针对歼击机在结构故障下的动力学方程 ,提出了一种基于径向基函数 (RBF)神经网络的模型跟随非线性重构控制策略。该方法不必精确已知系统故障的位置及其损伤程度 ,可直接对故障系统实施重构控制 ,使其输出能精确跟踪期望参考模型的输出。该方法在模型跟随重构控制的基础上 ,引入了神经网络控制器 ,以补偿故障引起的非线性因素的影响。理论分析和仿真验证表明 ,所提方法可保证闭环系统具有良好的重构性能和很强的鲁棒性 ,且算法高效简单 ,易于计算机在线控制。 Aiming at the kinetic equation of fighter under structural failure, a model following nonlinear reconstruction control strategy based on radial basis function (RBF) neural network is proposed. The method does not need to know exactly the location of the system fault and the degree of damage, and the reconstruction of the fault system can be directly implemented so that the output of the system accurately tracks the output of the expected reference model. Based on the model following reconstruction control, this method introduces neural network controller to compensate for the nonlinearity caused by fault. Theoretical analysis and simulation results show that the proposed method can guarantee closed-loop system has good reconstruction performance and strong robustness, and the algorithm is simple and efficient and easy to control online.