论文部分内容阅读
神经网络是一门新兴的信息处理技术，它可用来解决测并解释和油藏描述中的模式识别和参数估算等问题。本文利用取心井的储层孔隙度与测并数据，应用改进的ＢＰ神经网络模型建立了川中磨溪气田香四储层物性参数孔隙度的预测模型。与传统方法～回归方程、灰色方程和测井解释相比，其精度及实际预测效果均令人满意。该法值得推广应用。
Neural network is a new information processing technology, which can be used to solve problems such as pattern recognition and parameter estimation in measurement interpretation and reservoir description. Based on the reservoir porosity and measured data of coring well, this paper established a prediction model of porosity of physical property parameters of Xiang 4 reservoir in Moxi gas field of Central Sichuan by using improved BP neural network model. Compared with the traditional method ~ regression equation, gray equation and well logging interpretation, the accuracy and actual prediction results are satisfactory. The law is worth promoting.