基于神经网络的水沙运动预报模型与回归模型比较及应用

河道水沙运动过程中是一个复杂的非线性动力学过程，鉴于神经网络具有很强的处理大规模复杂非线性动力学系统的能力，本文将神经网络理论应用于河道水沙运动规律的模拟与预报，以期识别水流泥沙运动变化过程与其影响因素因子之间的复杂非线性关系，为河道水沙模拟和预报提供一条新的方法和途径。在此基础上将神经网络模型与传统回归模拟进行了对比分析并用于螺山站流量大于5000m^3/s的水沙规律模拟，两模型模拟结果与实际水沙规律一带，神经网络模型在水沙因素选择方面回归模型简单，有较成熟的数学理论基础，而回归模型数学表达直观，易于理解。

Application and Comparison of Fluid-Sediment ANN Prediction Model with Empirical Model

Flood evolvement exhibits a complicated non\|linear dynamical process. Seeing that artificial neural network possesses the capabilities of dealing with complex non\|linear dynamical systems, this paper demonstrates how it can be used in flood prediction as a new approach by considering the non\|linear relationship between flood evolvement and its affecting factors. Comparing of fluid\|sediment ANN(Artificial Neural Network) prediction model with empirical model is made and two models are applied to the flood level prediction of Yangtze River at Luoshan station.