论文部分内容阅读
在水体工程及河流工程项目规划与设计中,瞬时顶峰流量是需要加以了解的最重要因素之一。本研究的目的是,在估算伊朗法尔斯省西北部Kharestan流域的瞬时顶峰流量时,对人工神经网络法与传统方法的功效进行对比。为此,采用了Jamal Beig水文站25年的日顶峰流量和瞬时顶峰流量数据。在Fuller、Sangal及Fill-Steiner经验方法以及人工神经网络方法的基础上进行了估算,并根据RMSE和R2进行了对比。结果显示,采用人工神经网络法的估算值比经验方法的更为精确,RMSE =13.710,R2= 0.942。这表明人工神经网络法比经验方法的误差更低。
In the planning and design of water projects and river engineering projects, the instantaneous peak flow is one of the most important factors that needs to be understood. The purpose of this study was to compare the effectiveness of the artificial neural network with that of the traditional method when estimating the instantaneous peak flow in the Kharestan basin in the northwestern part of Iran’s Farsh province. For this purpose, the 25-year peak daily flow and instantaneous peak flow data of the Jamal Beig hydrological station were used. Based on the Fuller, Sangal and Fill-Steiner empirical methods and the artificial neural network method, an estimation is made based on RMSE and R2. The results show that the artificial neural network method is more accurate than the empirical method, RMSE = 13.710, R2 = 0.942. This shows that the artificial neural network method is less error than the empirical method.