Chang Yeong-Chan, Yen Hui-Min
IEEE Trans Syst Man Cybern B Cybern. 2005 Dec;35(6):1311-6. doi: 10.1109/tsmcb.2005.850158.
This correspondence addresses the problem of designing robust tracking control for a class of uncertain nonlinear MIMO second-order systems. An adaptive neural-network-based output feedback tracking controller is constructed such that all the states and signals involved are uniformly bounded and the tracking error is uniformly ultimately bounded. Only the output measurement is required for feedback. The implementation of the neural network basis functions depends only on the desired reference trajectory. Therefore, the intelligent adaptive output feedback controller developed here possesses the properties of computational simplicity and easy implementation. A simulation example of controlling mass-spring-damper mechanical systems is made to confirm the effectiveness and performance of the developed control scheme.
本通信针对一类不确定非线性多输入多输出二阶系统的鲁棒跟踪控制问题展开研究。构建了一种基于自适应神经网络的输出反馈跟踪控制器，使得所有涉及的状态和信号均一致有界，且跟踪误差一致最终有界。反馈仅需输出测量值。神经网络基函数的实现仅取决于期望的参考轨迹。因此，本文所开发的智能自适应输出反馈控制器具有计算简单和易于实现的特性。通过对质量 - 弹簧 - 阻尼器机械系统进行控制的仿真示例，验证了所开发控制方案的有效性和性能。
