首页> 外文期刊>Engineering Applications of Computational Fluid Mechanics >Efficient methods for prediction of velocity fields in open channel junctions based on the artifical neural network
【24h】

Efficient methods for prediction of velocity fields in open channel junctions based on the artifical neural network

机译:基于人工神经网络的明渠路口速度场预测的高效方法

获取原文
           

摘要

Measurement results, sediment transport and pollutant dispersion in confluence regions are highly affected by flow structures of open channel junction and it is necessary to find an efficient method that can fully describe the velocity fields in junctions. In this study the velocity field in an open channel junction was investigated by using Artificial Neural Network (ANN) and three dimensional modelling. First, a modified Genetic Algorithm (GA) was introduced, then, an ANN model was optimized and the flow velocity was predicted in a 90 degree channel junction. Also, for three dimensional simulation of the free surface flow in the considered junction ANSYS-CFX software was used. Comparison of the results obtained from ANN and CFX models with laboratory data with root mean square error of 0.094 and 0.182 and percent standard error of prediction of ?9.75 and ?25.71 respectively, showed that the introduced ANN perform better than CFX in modelling velocity field in open channel junction and it was able to pre...
机译:汇合区的流场结构对汇合区的测量结果,沉积物迁移和污染物扩散影响很大,因此有必要寻找一种能够充分描述汇合处速度场的有效方法。在这项研究中,通过使用人工神经网络(ANN)和三维建模,研究了明渠路口的速度场。首先,介绍了一种改进的遗传算法(GA),然后优化了ANN模型,并预测了90度通道结的流速。同样,对于所考虑的连接处的自由表面流的三维模拟,使用了ANSYS-CFX软件。将ANN和CFX模型的结果与实验室数据的均方根误差为0.094和0.182,预测标准误差的百分比标准误差为?9.75和?25.71进行比较,表明引入的ANN在速度场建模方面优于CFX。开放渠道的交界处,它能够预...

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