File(s) not publicly available

A fuzzy neural network approximator with fast terminal sliding mode and its applications

conference contribution
posted on 06.12.2017, 00:00 by Xinghuo YuXinghuo Yu, Z Man, Shuanghe YuShuanghe Yu
This paper presents a new training method for fuzzy neural network (FNN) systems to approximate unknown nonlinear continuous functions. Fast terminal sliding mode combining the 3nite time convergent property of terminal attractor and exponential convergent property oflinear system has faster convergence to the origin in 3nite time. The proposed training algorithm uses the principle ofthe fast terminal sliding mode into the conventional gradient descent learning algorithm. The Lyapunov stability analysis in this paper guarantees that the approximation is stable and converges to the optimal approximation function with improved speed instead of3nite time convergence to unknown function. The proposed FNN approximator is then applied in the control ofan unstable nonlinear system and the Du5ng system. The simulation results demonstrate the effectiveness of the proposed method.

Funding

Category 1 - Australian Competitive Grants (this includes ARC, NHMRC)

History

Start Page

1257

End Page

1261

Number of Pages

5

Start Date

01/01/2002

ISBN-10

9810475241

Location

Singapore

Publisher

IEEE Service Center

Place of Publication

Singapore

Peer Reviewed

Yes

Open Access

No

External Author Affiliations

Monash University; Nanyang Technological University; Royal Melbourne Institute of Technology (Australia);

Era Eligible

Yes

Name of Conference

ICONIP (Conference)