计算机与现代化 ›› 2024, Vol. 0 ›› Issue (09): 15-19.doi: 10.3969/j.issn.1006-2475.2024.09.003

• 人工智能 • 上一篇    下一篇

基于改进时序胶囊网络的油藏生产动态分析模型


  

  1. (1.东北石油大学计算机与信息技术学院,黑龙江 大庆 163318;
    2.大庆油田责任有限公司第五采油厂第七作业区,黑龙江 大庆 163318)
  • 出版日期:2024-09-27 发布日期:2024-09-27
  • 基金资助:
    国家自然科学基金资助项目(42002138); 黑龙江省自然科学基金资助项目(LH2022F008); 黑龙江省博士后专项(LBH-Q20077)

Dynamic Analysis Model of Reservoir Production Based on Improved#br# Time-series Capsule Network

  1. (1. College of Computer and Information Technology, Northeast Petroleum University, Daqing 163318, China;
    2. The 7th Operation Area, the No.5 Oil Production Company, Daqing Oilfield Limited Company, Daqing 163318, China)
  • Online:2024-09-27 Published:2024-09-27

摘要: 我国许多油田的主力开发区块已逐渐进入高含水期,地下油藏复杂,含水量逐步上升,产油量下降。提高对现阶段油田开发生产规律和开采状况的准确认识,对研究油田生产动态变化规律以及制定油田开发策略具有重要意义。针对油田生产动态变化规律的问题,本文提出一种基于改进时序胶囊预测的油藏动态分析模型。首先,应用双向门控循环单元来捕捉油田数据中的时序特征,提升模型对时序信息的建模能力;其次,用多头注意力深度卷积层捕捉初级时序特征信息,高效地提取序列的长距离依赖关系和复杂特征表示;最后,在动态路由算法中引入注意力机制,让高级胶囊更好地关注重要特征,从而提高信息传递的效率和准确性。为验证本文模型有效性,将油田的时序数据作为输入,通过改进胶囊网络模型输出预测日产油量。将改进的胶囊网络与ResNet、LeNet5等9种模型进行对比。实验结果表明,改进后的胶囊网络的预测精度更高,可达到94.5%。

关键词: 胶囊网络, 双向门控循环单元, 动态路由算法, 多头注意力, 时序预测, 油藏分析模型

Abstract:  Many of China’s main development blocks in oilfields have gradually entered a high water cut period, with complex underground oil reservoirs and progressively increasing water content, leading to a decline in oil production. Improving the accurate understanding of the current stage of oilfield development and production patterns is of significant importance for studying the dynamic changes in oilfield production and formulating oilfield development strategies. In view of the dynamic change law of oilfield production, this paper proposes a dynamic analysis model for reservoirs based on improved time-series capsule prediction method. Firstly, a bidirectional gated recurrent unit is applied to capture the timing features in the oilfield data to enhance the fitting ability of the model to timing information. Secondly, the primary temporal feature information is captured with a multi-headed attentional deep convolutional layer to efficiently extract long-range dependencies and complex feature representations of sequences. Finally, in the dynamic routing algorithm, attention mechanism is introduced to allow the higher-level capsules to better focus on important features, so as to improve the efficiency and accuracy of information transmission. To verify the validity of the model, the time-series data of the oil field is used as input to predict the daily oil production by improving the output of the capsule network model. The improved capsule network is compared with nine models such as ResNet, LeNet. The experimental results show that the improved capsule network has higher prediction accuracy, it can reach 94.5%.

Key words: capsule networks, bidirectional gated recurrent unit, dynamic routing algorithms, multi-headed attention, time-series forecasting, reservoir analysis model

中图分类号: