¹Dept of Electrical and Information Engineering, Hunan Institute of Engineering, Hunan Xiangtan, China
²Dept of Computer Science, Hunan Institute of Engineering, Hunan Xiangtan, China

---

Abstract—The paper presents a direct adaptive tracking control scheme for a class of matched SISO affine nonlinear uncertain systems with zero dynamic using neural network. Through neural network approximation, neural network is used as the emulator of the unknown ideal controller. A quadratic cost function of the error between the unknown ideal controller and the used neural network controller is minimized using a gradient descent method to adjust parameters in neural network. The convergence of parameters and the uniformly ultimately boundedness of tracking error and all states of the closed-loop system are guaranteed based on Lyapunov stability theorem. The effectiveness of the proposed controller is illustrated through the simulation results.

Index Terms—Tracking control, matched uncertain nonlinear, gradient descent method, neural network, zero dynamic.

[PDF]

Cite: Hui Hu, Peng Guo, "Neural Network Adaptive Control for a Class of Matched SISO Nonlinear Uncertain Systems with Zero Dynamics," Journal of Computers vol. 7, no. 6, pp. 1490-1496, 2012.