神经网络反演方法在地震储层上的应用
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
基于神经网络对地球物理资料进行反演,其原理是把希望输出与实际输出之差偏差归结为连接权的"过错",通过把输入层单元的误差,逐层向输入层逆向回转,分摊给各层单元,从而获得各层单元的参考误差,以调整相应的连接权;并讨论了神经网络反演和基于模型反演在少井的情况下对反演效果的影响,以及神经网络反演中的各参数对分辨率的影响,对神经网络反演的应用及推广提供了相关参考.
The principle of neural network inversion of geophysical data is that differences between desired output and actual output are summed up as the "fault" of connection weights,and then,the error of input layer unit is reversed rotation to the input layer,layer by layer,and allocates to the layers of units in order to obtain a reference error of layers units and to adjust the connection weights of the corresponding.The influences of neural network inversion and model based inversion in the case of less well effect inversion and the various parameters of neural network inversion on resolution ratio are discussed,and provide relevant information to application for neural network inversion.
引文
[1]阎平凡,张长水.人工神经网络与模拟进化计算[M].北京:清华大学出版社,2000:193-197.
    [2]刘玲,黄玲.用神经网络方法进行地震记录的标定[J].物探化探计算技术,1993,15(4):180-183.
    [3]文晓涛,贺振华,黄德济.遗传算法与神经网络在碳酸盐岩储集层评价中的应用[J].石油物探,2005,44(3):225-228.
    [4]贺振华,黄德济.复杂油气藏地震波场特征方法理论及应用[M].成都:四川科学技术出版社,1999:229-232.
    [5]贺振华,黄德济,文晓涛.裂缝油气藏地球物理预测[M].成都:四川科学技术出版社2007:210-215.
    [6]SIMON Haykin.Neural networks:a comprehensive found-ation[M].2th ed.Beijing:China Machine Press,2004:186-189.
    [7]王家映.地球物理反演理论[M].2版.北京:高等教育出版社,2002:153-156.

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