Journal
NEURAL COMPUTING & APPLICATIONS
Volume 22, Issue -, Pages S421-S433Publisher
SPRINGER LONDON LTD
DOI: 10.1007/s00521-012-1154-4
Keywords
Hermite neural network; Adaptive control; Neural control; Coupled chaotic system; Synchronization
Categories
Funding
- National Science Council of Republic of China [NSC 100-2628-E-032-003]
Ask authors/readers for more resources
A TSK-type Hermite neural network (THNN) is studied in this paper. Since the output weights of the THNN use a functional-type form, it provides powerful representation, high learning performance and good generalization capability. Then, a Hermite-neural-network-based adaptive control (HNNAC) system which is composed of a neural controller and a robust compensator is proposed. The neural controller utilizes a THNN to online approximate an ideal controller, and the robust compensator is designed to eliminate the effect of the approximation error introduced by the neural controller upon the system stability. Moreover, a proportional-integral (PI)-type learning algorithm is derived to speed up the convergence of the tracking error. Finally, the proposed HNNAC system is applied to synchronize a coupled non-linear chaotic system. In the simulation study, it shows that the proposed HNNAC system can achieve favorable synchronization performance without requiring a preliminary offline tuning.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available