Stability analysis of neural networks with time-varying delay: Enhanced stability criteria and conservatism comparisons

Abstract This paper is concerned with the stability analysis of neural networks with a time-varying delay. To assess system stability accurately, the conservatism reduction of stability criteria has attracted many efforts, among which estimating integral terms as exact as possible is a key issue. At first, this paper develops a new relaxed integral inequality to reduce the estimation gap of popular Wirtinger-based inequality (WBI). Then, for showing the advantages of the proposed inequality over several existing inequalities that also improve the WBI, four stability criteria are derived through different inequalities and the same Lyapunov–Krasovskii functional (LKF), and the conservatism comparison of them is analyzed theoretically. Moreover, an improved criterion is established by combining the proposed inequality and an augmented LKF with delay-product-type terms. Finally, several numerical examples are used to demonstrate the advantages of the proposed method.

[1]  Xue-Zhong He,et al.  Delay-independent stability in bidirectional associative memory networks , 1994, IEEE Trans. Neural Networks.

[2]  Qing-Long Han,et al.  New Lyapunov-Krasovskii Functionals for Global Asymptotic Stability of Delayed Neural Networks , 2009, IEEE Trans. Neural Networks.

[3]  Fang Liu,et al.  Exponential Stability Analysis for Neural Networks With Time-Varying Delay , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[4]  Shen-Ping Xiao,et al.  Stability analysis of generalized neural networks with time-varying delays via a new integral inequality , 2015, Neurocomputing.

[5]  Alexander H. Waibel,et al.  A novel objective function for improved phoneme recognition using time delay neural networks , 1990, International 1989 Joint Conference on Neural Networks.

[6]  Georgi M. Dimirovski,et al.  New delay-dependent stability criteria for recurrent neural networks with time-varying delays , 2008, Neurocomputing.

[7]  Frédéric Gouaisbaut,et al.  Wirtinger-based integral inequality: Application to time-delay systems , 2013, Autom..

[8]  Ju H. Park,et al.  On stability analysis for neural networks with interval time-varying delays via some new augmented Lyapunov-Krasovskii functional , 2014, Commun. Nonlinear Sci. Numer. Simul..

[9]  Shiho Kim,et al.  New results on stability criteria for neural networks with time-varying delays , 2011 .

[10]  Kun She,et al.  New and improved results for recurrent neural networks with interval time-varying delay , 2016, Neurocomputing.

[11]  Jin-Hua She,et al.  Delay-dependent exponential stability of delayed neural networks with time-varying delay , 2006, IEEE Transactions on Circuits and Systems II: Express Briefs.

[12]  Yong He,et al.  Stability analysis of systems with time-varying delay via relaxed integral inequalities , 2016, Syst. Control. Lett..

[13]  Guang-Hong Yang,et al.  New Delay-Dependent Stability Results for Neural Networks With Time-Varying Delay , 2008, IEEE Transactions on Neural Networks.

[14]  Leon O. Chua,et al.  Cellular neural networks: applications , 1988 .

[15]  Min Wu,et al.  Further results on exponential stability of neural networks with time-varying delay , 2015, Appl. Math. Comput..

[16]  Jian-an Wang,et al.  Less conservative stability criteria for neural networks with interval time-varying delay based on delay-partitioning approach , 2015, Neurocomputing.

[17]  Guo-Ping Liu,et al.  New Delay-Dependent Stability Criteria for Neural Networks With Time-Varying Delay , 2007, IEEE Transactions on Neural Networks.

[18]  Yong He,et al.  Stability Analysis for Delayed Neural Networks Considering Both Conservativeness and Complexity , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[19]  Huaguang Zhang,et al.  Stability Criteria for Recurrent Neural Networks With Time-Varying Delay Based on Secondary Delay Partitioning Method , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[20]  Yong He,et al.  Complete Delay-Decomposing Approach to Asymptotic Stability for Neural Networks With Time-Varying Delays , 2011, IEEE Transactions on Neural Networks.

[21]  Min Wu,et al.  Delay-dependent stability analysis of neural networks with time-varying delay: A generalized free-weighting-matrix approach , 2017, Appl. Math. Comput..

[22]  Yong He,et al.  Delay-Variation-Dependent Stability of Delayed Discrete-Time Systems , 2016, IEEE Transactions on Automatic Control.

[23]  James Lam,et al.  Stability and Dissipativity Analysis of Static Neural Networks With Time Delay , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[24]  Ju H. Park,et al.  New and improved results on stability of static neural networks with interval time-varying delays , 2014, Appl. Math. Comput..

[25]  Qing-Long Han,et al.  Global asymptotic stability analysis for delayed neural networks using a matrix-based quadratic convex approach , 2014, Neural Networks.

[26]  S. M. Lee,et al.  New augmented Lyapunov–Krasovskii functional approach to stability analysis of neural networks with time-varying delays , 2014 .

[27]  Qiongfen Yang,et al.  New delay dependent stability criteria for recurrent neural networks with interval time-varying delay. , 2014, ISA transactions.

[28]  Zhiqiang Zuo,et al.  On exponential stability analysis for neural networks with time-varying delays and general activation functions , 2012 .

[29]  Zidong Wang,et al.  Global exponential stability of generalized recurrent neural networks with discrete and distributed delays , 2006, Neural Networks.

[30]  Jinde Cao,et al.  Global asymptotic stability of neural networks with transmission delays , 2000, Int. J. Syst. Sci..

[31]  Min Wu,et al.  Stability analysis of recurrent neural networks with interval time-varying delay via free-matrix-based integral inequality , 2016, Neurocomputing.

[32]  Ju H. Park,et al.  Stability for Neural Networks With Time-Varying Delays via Some New Approaches , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[33]  PooGyeon Park,et al.  Auxiliary function-based integral inequalities for quadratic functions and their applications to time-delay systems , 2015, J. Frankl. Inst..

[34]  Min Wu,et al.  Stability Analysis for Neural Networks With Time-Varying Interval Delay , 2007, IEEE Transactions on Neural Networks.

[35]  Qing-Long Han,et al.  Global Asymptotic Stability for a Class of Generalized Neural Networks With Interval Time-Varying Delays , 2011, IEEE Trans. Neural Networks.

[36]  PooGyeon Park,et al.  Improved stability criteria for recurrent neural networks with interval time-varying delays via new Lyapunov functionals , 2015, Neurocomputing.

[37]  Min Wu,et al.  Summation Inequalities to Bounded Real Lemmas of Discrete-Time Systems With Time-Varying Delay , 2017, IEEE Transactions on Automatic Control.

[38]  Xin Yang,et al.  New delay-variation-dependent stability for neural networks with time-varying delay , 2013, Neurocomputing.

[39]  Shengyuan Xu,et al.  A new LMI condition for delay-dependent asymptotic stability of delayed Hopfield neural networks , 2006, IEEE Transactions on Circuits and Systems II: Express Briefs.

[40]  PooGyeon Park,et al.  Reciprocally convex approach to stability of systems with time-varying delays , 2011, Autom..

[41]  Huaguang Zhang,et al.  A Comprehensive Review of Stability Analysis of Continuous-Time Recurrent Neural Networks , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[42]  Zhigang Zeng,et al.  Improved conditions for global exponential stability of a general class of memristive neural networks , 2015, Commun. Nonlinear Sci. Numer. Simul..

[43]  Min Wu,et al.  Free-Matrix-Based Integral Inequality for Stability Analysis of Systems With Time-Varying Delay , 2015, IEEE Transactions on Automatic Control.

[44]  Min Wu,et al.  Delay-Dependent Stability Criteria for Generalized Neural Networks With Two Delay Components , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[45]  Ju H. Park,et al.  Stability and dissipativity analysis of static neural networks with interval time-varying delay , 2015, J. Frankl. Inst..

[46]  Shengyuan Xu,et al.  Novel global asymptotic stability criteria for delayed cellular neural networks , 2005, IEEE Transactions on Circuits and Systems II: Express Briefs.

[47]  Ting Wang,et al.  Combined Convex Technique on Delay-Dependent Stability for Delayed Neural Networks , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[48]  Jian Sun,et al.  Improved stability criteria for neural networks with time-varying delay , 2009 .

[49]  Daoyun Xu,et al.  Vector Wirtinger-type inequality and the stability analysis of delayed neural network , 2013, Commun. Nonlinear Sci. Numer. Simul..

[50]  Xin-Ping Guan,et al.  New Delay-Dependent Stability Criteria for Neural Networks With Time-Varying Delay Using Delay-Decomposition Approach , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[51]  Min Wu,et al.  Novel stability criteria for recurrent neural networks with time-varying delay , 2014, Neurocomputing.

[52]  Yong He,et al.  Global exponential stability of neural networks with time-varying delay based on free-matrix-based integral inequality , 2016, Neural Networks.