...
首页> 外文期刊>Journal of Hydroinformatics >Prediction of side thermal buoyant discharge in the cross flow using multi-objective evolutionary polynomial regression (EPR-MOGA)
【24h】

Prediction of side thermal buoyant discharge in the cross flow using multi-objective evolutionary polynomial regression (EPR-MOGA)

机译:使用多目标进化多项式回归(EPR-MOGA)在交叉流中预测侧热浮力放电

获取原文
获取原文并翻译 | 示例
           

摘要

The capability to predict the distribution of pollutants in water bodies is one of the most important issues in the design of jet outfalls. Three-dimensional computational fluid dynamics (CFD) model and multi-objective evolutionary polynomial regression (EPR-MOGA) are used and compared in modeling the temperature field in the side thermal buoyant discharge in the cross flow. The input variables used for training the EPR-MOGA models are spatial coordinates (x, y, z), jet to cross flow velocity ratio (R), depth of the channel (d), and the temperature excess (T-0). A previous experimental study is used to verify and compare the performance of the EPR-MOGA and CFD models. The results show that the EPR-MOGA model predicts the thermal cross section of the flow and the spread of pollutants at the surface with a better accuracy than the CFD model. However, the CFD method performs significantly better than EPR-MOGA in predicting temperature profiles. The uncertainty analysis indicated that the EPR-MOGA model had lower mean prediction error and smaller uncertainty band than the CFD model. The relationships achieved by the EPR-MOGA model are very useful to predict temperature profiles, temperature half-thickness, and temperature spread on surface in practice.
机译:预测水体污染物分布的能力是喷气出口设计中最重要的问题之一。使用三维计算流体动力学(CFD)模型和多目标进化多项式回归(EPR-MOGA)并比较在交叉流动中的侧热浮力放电中的温度场模拟。用于训练EPR-MOGA模型的输入变量是空间坐标(x,y,z),喷射到交叉流速比(r),通道深度(d)和温度过量(t-0)。以前的实验研究用于验证和比较EPR-MOGA和CFD模型的性能。结果表明,EPR-MOGA模型预测流量的热横截面和污染物在表面上的扩散,比CFD模型更好。然而,CFD方法在预测温度分布中的epr-moga比EPR-MOGA更好地执行。不确定性分析表明,EPR-MOGA模型具有较低的平均预测误差和比CFD模型更小的不确定性频带。 EPR-MOGA模型实现的关系对于预测在实践中预测温度曲线,温度半厚度和温度差异的非常有用。

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