基于径向基函数神经网络的模型跟随自修复控制

提出一种基于径向基函数神经网络的模型跟随非线性自修复控制方法。该方法可不必精确已知故障的位置及程度，即可重构控制律使系统在故障情况下的输出精确跟踪期望参考模型的输出，并采用神经网络控制器以补偿邦联引起的非线性因素的影响。

Model Following Nonlinear Self Repairing Control Based on RBF Neural Networks

A new type of non linear self repairing control strategy based on model following method using radial basis function (RBF) neural networks is presented. This method can make the outputs of impaired system tracking those of reference model accurately without knowing the location and damage degree of failure, and a RBF neural network controller is used to compensate non linear dynamics caused by failure. The structure of the controller is simple and the neural compensator does not require a complex iterative procedure, so it can be carried out on line. Since the conditions of perfect model following (PMF) are satisfied, the proposed method can be applied to self repaining control for a large class of nonlinear system. At last, this method is demonstrated in an aircaft longitudinal contorl system. Simulation results reveal that this method has good reconfigurable performance and robustness.