时间延迟神经网络地震油气预测方法
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
本文绘出基于时间延迟神经网络模型的地震油气预测方法及其初步应用结果,不同于通常的孤立模式识别方法.在特征提取阶段,不仅提取地震道中相应目的层单时窗的特征,同时也提取时窗滑动时的特征,这些多时窗的特征信息反映出地层层序的变化.时间延迟神经网络模型通过井旁道特征串的训练,用于表达特征信息与地层含油气情况的复杂关系和特征信息的变化与地层油气聚集的联系.初步应用表明,这种基于时间延迟网络模型的油气预测方法的结果要好于BP网络方法的结果.
In this paper, We present a method of time-delay neural network (TDNN) for reservior lateral predication. It is different from common isolated pattern recognition method. In the phase of extracting features, we extract not only features in single time-window, but also features in multiple time-window. Those features in multiple time window could represent the variation of features with bine in the bee when the TDNN has been trained with the features of traces near the wells. It can not only represent the complex relationship between features containing oil/gas in the layer,but also the relationship between the variation of features in the layer. Examples show that the TDNN model is more suitable to predict the reservior laterallythan the BP model.
引文
[1] 钱绍新,应用模式识别方法预测油气储层,地球物理学报,35,630-636,1992.
    [2] 朱广生、刘瑞林、王庭阁,神经网络在油气横向预测和地震道编辑中的应用,石油物探,33,1-9,1994.
    [3] 牛毓荃译,地震地层学,北京:石油工业出版社,1980.
    [4] Plona, J., Observation of second bulk compressional wave in a porous at ultrasonic frequencies, Appl. Lett., 36, 259-261,1980.
    [5] Napy, P.B., Adler, L. Observation of slow compressional waves in natural rocks, J. Acoust. Soc. Am. Suppl., 87(1), S145, 1990.
    [6] Johnson, D.L., Plona, T. J., Kojima, H., Probing porous media with first and second sound: Ⅱ Acoustic properties of water-saturated porous media. J. Appl. Phys., 75,115-125, 1994.
    [7] Dai, N., Vafidis, A., Kanasewich, K., Wave propapation in heterogeneous porous media:A velocity-stress finite difference method, Geophys., 60,327-340,1995.
    [8] Waibel,A., Hanzawa, T., Hinton, G. et al., Phoneme recognition using time-delay neural networks, IEEE Trans. on ASSP, 37, 328-339, 1989.
    [9] Werbos,P.J., Backproopation through time: What it does and how to do it, Proceeding of IEEE, 78,1550-1560, 1990.
    [10] Rumelhart, D. E., Hinton, G. E., Williams,R. J., Learning interal representation by enor Propagation, In: Parallel Distribution Processing, Vol. I, Massachusetts: MIT Press, 1986.

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