论文信息 - Decoupling control of three-axis simulator

Decoupling control of three-axis simulator

In this paper, the decoupling problem for a three-axis simulator is considered. The dynamic model of the simulator is established firstly, and the reversibility of the model is proved. The three-axis simulator is highly coupled and nonlinear. The nonlinear autoregressive exogenous input (NARX) neural network is introduced to identify the inverse model of the simulator. A Lyapunov function is introduced to prove the convergence of the network. A strategy for inverse model decoupling control is proposed. The decoupling result in this paper supports the theory and decoupling strategy.

Wei Jiang | Zhen-Yu Wang | Bo-Chang Shen | Guo-Xing Yi | Chang-Hong Wang

[1] John Tsinias,et al. Invertibility of nonlinear analytic single-input systems , 1983 .

[2] Yoshua Bengio,et al. Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[3] Hava T. Siegelmann,et al. Computational capabilities of recurrent NARX neural networks , 1997, IEEE Trans. Syst. Man Cybern. Part B.

[4] Kevin Warwick,et al. Inverse model control using recurrent networks , 2000 .

[5] Ronald J. Williams,et al. Experimental Analysis of the Real-time Recurrent Learning Algorithm , 1989 .

[6] Wang Changhong,et al. The compensation of speed ripple caused by the angle-measuring error of inductosyn using neural network , 2001, 2001 International Conferences on Info-Tech and Info-Net. Proceedings (Cat. No.01EX479).