摘要
黄河内蒙古河段过流能力是黄河上游水沙调控的重要影响因素,也是制约其自身健康发展以及沿岸社会发展需求的瓶颈。通过建立黄河内蒙古河段平滩流量BP神经网络模型,模拟平滩流量与来水来沙之间的非线性特征,并与滞后响应模型进行比较。结果表明,BP神经网络模型在考虑来水来沙条件累积作用的基础上,综合考虑了汛期和非汛期的来水来沙条件,数据拟合和预测方面达到较高的精度,综合评价的4个指标值均为最优,在模拟和预测黄河内蒙古河段平滩流量随来水来沙的调整过程中,具有较高的实用价值。
Conveyance capacity is an important factor of runoff and sediment regulation in the Upper Yellow River,and it is also the bottleneck problem to its own healthy development and coastal social development demand in Inner Mongolia reach of Yellow River.In this paper,the BP neural network model is adopted to simulate the nonlinear characteristics between bankfull discharge and incoming flow and sediment load,and the results were compared to the delayed response model.The results show that the BP neural network model has high precision in data fitting and prediction,considering not only the cumulative action of incoming flow and sediment load conditions,but also incoming flow and sediment load conditions in flood season and non-flood season,4 evaluation indexes are all optimal,which proves that it has a high practical value in simulating and predicting the change process of bankfull discharge with incoming flow and sediment load in Inner Mongolia Reach of Yellow River.
作者
郭彦
王平
侯素珍
魏欢
GUO Yan;WANG Ping;HOU Suzhen;WEI Huan(Yellow River Institute of Hydraulic Research,Yellow River Conservancy Commission,Zhengzhou,He'an 450003,China;Key Laboratory of Yellow River Sediment Research,Ministry of Water Resources,Zhengzhou,He'nan 450003,China)
出处
《水利与建筑工程学报》
2021年第3期246-251,256,共7页
Journal of Water Resources and Architectural Engineering
基金
国家重点研发计划资助项目(2017YFC0405202)
国家自然科学基金资助项目(51609094)。
关键词
过流能力
平滩流量
滞后响应
BP神经网络
conveyance capacity
bankfull discharge
delayed response
BP neural network
