神经网络及遗传算法在径流预报中的应用

提出用遗传算法和BP算法相结合的改进神经网络模型来进行径流预报。即先通过遗传算法对初始权值分布进行优化，在解空间定位出一个较好的搜索空间，然后采用BP算法，在这个较小的解空间中搜索出最优解。使网络收敛速度加快和避免局部极小。作为实例，以清江鸭子口的实测径流资料为样本进行训练并用以预测该水文站的日径流量。结果表明，该方法具有收敛速度快和预测精度高的特点。

Application of Neural Network and GA in Runoff Prediction Model

A new method for training the neural network prediction model is presented. In this method, the genetic algorithm(GA),a general-purpose global search algorithm is used to update the initial weights for minimizing the error between the network output and the desired output. Then the back-propagation(BP) algorithm is used to further train the neural network prediction model. This method is used to speed up the convergence and improve the performance. Analyzing and discussing the case of Yazikou,Qingjiang demonstrated the procedures and performance of this neural network-training algorithm.