reservoirs.Petroleum Geology&Experimfnt,2002,24(4):377～380
[2]姜传金,马学辉,周恩红.拟声波曲线构建的意义及应用.大庆石油地质与开发,2004,23(1):12～14Jiang Chuangjin,Ma Xuehui,Zhou Enhong.Thesignificance and application of composing pseudo-a-coustic curve.Petroleum Geology&Oil Field De-velopment in Daqing,2004,23(1):12～14
[3]彭真明,肖慈珣,杨斌等.利用地震非线性参数重建声波测井曲线.石油物探,2000,39(2):72～76Peng Zhenming,Xiao Cixun,Yang Bin et al.Recon-structing sonic log curve using seismic nonlinear pa-rameters.Geophysical Prospecting for Petroleum,2000,39(2):72～76
[4]贾建亮,刘招君,陈永成等.测井—地震多属性分层重构特征曲线技术.石油地球物理勘探,2010,43(3):436～442Jia Jianliang,Liu Zhaojun,Chen Yongcheng et al.Well logging-seismic multi-attribute stratified recon-struction characteristic curve technique.OGP,2010,43(3):436～442
[5]Specht Donald F.Probabilistic neural networks andthe polynomial Adaline as complementary techniquesfor classification.IEEE Transactions On NeuralNetworks,1990,1(1):111～121
[6]黄飞,彭真明,张晓燕.PNN及其在储层物性参数预测中的应用.物探化探计算技术,2002,25(1):78～82Huang Fei,Peng Zhenming,Zhang Xiaoyan.PNNand its application in prediction of reservoir parame-ters.Computing Techniques for Geophysical and Ge-ochemical Exploration,2002,25(1):78～82
[7]Specht Donald F.A general regression neural net-work.IEEE Transactions on Neural Networks,1991,2(6):568～576
[8]成奇明,张树京.概率神经网络回归、判别与聚类.北方交通大学学报,1993,17(4):369～373Cheng Qiming,Zhang Shujing.Probabilistic neuralnetworks for regression,decision and clustering.Journal of Beijing Jiaotong University,1993,17(4):369～373
[9]Chen S,Cowan C F N and Grant P M.Orthogonalleast squares learning algorithm for radial basis func-tion networks.IEEE Transactions on Neural Net-works,1991,2(2):302～309
[10]Emanuel Parzen.On estimation of a probability den-sity function and mode.Annals of Mathematical Sta-tistics,1962,33(3):1065～1076
[11]史忠植.神经网络.北京:高等教育出版社,2009
[12]李洪强,丁景丽,林楠等.随钻伽马测量数据处理方法的研究及应用.石油钻探技术,2008,36(4):12～14Li Hongqiang,Ding Jingli,Lin Nan et al.Researchand application of data processing in gamma ray log-ging while drilling.Petroleum Drillng Techniques,2008,36(4):12～14
[2]姜传金,马学辉,周恩红.拟声波曲线构建的意义及应用.大庆石油地质与开发,2004,23(1):12～14Jiang Chuangjin,Ma Xuehui,Zhou Enhong.Thesignificance and application of composing pseudo-a-coustic curve.Petroleum Geology&Oil Field De-velopment in Daqing,2004,23(1):12～14
[3]彭真明,肖慈珣,杨斌等.利用地震非线性参数重建声波测井曲线.石油物探,2000,39(2):72～76Peng Zhenming,Xiao Cixun,Yang Bin et al.Recon-structing sonic log curve using seismic nonlinear pa-rameters.Geophysical Prospecting for Petroleum,2000,39(2):72～76
[4]贾建亮,刘招君,陈永成等.测井—地震多属性分层重构特征曲线技术.石油地球物理勘探,2010,43(3):436～442Jia Jianliang,Liu Zhaojun,Chen Yongcheng et al.Well logging-seismic multi-attribute stratified recon-struction characteristic curve technique.OGP,2010,43(3):436～442
[5]Specht Donald F.Probabilistic neural networks andthe polynomial Adaline as complementary techniquesfor classification.IEEE Transactions On NeuralNetworks,1990,1(1):111～121
[6]黄飞,彭真明,张晓燕.PNN及其在储层物性参数预测中的应用.物探化探计算技术,2002,25(1):78～82Huang Fei,Peng Zhenming,Zhang Xiaoyan.PNNand its application in prediction of reservoir parame-ters.Computing Techniques for Geophysical and Ge-ochemical Exploration,2002,25(1):78～82
[7]Specht Donald F.A general regression neural net-work.IEEE Transactions on Neural Networks,1991,2(6):568～576
[8]成奇明,张树京.概率神经网络回归、判别与聚类.北方交通大学学报,1993,17(4):369～373Cheng Qiming,Zhang Shujing.Probabilistic neuralnetworks for regression,decision and clustering.Journal of Beijing Jiaotong University,1993,17(4):369～373
[9]Chen S,Cowan C F N and Grant P M.Orthogonalleast squares learning algorithm for radial basis func-tion networks.IEEE Transactions on Neural Net-works,1991,2(2):302～309
[10]Emanuel Parzen.On estimation of a probability den-sity function and mode.Annals of Mathematical Sta-tistics,1962,33(3):1065～1076
[11]史忠植.神经网络.北京:高等教育出版社,2009
[12]李洪强,丁景丽,林楠等.随钻伽马测量数据处理方法的研究及应用.石油钻探技术,2008,36(4):12～14Li Hongqiang,Ding Jingli,Lin Nan et al.Researchand application of data processing in gamma ray log-ging while drilling.Petroleum Drillng Techniques,2008,36(4):12～14
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心