基于神经网络的一类非线性系统的变结构控制

在已知名义系统的基础上 ,将小脑关节模型控制器 (CMAC)神经网络用于一类状态反馈可线性化的多输入多输出连续时间非线性系统的变结构控制中。利用自适应技术估计了估计误差的大小 ,减小了系统的不确定性 ,并利用模糊控制技术调整了变结构增益 ,改善了系统的性能。在很弱的假设条件下 ,应用Lyapunov稳定性定理证明了闭环系统内的所有信号为均匀最终有界。算法在导弹控制系统中的应用进一步证明了本文方法的有效性。

Neural Network-Based Variable Structure Control for a Class of Nonlinear Systems

Based on the nominal model of the system, cerebellum model articulation controller (CMAC) is used for the variable structure control of a class of state feedback linearizable multiple-input multiple-output continuous-time nonlinear systems. By using adaptive law to estimate the error of estimation, the uncertainty of the system is reduced. The variable structure gain is tuned by the fuzzy logic. The designed controller exploits the advantages of CMAC neural network, variable structure control and fuzzy control theory to improve the performance of the system. For this scheme, stable update laws are determined by using the Lyapunov theory, and the boundedness of all signals in the closed loop system is guaranteed. No prior off-line training phase is necessary. The simulation results verify the efficiency of the proposed approach.