文献类型：期刊文献

英文题名：Stability Analysis for Delayed Neural Networks via Improved Auxiliary Polynomial-Based Functions

作者：Li, Zhichen[1];Yan, Huaicheng[1];Zhang, Hao[2];Zhan, Xisheng[3];Huang, Congzhi[4]

机构：[1]East China Univ Sci & Technol, Minist Educ, Key Lab Adv Control & Optimizat Chem Proc, Shanghai 200237, Peoples R China;[2]Tongji Univ, Dept Control Sci & Engn, Shanghai 200092, Peoples R China;[3]Hubei Normal Univ, Coll Mechatron & Control Engn, Huangshi 435002, Hubei, Peoples R China;[4]North China Elect Power Univ, Sch Control & Comp Engn, Beijing 102206, Peoples R China

年份：2019

卷号：30

期号：8

起止页码：2562

外文期刊名：IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS

收录：;EI(收录号：20185206292151);WOS:【SCI-EXPANDED(收录号:WOS:000476787300027)】；

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 61803159, Grant 61673178, and Grant 61773289, in part by the Shanghai Sailing Program under Grant 18YF1406400, in part by the Shanghai Natural Science Foundation under Grant 18ZR1409600, Grant 17ZR1444700, and Grant 17ZR1445800, in part by the Shanghai International Science and Technology Cooperation Project under Grant 15220710700 and Grant 18510711100, in part by the Shanghai Shuguang Project under Grant 16SG28, in part by the China Postdoctoral Science Foundation under Grant 2018M032042, and in part by the Fundamental Research Funds for the Central Universities under Grant 222201814040. (Corresponding author: Huaicheng Yan.)

语种：英文

外文关键词：Auxiliary polynomial-based functions (APFs); delay-product terms; delayed neural networks (DNNs); slack variables; stability

摘要：This brief is concerned with stability analysis for delayed neural networks (DNNs). By establishing polynomials and introducing slack variables reasonably, some improved delay-product type of auxiliary polynomial-based functions (APFs) is developed to exploit additional degrees of freedom and more information on extra states. Then, by constructing Lyapunov-Krasovskii functional using APFs and integrals of quadratic forms with high order scalar functions, a novel stability criterion is derived for DNNs, in which the benefits of the improved inequalities are fully integrated and the information on delay and its derivative is well reflected. By virtue of the advantages of APFs, more desirable performance is achieved through the proposed approach, which is demonstrated by the numerical examples.