CMAC神经网络用于一类不确定MIMO非线性系统的鲁棒自适应反馈线性化

在已知标称系统的基础上，将CMAC神经网络用于一类状态反馈可线性化的多输入多输出（MIMO）不稳定连续时间非线性系统的鲁棒自适应反馈线性化，使系统获得要求的跟踪性能。在很弱的假设条件下，应用李雅普诺夫稳定性理论证明了闭环系统内的所有信号为UUB（一致最终有界）。仿真算例进一步验证了算法的正确与有效。

CMAC neural networks-based robust-adaptive feedback linearization for MIMO nonlinear systems

Justifies the necessity of feedback linearization, a important branch of non linear control theory, to make the system linear by feedback because the dependence on the precise non linear model made the actual application limited and the statefeedback linearization of a kind of MIMO non linear system based on CMAC needs to estimate the whole non linear system model using the model information, and presents the CMAC neural network used for robust adaptive feedback linearization of a class of multiple input multiple output uncertain continuous time nonlinear systems, and the stability proof given strictly in the sense of Lyapunov and the finding that all the signals in the closed loop systems are bounded and concludes from the simulation results that the proposed scheme is right and effective.