首页> 外文期刊>Journal of Petroleum Exploration and Production Technology >The prediction of shale gas well production rate based on grey system theory dynamic model GM(1, N)
【24h】

The prediction of shale gas well production rate based on grey system theory dynamic model GM(1, N)

机译:基于灰色系统理论动态模型GM(1,N)的页岩气井生产率预测

获取原文
           

摘要

The prediction of production volumes from shale gas wells is important in reservoir development. The physical parameters of a reservoir are uncertain and complex, and therefore, it is very difficult to predict the production capability of a shale gas well. An improved GM(1, N) model for shale gas well productivity prediction, focused upon the causes of prediction errors from the existing traditional GM(1, N) method, was established. By processing a data series related to the predicted data, the improved GM(1, N) model takes into account the fluctuations of the original production data, reflects the trend of the original data under the influence of relevant factors, and hence predicts more accurately the fluctuation amplitude and direction of the original data. Additionally, the proposed method has higher accuracy than the conventional GM(1, N), GM(1, 1), and MEP models. The prediction accuracy increases gradually and the relative error decreases gradually from bottom data (casing pressure at well start-up, etc.) to top data (shale gas production). Accordingly, a step-by-step prediction method could be effective in improving prediction accuracy and reflects the typical fluctuation characteristics of shale gas production.
机译:来自页岩气井的生产量的预测在储层开发中是重要的。储存器的物理参数是不确定和复杂的,因此,非常困难预测页岩气井的生产能力。建立了一种改进的GM(1,N)模型的页岩气井生产率预测,重点是从现有的传统GM(1,N)方法的预测误差的原因。通过处理与预测数据相关的数据序列,改进的GM(1,N)模型考虑了原始生产数据的波动,反映了相关因子的影响下原始数据的趋势,因此更准确地预测原始数据的波动幅度和方向。此外,所提出的方法比传统的GM(1,N),GM(1,1)和MEP模型具有更高的精度。预测精度逐渐增加,相对误差逐渐从底部数据(井启动等)到顶部数据(页岩气生产)逐渐减小。因此,逐步的预测方法可以有效地提高预测精度,并反映出页岩气产量的典型波动特性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号