| 基于CMAC 神经网络的一类M I MO非线性系统的自适应反馈线性化 |
| |
| 引用本文： | 张友安,周绍磊,崔平远,杨 涤. 基于CMAC 神经网络的一类M I MO非线性系统的自适应反馈线性化[J]. 控制与决策, 2000, 15(1): 83-85 |
| |
| 作者姓名： | 张友安 周绍磊 崔平远 杨 涤 |
| |
| 作者单位： | 1. 烟台海军航空工程学院自动控制系,264001
2. 哈尔滨工业大学航天工程与力学系 |
| |
| 基金项目： | 国家自然科学基金项目!（19572114） |
| |
| 摘 要： | 在已知系统标称模型的基础上，将ＣＭＡＣ；神经网络用于一类状态反馈可线性化的ＭＩＭＯ连续时间不确定性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一致最终有界。仿真算例验证了该方法的正确性与有效性。
|
| 关 键 词： | MIMO 非线性系统 CMAC 神经网络 自适应控制 |
CMAC Neural Network Based Adaptive Feedback Linearization for MIMO Nonlinear Systems |
| |
| Zhang Youan,Zhou Shaolei. CMAC Neural Network Based Adaptive Feedback Linearization for MIMO Nonlinear Systems[J]. Control and Decision, 2000, 15(1): 83-85 |
| |
| Authors: | Zhang Youan Zhou Shaolei |
| |
| Abstract: | The CMAC neural network is used for adaptive feedback-linearization of a class of state-feedback linearizable multiple-input multiple-output (MIMO) continuous-time nonlinear systems with model uncertainty. The adaptive feedback-linearization portion is based on the nominal model of the system. A stability proof is given strictly in the sense of Lyapunov. It is shown that all the signals in the closed loop systems are uniformly ultimately bounded. The proposed scheme is quite fit for real-time adaptive control. Simulation results have shown the rightness and effectiveness of the proposed scheme. |
| |
| Keywords: | MIMO nonlinear systems CMAC neural networks feedback linearization robust-adaptive |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《控制与决策》浏览原始摘要信息 |
|
点击此处可从《控制与决策》下载全文 |
