Sliding mode control of neural networks via continuous or periodic sampling event-triggering algorithm

Shiqin Wang; Yuting Cao; Tingwen Huang; Yiran Chen; Peng Li; Shiping Wen

doi:10.1016/j.neunet.2019.09.001

Sliding mode control of neural networks via continuous or periodic sampling event-triggering algorithm

Neural Netw. 2020 Jan:121:140-147. doi: 10.1016/j.neunet.2019.09.001. Epub 2019 Sep 17.

Authors

Shiqin Wang¹, Yuting Cao², Tingwen Huang³, Yiran Chen⁴, Peng Li⁵, Shiping Wen⁶

Affiliations

¹ School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, China.
² College of Mathematics and Econometrics, Hunan University, Changsha, 410082, China.
³ Science Program, Texas A & M University at Qatar, Doha 23874, Qatar.
⁴ Department of Electrical and Computer Engineering, Duke University, Durham, NC 27708, USA.
⁵ Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA 93106, USA.
⁶ School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, China. Electronic address: wenshiping@uestc.edu.cn.

PMID: 31546126
DOI: 10.1016/j.neunet.2019.09.001

Abstract

This paper presents the theoretical results on sliding mode control (SMC) of neural networks via continuous or periodic sampling event-triggered algorithm. Firstly, SMC with continuous sampling event-triggered scheme is developed and the practical sliding mode can be achieved. In addition, there is a consistent positive lower bound for the time interval between two successive trigger events which implies that the Zeno phenomenon will not occur. Next, a more economical and realistic SMC technique is presented with periodic sampling event-triggered algorithm, which guarantees the robust stability of the augmented system. Finally, two illustrative examples are presented to substantiate the effectiveness of the derived theoretical results.

Keywords: Event-triggering; Neural network; Periodic sampling; Sliding mode control.

MeSH terms

Algorithms*
Neural Networks, Computer*
Sampling Studies