基于神经网络参数辨识的洪水波特性研究

Study on artificial neural network to identify the parameters of flood wave equation

本文提出利用神经网络辨识扩散波参数的方法 ,探索从一种新的角度研究洪水波特性。应用实例表明该方法的模拟精度满足要求 ,模拟效果良好。说明建立的洪水波神经网络模型能较好地描述洪水波的运动规律。

An ANN-based parameters identification method of flood diffusion wave is presented in this paper. Flood diffusion wave equation is reinstated through the trained ANN, and then the downstream outflow can be forecasted. This study opens up a new way to observed data for knowledge discovery. This method has been applied to the Qingjiang River, the satisfactory results are acquired.