摘要
An adaptive neural fuzzy (NF) controller is developed in this paper for active vibration suppression in flexible structures. A recurrent identification network (RIN) is developed to adaptively identify system dynamics of the plant. A novel recurrent training (RT) technique is suggested to train the RIN so as to optimize nonlinear input-output mapping and to enhance convergence. The effectiveness of the developed controller and the related techniques has been verified experimentally corresponding to different control scenarios. Test results show that the proposed RIN can effectively recognize the time-varying dynamics of the plant. The RT-based hybrid training technique can improve the adaptive capability of the control system to accommodate different system conditions and enhance the training convergence. The developed NF controller is a robust and stable vibration suppression system, and it outperforms other related NF controllers.
An adaptive neural fuzzy (NF) controller is developed in this paper for active vibration suppression in flexible structures. A recurrent identification network (RIN) is developed to adaptively identify system dynamics of the plant. A novel recurrent training (RT) technique is suggested to train the RIN so as to optimize nonlinear input-output mapping and to enhance convergence. The effectiveness of the developed controller and the related techniques has been verified experimentally corresponding to different control scenarios. Test results show that the proposed RIN can effectively recognize the time-varying dynamics of the plant. The RT-based hybrid training technique can improve the adaptive capability of the control system to accommodate different system conditions and enhance the training convergence. The developed NF controller is a robust and stable vibration suppression system, and it outperforms other related NF controllers.
