• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Hydrology Research >GA-optimized model predicts dispersion coefficient in natural channels
【24h】

GA-optimized model predicts dispersion coefficient in natural channels

机译：GA优化模型可预测自然通道中的弥散系数

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Models whose parameters were optimized by genetic algorithm (GA) were developed to predictnthe longitudinal dispersion coefficient in natural channels. Following the existing equations in thenliterature, ten different linear and nonlinear models were first constructed. The models relatenthe dispersion coefficient to flow and channel characteristics. The GA model was then employednto find the optimal values of the constructed model parameters by minimizing the mean absolutenerror function (objective function). The GA model utilized an 80% cross-over rate and 4% mutationnrate. It started each computation with a population of 100 chromosomes in the gene pool. Forneach model, while minimizing the objective function, the values of the model parameters werenconstrained between [210, +10] at each iteration. The optimal values of the model parametersnwere obtained using a calibration set of 54 out of 80 sets of measured data. The minimum errornwas obtained for the case where the model was a linear equation relating dispersion coefficientnto flow discharge. The model performance was then satisfactorily tested against the remaining 26nmeasured validation datasets. It performed better than the existing equations. It yielded minimumnerrors of MAE ¼ 21.4m2n/s (mean absolute error) and RMSE ¼ 28.5m2n/s (root mean-squaresnerror) and a maximum accuracy rate of 81%.
机译：开发了通过遗传算法（GA）优化参数的模型，以预测自然通道中的纵向弥散系数。根据当时的现有方程，首先构造了十个不同的线性和非线性模型。这些模型将色散系数与流量和通道特性联系起来。然后，通过最小化平均绝对误差函数（目标函数），采用GA模型找到构造模型参数的最佳值。 GA模型利用了80％的交叉率和4％的突变率。它从基因库中的100条染色体开始进行每次计算。对于模型，在最小化目标函数的同时，模型参数的值在每次迭代时都限制在[210，+10]之间。使用80组测量数据中的54组校准集获得模型参数的最佳值。对于模型为与色散系数与流量相关的线性方程的情况，获得了最小误差。然后针对剩余的26n个测量的验证数据集对模型性能进行了令人满意的测试。它的性能比现有方程更好。它产生的最小误差为MAE¼21.4m2n / s（平均绝对误差）和RMSE¼28.5m2n / s（均方根误差），最大准确率为81％。

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