提出了一种使用神经网络作为非线性对象直接控制器的设计方法 ,该控制器由一个常规控制器和一个神经网络控制器组成 .常规控制器对系统给出粗略控制 ,神经网络控制器给出补偿信号来进一步减小系统输出跟踪误差 .该方法对被控非线性对象类型的限制很少 .在该方法中 ,径向基函数 (RBF)神经网络被用来进行训练 ,训练后系统具有较好的稳定性 .仿真结果表明 ,该方法非常有效 ,对非线性系统能取得比较满意的控制效果 A neural network is proposed to design a direct controller for nonlinear objects. The controller consists of a conventional controller and a neural network controller. The conventional controller gives a rough control of the system and the neural network controller gives Compensation signal to further reduce the system output tracking error.This method has very few restrictions on the types of controlled nonlinear objects.In this method, radial basis function (RBF) neural network is used to train the system after training Good stability.The simulation results show that this method is very effective and can achieve more satisfactory control effect for nonlinear systems