Novel \(H_{\infty}\) performance and delay-dependent exponential passivity for neural networks in response to leakage delay

Volume 35, Issue 4, pp 431--456 https://dx.doi.org/10.22436/jmcs.035.04.04

Publication Date: May 31, 2024 Submission Date: February 09, 2024 Revision Date: April 02, 2024 Accteptance Date: May 10, 2024

Download PDF

Download XML

• Export citations
  • CITATIONS & REFERENCES
  • EndNote (.ENW)
  • Mendeley, JabRef (.BIB)
  • Papers, Zotero, Reference Manager, RefWorks (.RIS)
  • ARTICLE CITATION
  • EndNote (.ENW)
  • Mendeley, JabRef (.BIB)
  • Papers, Zotero, Reference Manager, RefWorks (.RIS)
  • REFERENCES
  • EndNote (.ENW)
  • Mendeley, JabRef (.BIB)
  • Papers, Zotero, Reference Manager, RefWorks (.RIS)

• 87 Downloads
• 463 Views

Authors

P. Singkibud - Department of Applied Mathematics and Statistics, Faculty of Science and Liberal Arts, Rajamangala University of Technology Isan, Nakhon Ratchasima 30000, Thailand. W. Chartbuphapan - Department of Applied Mathematics and Statistics, Faculty of Science and Liberal Arts, Rajamangala University of Technology Isan, Nakhon Ratchasima 30000, Thailand. Ch. Zamart - Department of Applied Mathematics and Statistics, Faculty of Science and Liberal Arts, Rajamangala University of Technology Isan, Nakhon Ratchasima 30000, Thailand. S. Luemsai - Department of Applied Mathematics and Statistics, Faculty of Science and Liberal Arts, Rajamangala University of Technology Isan, Nakhon Ratchasima 30000, Thailand. K. Mukdasai - Department of Mathematics, Faculty of Science, Khon Kaen University, Khon Kaen 40002, Thailand.

Abstract

This article studies the problem of exponential passivity and \(H_{\infty}\) performance for neural networks (NNs) under the effect of leakage and distributed delays. A novel criterion for achieving exponential passivity in these neural networks is derived. Moreover, we establish new criteria for analyzing the exponential stability and \(H_{\infty}\) performance of the system. Utilizing the Lyapunov-Krasovskii stability theory, we employ an integral inequality to assess the derivative of the Lyapunov-Krasovskii functionals, often referred to as LKFs. This estimation involves constructing novel LKFs that incorporate triple and quadruple integral terms. Furthermore, we obtain results contingent upon the leakage delay and the upper bound of the time-varying delays. To provide context, we conduct comparisons to contrast with existing results. In order to demonstrate the usefulness of the findings, a few numerical examples are provided together with computer simulations.

Share and Cite

Keywords

• Exponential passivity and \(H_{\infty}\) performance
• neural networks
• leakage delay

MSC

•  34A34
•  26D10
•  34D20
•  92B20

References

• [1] S. Arockia Samy, P. Anbalagan, Disturbance observer-based integral sliding-mode control design for leader-following consensus of multi-agent systems and its application to car-following model, Chaos Solitons Fractals, 174 (2023), 14 pages
  • View Article
  • MathSciNet
  • Google Scholar


• [2] S. Arockia Samy, R. Raja, P. Anbalagan, Y. Cao, Synchronization of nonlinear multi-agent systems using a non-fragile sampled data control approach and its application to circuit systems, Front. Inf. Technol. Electron. Eng., 24 (2023), 553–566
  • View Article
  • Google Scholar


• [3] T. Botmart, N. Yotha, K. Mukdasai, W. Weera, Improved results on passivity analysis of neutral-type neural networks with mixed time-varying delays, WSEAS Trans. Circuits Syst., 17 (2018), 53–59
  • View Article
  • Google Scholar


• [4] J. D. Cao, K. Yuan, H.-X. Li, Global asymptotical stability of recurrent neural networks with multiple discrete delays and distributed delays, IEEE Trans. Neural Netw., 17 (2006), 1646–1651
  • View Article
  • Google Scholar


• [5] T. Chen, Global exponential stability of delayed Hopfield neural networks, Neural Netw., 14 (2001), 977–980
  • View Article


• [6] J.-D. Chen, Delay-dependent robust H1 control of uncertain neutral systems with state and input delays: LMI optimization approach, Chaos Solitons Fractals, 33 (2007), 596–606
  • View Article
  • MathSciNet
  • Google Scholar
  • MATH


• [7] E. Fridman, U. Shaked, On delay-dependent passivity, IEEE Trans. Automat. Control, 47 (2002), 664–669
  • View Article
  • MathSciNet
  • Google Scholar
  • MATH


• [8] H. Gao, T. Chen, T. Chai, Passivity and pacification for networked control systems, SIAM J. Control Optim., 46 (2007), 1299–1322
  • View Article
  • Google Scholar


• [9] R. S. Gau, C. H. Lien, J. G. Hsieh, Global exponential stability of uncertian cellular neural networks with multiple time-varying delays via LMI approach, Chaos Solitons Fractals, 32 (2007), 1258–1267
  • View Article
  • Google Scholar


• [10] C. Ge, C. Hua, X. Guan, New delay-dependent stability criteria for neural networks with time-varying delay using delaydecomposition approach, IEEE Trans. Neural Netw. Learn. Syst., 25 (2014), 1378–1383
  • View Article
  • Google Scholar


• [11] Y. He, M.-D. Ji, C.-K. Zhang, M. Wu, Global exponential stability of neural netorks with time-varying delay based on free-matrix-based integral inequality, Neural Netw., 77 (2016), 80–86
  • View Article
  • Google Scholar


• [12] Y. He, G. Liu, D. Ress, M. Wu, Stability analysis for neural networks with timevarying interval delay, IEEE Trans. Neural Netw., 18 (2007), 1850–1854
  • View Article
  • Google Scholar


• [13] Y.-L. Huang, S.-H. Qiu, S.-Y. Ren, Finite-time synchronisation and passivity of coupled memristive neural networks, Internat. J. Control, 93 (2019), 2824–2837
  • View Article
  • MathSciNet
  • Google Scholar
  • MATH


• [14] M.-D. Ji, Y. He, M. Wu, C.-K. Zhang, New exponential stability criterion for neural networks with time-varying delay, In: proceeding of the 33rd Chinese control conference, IEEE, (2014), 6119–6123
  • View Article


• [15] M.-D. Ji, Y. He, M. Wu, C.-K. Zhang, Further results on exponential stability of neural networks with time-varying delay, Appl. Math. Comput., 256 (2015), 175–182
  • View Article
  • MathSciNet
  • Google Scholar
  • MATH


• [16] A. Klamnoi, N. Yotha, W. Weera, T. Botmart, Improved results on passivity analysis of neutral-type neural networks with time-varying delays, J. Res. Appl. Mech. Eng., 6 (2018), 71–81
  • View Article
  • Google Scholar


• [17] O. M. Kwon, J. H. Park, Exponential stability of uncertain dynamic systems including state delay, Appl. Math. Lett., 19 (2006), 901–907
  • View Article
  • MathSciNet
  • Google Scholar
  • MATH


• [18] O. M. Kwon, M. J. Park, Exponential stability analysis for uncertain neural networks with interval time-varying delays, Appl. Math. Comput., 212 (2009), 530–541
  • View Article
  • MathSciNet
  • Google Scholar
  • MATH


• [19] O. M. Kwon, J. H. Park, S. M. Lee, E. J. Cha, A new augmented Lyapunov-Krasovskii functional approach to exponential passivity for neural networks with time-varying delays, Appl. Math. Comput., 217 (2011), 10231–10238
  • View Article
  • MathSciNet
  • Google Scholar
  • MATH


• [20] O. M. Kwon, M. J. Park, J. H. Park, S. M. Lee, E. J. Cha, Analysis on robust H1 performance and stability for linear systems with interval time-varying state delays via some new augmented Lyapunov-Krasovskii functional, Appl. Math. Comput., 244 (2013), 108–122
  • View Article
  • MathSciNet
  • Google Scholar
  • MATH


• [21] J. Liang, Z. Wang, X. Liu, Robust passivity and passification of stochastic fuzzy time-delay systems, Inf. Sci., 180 (2010), 1725–1737
  • View Article
  • Google Scholar
  • MATH


• [22] D. Liberzon, Switching in Systems and Control, Birkh¨auser Boston, Boston, MA (2003)
  • View Article
  • MathSciNet
  • Google Scholar


• [23] W. Lin, C. I. Byrnes, Passivity and absolute stabilization of a class of discrete-time nonlinear systems, Automatica J. IFAC, 31 (1995), 263–267
  • View Article
  • MathSciNet
  • Google Scholar
  • MATH


• [24] R. Manivannan, R. Samidurai, J. Cao, A. Alsaedi, F. E. Alsaadi, Delay-dependent stability criteria for neutral-type neural networks with interval time-varying delay signals under the effects of leakage delay, Adv. Difference Equ., 2018 (2018), 25 pages
  • View Article
  • MathSciNet
  • Google Scholar
  • MATH


• [25] S. Mou, H. Gao, W. Qiang, K. Chen, New delay-dependent exponential stability for neural networks with time delays, IEEE Trans. Syst. Man. Cybern. B Cybern., 38 (2008), 571–576
  • View Article
  • Google Scholar


• [26] J. H. Park, Further note on global exponential stability of uncertain cellular neural networks with variable delays, Appl. Math. Comput., 188 (2007), 850–854
  • View Article
  • MathSciNet
  • Google Scholar
  • MATH


• [27] N. Promdee, K. Mukdasai, P. Junsawang, New exponential passivity analysis of integro-differential neural networks with time-varying delays, Thai J. Math., 18 (2020), 1677-1699
  • View Article
  • Google Scholar
  • MATH


• [28] N. Radhakrishnan, R. Kodeeswaran, R. Raja, C. Maharajan, A. Stephen, Global exponential stability analysis of anti-periodic of discontinuous BAM neural networks with time-varying delays, J. Phys.: Conf. Ser., 1850 (2021), 1–20
  • View Article
  • Google Scholar


• [29] G. Rajchakit, R. Sriraman, R. Samidurai, Dissipativity analysis of delayed stochastic generalized neural networks with Markovian jump parameters, Int. J. Nonlinear Sci. Numer. Simul., 23 (2022), 661–684
  • View Article
  • MathSciNet
  • Google Scholar
  • MATH


• [30] G. Rajchakit, R. Sriraman, C. P. Lim, P. Sam-Ang, P. Hammachukiattikul, Synchronization in finite-time analysis of clifford-valued neural networks with finite-time distributed delays, Mathematics, 9 (2021), 18 pages
  • View Article
  • Google Scholar


• [31] G. Rajchakit, R. Sriraman, C. P. Lim, B. Unyong, Existence, uniqueness and global stability of Clifford-valued neutraltype neural networks with time delays, Math. Comput. Simul., 201 (2022), 508–527
  • View Article
  • MathSciNet
  • Google Scholar
  • MATH


• [32] G. Rajchakit, P. Agarwal, S. Ramalingam, Stability analysis of neural networks, Springer, Singapore (2021)
  • View Article
  • MathSciNet
  • Google Scholar


• [33] G. Rajchakit, R. Sriraman, P. Vignesh, C. P. Lim, Impulsive effects on Clifford-valued neural networks with time-varying delays: an asymptotic stability analysis, Appl. Math. Comput., 407 (2021), 18 pages
  • View Article
  • MathSciNet
  • Google Scholar
  • MATH


• [34] R. Sakthivel, R. Anbuvithya, K. Mathiyalagan, P. Prakash, Combined H1 and passivity state estimation of memristive neural networks with random gain fluctuations, Neurocomputing, 168 (2015), 1111–1120
  • View Article
  • Google Scholar


• [35] M. Sathishkumar, R. Sakthivel, O. M. Kwon, B. Kaviarasan, Finitetime mixed H1 and passive filtering for Takagi– Sugeno fuzzy nonhomogeneous Markovian jump systems, Int. J. Syst. Sci., 48 (2016), 1416–1427
  • View Article
  • Google Scholar


• [36] S. Senthilraj, R. Raja, Q. Zhu, R. Samidurai, Z. Yao, Exponential passivity analysis of stochastic neural networks with leakage, distributed delays and Markovian jumping parameters, Neurocomputing, 175 (2016), 401–410
  • View Article
  • Google Scholar


• [37] S. Shanmugam, S. A. Muhammed, G. M. Lee, Finite-time extended dissipativity of delayed Takagi-Sugeno fuzzy neural networks using a free-matrix-based double integral inequality, Neural Comput. Appl., 32 (2020), 8517–8528
  • View Article
  • Google Scholar


• [38] P. Singkibud, P. Niamsup, K. Mukdasai, Improved results on delay-rage-dependent robust stability criteria of uncertain neutral systems with mixed interval time-varying delays, IAENG Int. J. Appl. Math., 47 (2017), 209–222
  • View Article
  • Google Scholar


• [39] P. Singkibud, N. Yotha, K. Mukdasai, New delay-dependent exponential passivity analysis of neutral-type neural networks with discrete and distributed time-varying delays, Thai J. Math., 18 (2020), 879–898
  • View Article
  • Google Scholar
  • MATH


• [40] A. Stephen, R. Karthikeyan, C. Sowmiya, R. Raja, R. P. Agarwal, Sampled-data controller scheme for multi-agent systems and its Application to circuit network, Neural Netw., 170 (2024), 506–520
  • View Article
  • Google Scholar
  • MATH


• [41] A. Stephen, R. Raja, X. Bai, J. Alzabut, R. Swaminathan, G. Rajchakit, Asymptotic pinning synchronization of nonlinear multi-agent systems: Its application to tunnel diode circuit, Nonlinear Anal. Hybrid Syst., 49 (2023), 17 pages
  • View Article
  • MathSciNet
  • Google Scholar
  • MATH


• [42] J. Sun, G. P. Liu, J. Chen, D. Rees, Improved delay-range-dependent stability criteria for linear systems with time-varying delays, Automatica J. IFAC, 46 (2010), 466–470
  • View Article
  • MathSciNet
  • Google Scholar
  • MATH


• [43] M. V. Thuan, H. Trinh, L. V. Hien, New inequality-based approach to passivity analysis of neural networks with interval time-varying delay, Neurocomputing, 194 (2016), 301–307
  • View Article
  • Google Scholar


• [44] J.-L. Wang, X.-X. Zhang, H.-N. Wu, T. Huang, Q. Wang, Finitetime passivity and synchronization of coupled reaction– diffusion neural networks with multiple weights, IEEE Trans. Cybern, 49 (2018), 3385–3397
  • View Article
  • Google Scholar


• [45] M. Wu, F. Liu, P. Shi, Y. He, R. Yokoyama, Exponential stability analysis for neural networks with time-varying delay, IEEE Trans. Syst., Man., Cybern., B Cybern., 38 (2008), 1152–1156
  • View Article
  • Google Scholar


• [46] Z.-G. Wu, J. H. Park, H. Su, J. Chu, New results on exponential passivity of neural networks with time-varying delays, Nonlinear Anal. Real World Appl., 13 (2012), 1593–1599
  • View Article
  • MathSciNet
  • Google Scholar
  • MATH


• [47] A. Wu, Z. Zeng, Exponential passivity of memristive neural networks with time delays, Neural Netw., 49 (2014), 11–18
  • View Article
  • Google Scholar


• [48] N. Yotha, T. Botmart, K. Mukdasai, W. Weera, Improved delay-dependent approach to passivity analysis for uncertain neural networks with discrete interval and distributed time-varying delays, Vietnam J. Math., 45 (2017), 721–736
  • View Article
  • MathSciNet
  • Google Scholar
  • MATH


• [49] H.-B. Zeng, Y. He, M. Wu, C.-F. Zhang, Complete delay-decomposing approch to asymptotic stability for neural networks with time-varying delays, IEEE Trans. Neural Netw., 22 (2011), 806–812
  • View Article
  • Google Scholar


• [50] H. Zhang, F. Yang, X. Liu, Q. Zhang, Stability analysis for neural networks with time-varying delay based in quadratic convex combination, IEEE Trans. Neural Netw. Learn. Syst., 24 (2013), 513–521
  • View Article
  • Google Scholar


• [51] J. Zhao, D. J. Hill, Passivity and stability of switched systems: A multiple storage function method, Syst. Control Lett., 57 (2008), 158–164
  • View Article
  • MathSciNet
  • Google Scholar
  • MATH


• [52] S. Zhu, Y. Shen, G. Chen, Exponential passivity of neural networks with time-varying delay and uncertainty, Phys. Lett. A, 375 (2010), 136–142
  • View Article
  • MathSciNet
  • Google Scholar
  • MATH