输出不可量测非线性系统的神经模型参考自适应控制
A neural network model reference adaptive control for the nonlinear system with unavailable outputs
-
摘要: 该文针对被控对象输出不可量测的非线性系统，引入一个便于在线辨识的扩展神经网络模型，提出一种基于前馈-反馈结构的神经网络模型参考自适应控制方法。给出了具有全局收敛性的网络训练算法，并分析了控制系统的稳定性。仿真结果表明该控制方法是有效的，而且对网络初始权值的选取及被控对象特性参数的扰动都具有良好的鲁棒性。Abstract: In this paper, by introducing an extended neural network model which can be easily identified on-line, a neural network model reference adaptive control method based on a feedforward-feedback structure is proposed for a class of nonlinear systems whose outputs are not measurable. A training algorithm with global convergence is offered, and the stability of the control system is analyzed. The simulation results show that this method is effective, anrl it has good robustness for both the selection of original network weights and the disturbance of plant parameters.
-
李新忠,简林柯,何钺,非线性系统的模型参考神经网络控制,信息与控制,1996,25(6),367-372[2]G. Lightbody, G. W. Irwin, Direct neural model reference adaptive control, IEE Proc. Control Theory Appl., 1995, 142(1), 31-43.[3]S.J. Elliott, P. A. Nelson, Active noise control, IEEE Signal Processing Mag., 1993, 10(4), 12 35.[4]S.D. Snyder, N. Tanaka, Active control of vibration using a neural network, IEEE Trans. on Neural Networks, 1995, 6(4), 819-828.[5]M. Bouchard, B. Paillard, C. T. L. Dinh, Improved training of neural networks for the nonlinear active control of sound and vibration, IEEE Trans. on Neural Networks, 1999, 10(2), 391-401.[6]何玉彬,李新忠,神经网络控制技术及其应用,北京,科学出版社,2000,39-48. -
计量
- 文章访问数: 2023
- HTML全文浏览量: 74
- PDF下载量: 595
- 被引次数: 0
下载:
