|
|||||
|
|
| 基于改进神经网络的渗透率预测方法 | |
| 引用本文： | 杨建,杨程博,张岩,崔力公,王龙飞.基于改进神经网络的渗透率预测方法[J].岩性油气藏,2011,23(1):98-102. |
| 作者姓名： | 杨建 杨程博 张岩 崔力公 王龙飞 |
| 作者单位： | 1. 中国石化西南油气分公司勘探开发研究院 2. 西南石油大学"油气藏地质及开发工程"国家重点实验室 3. 中国石油川庆钻探地质勘探开发研究院 4. 中国石化中原油田采油工程技术研究院天然气技术研究所 |
| 摘 要： | 由于传统BP算法具有收敛速度慢、易陷入局部极小值等不足,文中对其进行了改进。在Kozeny-Carman方程和杨正明研究的基础上,借助于MATLAB神经网络工具箱,建立了预测岩石渗透率的3层前馈型BP神经网络模型。对改进的神经网络模型进行的仿真训练结果表明:改进模型具有更快的收敛速度和更高的精度,模型预测值与实验室测试值的一致性比较好,其相对误差小于10%,完全能够满足现场精度要求。 |
| 关 键 词： | BP神经网络 改进BP算法 网络仿真训练 MATLAB 渗透率预测 |
Permeability prediction method based on improved BP neural network |
|
| YANG Ran,YANG Cheng-bo,ZHANG Yan,CUI Li-gong,WANG Long-fen.Permeability prediction method based on improved BP neural network[J].Northwest Oil & Gas Exploration,2011,23(1):98-102. | |
| Authors: | YANG Ran YANG Cheng-bo ZHANG Yan CUI Li-gong WANG Long-fen |
| Affiliation: | YANG Jian1,YANG Cheng-bo2,ZHANG Yan1,CUI Li-gong3,WANG Long-fei4 (1.Research Institute of Exploration and Development,Southwest Oil-Gas Field Company,Sinopec,Chengdu 610081,China,2.State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation,Southwest Petroleum University,Chengdu 610500,3.Research Institute of Geologic Exploration and Development,Chuanqing Drilling & Exploration Corporation,CNPC,Chengdu 610051,4.Research Institute of Petroleum Engineering Technology,Zhongyuan Oilfield,... |
| Abstract: | The traditional BP algorithm has slow convergence rate,and is easy to fall into local minimum.It is improved based on Kozeny-Carman equation and the study of Yang Zhengming,and a three-layer feedforward BP neural network model for permeability prediction is established by means of MATLAB neural network toolbox.The simulation training of the improved neural network model is carried out.The result shows that the improved model has faster convergence rate and higher accuracy.The values predicted by the model a... |
| Keywords: | MATLAB |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |