计算机与数字工程2025，Vol.53Issue(4)：989-994,1001,7.DOI:10.3969/j.issn.1672-9722.2025.04.013
基于CNN和BiGRU的储层品质指数预测方法
Reservoir Quality Index Prediction Method Based on CNN and BiGRU
摘要
Abstract
This paper proposes a low-permeability oilfield reservoir quality index prediction method based on the combination of one-dimensional convolutional neural network(1DCNN)and bidirectional gated recurrent unit(BiGRU).The above part of the logging sequence data is used as input,and the convolution kernel is used to extract the characteristics of these data features,and the bidirectional GRU is used to update the eigenvalues in the forward and reverse order.The coefficients are multiplied by the corre-sponding features,and the values of the curve series corresponding to the next depth are predicted,and finally the reservoir quality index(RQI)is obtained.And this model is compared with other machine learning network models.The results show that the 1DCNN-BiGRU model designed in this paper is better than the BP neural network and the CNN convolutional neural network in terms of prediction accuracy of the reservoir quality index prediction method for low permeability oilfield reservoirs.关键词
低渗油田/卷积神经网络/双向门控循环单元/储层品质指数/储层特征Key words
low permeability oilfields/CNN/BiGRU/reservoir quality index/reservoir characteristics分类
信息技术与安全科学引用本文复制引用
李建平,张梓萱..基于CNN和BiGRU的储层品质指数预测方法[J].计算机与数字工程,2025,53(4):989-994,1001,7.基金项目
国家自然科学基金重点项目(编号:61933007)资助. （编号:61933007）
