采用基于递推预报误差算法的分布式神经网络结构建立非线性系统模型 .子神经网络模型及其连接权值均采用递推预报误差方法来进行训练 ,将所有子网络融合得到的分布式神经网络模型在模型精确性和鲁棒性方面有显著地增加 .该方法较好地应用于复杂非线性动态系统的建模 A distributed neural network model based on recursive forecasting error algorithm is used to establish a nonlinear system model.Nonlinear neural network model and its connection weights are trained by recursive forecasting error method and distributed neural network The model has a significant increase in the accuracy and robustness of the model.The proposed method is better applied to the modeling of complex nonlinear dynamic systems