根据流域径流预报的特点,针对神经网络原有固定结构学习方法的缺陷,通过对人工神经网络、遗传算法进行组合利用和加以改进,建立了混合遗传神经网络模型,并对其神经网络的结构和权值阈值同时进行了优化。然后以某灌区径流预报为例,分别利用BP(back propagation)算法、本文方法进行仿真试验,验证方案的可行性和有效性,结果表明本文算法既克服了神经网络结构选取的盲目性,给出了优秀的初始权值,又克服了遗传算法耗时的缺点,最终达到了提高网络收敛性能和收敛速度的目的。 According to the characteristics of runoff forecasting in runoff basin, aiming at the shortcomings of original fixed structure learning method in neural network, a hybrid genetic neural network model is established by combining and improving artificial neural network and genetic algorithm. The structure of neural network and its structure The weight threshold is also optimized at the same time. Taking the runoff forecast of a certain irrigation area as an example, this paper uses BP (back propagation) algorithm and the method in this paper to simulate the experiment to verify the feasibility and effectiveness of the scheme. The results show that the proposed algorithm not only overcomes the blindness of neural network structure selection, It also overcomes the shortcomings of time-consuming genetic algorithm and finally achieves the goal of improving network convergence performance and convergence speed.