【作者】 宋立松；

【Author】 SONG Li-song (Zhejiang Institute of Estuary and Coast, Hangzhou 310016, China)

【机构】 浙江省河口海岸研究所；

【摘要】 文章从潮流泥沙模型出发,以同时刻的U、V、H和前一时刻的S、U、V、H为输入,该时刻的S为输出,建立了杭州湾含沙量模拟的模糊神经网络模型。经初步实验表明含沙量的预报较为困难,该模式只能作实时预报,其预报尺度有限,只能有效预报1-3步,这一方面说明杭州湾含沙量变化的复杂性和不确定性,另一方面也表明试图对杭州湾含沙量过程作长期预报是不现实的。更多还原

【Abstract】 This paper presents an adaptive fuzzy neural network (AFNN) for the simulation of continuous sediment concentration on the basis of the tidal flow-sediment model. In this AFNN, 5 is considered as the output,and the values of the instant U、V、H and the previous instant S、U、V、H are considered as the input. The fuzzy relationships between the sediment and other factors are discussed by the field data training and learning with fuzzy clustering and neural network in Hangzhou Bay. The results of primary application shows that the network is only for real-time forecast or short-term sediment concentration forecast, which indicates that it is difficult to make sediment forecast, the forecast scale is very finite, and it is unpractical to make the long-term sediment forecast.更多还原