Recent Advances in Stability Analysis State Estimation for Time-Delay Neural Networks
DOI:
https://doi.org/10.54097/cx1ehn07Keywords:
Time-delay neural networks, state estimation, stability analysis, Lyapunov-Krasovskii functional, linear matrix inequality, reduced conservatismAbstract
This paper reviews recent advances in stability analysis and state estimation for time-delay neural networks (TDNNs). TDNNs are widely applied in various fields, but inherent time delays degrade their performance and induce instability, making the two topics core research focuses. We systematically summarize mainstream stability analysis methods, focusing on the Lyapunov-Krasovskii (L-K) functional method, its improved construction forms, and auxiliary tools like integral and reciprocally convex inequalities. We also synthesize state estimation research progress, emphasizing the core role of estimation error system stability. Finally, we point out existing key problems and prospect future trends, providing a reference for subsequent research.
Downloads
References
[1] Cohen M A, Grossberg S. Absolute stability of global pattern formation and parallel memory storage by competitive neural networks [J]. IEEE Transactions on Systems, Man, and Cybernetics, 1983, 5: 815–826.
[2] Giannopoulos A, Aider J L. Prediction of the dynamics of a backward-facing step flow using focused time-delay neural networks and particle image velocimetry datasets [J]. International Journal of Heat and Fluid Flow, 2020, 82: 108533.
[3] Zhang L M. Models and Applications of Artificial Neural Networks [M]. Shanghai: Fudan University Press, 1993.
[4] Elowitz M B, Leibler S. A synthetic oscillatory network of transcriptional regulators [J]. Nature, 2000, 403(6767): 335-338.
[5] Michel A N, Gray D. Analysis and synthesis of neural networks with lower block triangular interconnecting structure [J]. IEEE Transactions on Circuits and Systems, 1990, 37(10): 1267–1283.
[6] McCulloch W S, Pitts W. A logical calculus of the ideas immanent in nervous activity [J]. The Bulletin of Mathematical Biophysics, 1943, 5(4): 115–133.
[7] Kohonen T. Self-Organizing Maps [M]. Berlin: Springer, 1995.
[8] Grossberg S. Adaptive pattern classification and universal recoding, I: Parallel development and coding of neural feature detectors [J]. Biological Cybernetics, 1976, 23(3): 121-134.
[9] Ritter H, Schulten K. On the stationary state of Kohonen's self-organizing sensory mapping [J]. Biological Cybernetics, 1986, 54(1): 99-106.
[10] Carpenter G A, Grossberg S, Reynolds J H. ARTMAP: Supervised real-time learning and classification of nonstationary data by a self-organizing neural network [J]. Neural Networks, 1991, 4(5): 565-588.
[11] Hopfield J J. Neural networks and physical systems with emergent collective computational abilities [J]. Proceedings of the National Academy of Sciences, 1982, 79(8): 2554–2558.
[12] Hopfield J J. Neurons with graded response have collective computational properties like those of two-state neurons [J]. Proceedings of the National Academy of Sciences, 1984, 81(10): 3088–3092.
[13] Thuan M V, Hien L V, Phat V N. Exponential stabilization of non-autonomous delayed neural networks via Riccati equations [J]. Applied Mathematics and Computation, 2015, 257: 345-358.
[14] Mahmoud M S. New exponentially convergent state estimation method for delayed neural networks [J]. Neurocomputing, 2009, 72(10-12): 2396-2403.
[15] Song Z, Xu J. Stability switches and double Hopf bifurcation in a two-neural network system with multiple delays [J]. Cognitive Neurodynamics, 2013, 7(4): 337-348.
[16] Bengio Y, Simard P, Frasconi P. Learning long-term dependencies with gradient descent is difficult [J]. IEEE Transactions on Neural Networks, 1994, 5(2): 157-166.
[17] He Y, Wang Q G, Wu M, Lin C. Delay-dependent state estimation for delayed neural networks [J]. IEEE Transactions on Neural Networks, 2006, 17(4): 973-979.
[18] Mou S S, Gao H J, Qiang W Y, Fei Z Y. State estimation for discrete-time neural networks with time-varying delays [J]. Neurocomputing, 2008, 71(13-15): 2907-2915.
[19] Zheng C D, Ma M M, Wang Z S. Less conservative results of state estimation for delayed neural networks with fewer LMI variables [J]. Neurocomputing, 2010, 73(16-18): 3050-3057.
[20] Zhang L, Liu H P, Wang J A. State estimator design for neural networks with mixed time-varying delays [J]. Chinese Journal of Engineering, 2012, 34(7): 866-872.
[21] Yang F, Dong H L, Wang Z D, et al. A new approach to non-fragile state estimation for continuous neural networks with time-delays [J]. Neurocomputing, 2016, 191: 223-231.
[22] Ali M S, Gunasekaran N, Cao J D. Sampled-data state estimation for neural networks with additive time-varying delays [J]. Acta Mathematica Scientia, 2019, 39(5): 1417-1433.
[23] Zhou F Y. Stability analysis of generalized cellular neural networks with time delays under noise disturbance [J]. Journal of Engineering Mathematics, 2011, 28(5): 677-684.
[24] Zheng F J. State Estimation for Switched Neural Networks with Time Delays [D]. Jinan: Shandong Normal University, 2023.
[25] Liu J L, Tang J, Fei S M. Event-triggered and quantization-based state estimation for delayed neural network systems [J]. Science China Information Sciences, 2016, 46(12): 1727-1744.
[26] Qiu S B, Liu X G, Shu Y J. New approach to state estimator for discrete-time BAM neural networks with time-varying delay [J]. Advances in Difference Equations, 2015, 2015: 272.
[27] Liu Y, Wang Z, Liu X. State estimation for delayed neural networks [J]. IEEE Transactions on Neural Networks, 2005, 16(1): 279-284.
[28] Zhang B, Han Q L, Yu X. New results on state estimation for neural networks with time-varying delays [J]. Neurocomputing, 2008, 71(10-12): 2021-2029.
[29] Shen H, Wang Z, Shu H, et al. State estimation for delayed neural networks with Markovian jumping parameters [J]. IEEE Transactions on Neural Networks, 2009, 20(1): 169-174.
[30] Li X, Wu M, She J H, et al. Less conservative state estimation for delayed static neural networks via a novel Lyapunov-Krasovskii functional with negative definite terms [J]. Neurocomputing, 2020, 386: 111-120.
[31] Wu Z G, Shi P, Su H, et al. Improved state estimation for neural networks with mixed time-varying delays via delay-product-type functional approach [J]. IEEE Transactions on Cybernetics, 2021, 51(2): 882-892.
[32] Zhang X M, Han Q L, Seuret A, et al. A novel Lyapunov-Krasovskii functional approach to stability analysis of neural networks with time-varying delays [J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(1): 359-369.
[33] Grimble M. A new approach to robust filtering for uncertain discrete-time state-delayed systems [J]. IEEE Transactions on Signal Processing, 2005, 53(8): 3183-3192.
[34] Yang F, Li S, Shi Y, et al. State estimation for time-delay neural networks with applications to intelligent transportation systems [J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(10): 4201-4210.
[35] Chen Y, Liu Y, Tong C. State estimation for memristive fuzzy neural networks with time-varying delays: An adaptive event-triggered approach [J]. IEEE Transactions on Fuzzy Systems, 2023, 31(7): 2345-2355.
[36] Grimble M. Polynomial systems approach to optimal linear filtering and prediction [J]. International Journal of Control, 1985, 41(6): 1545-1564.
[37] Cao J D, Wang J. Global asymptotic stability of a general class of recurrent neural networks with time-varying delays [J]. IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications, 2005, 52(1): 41-52.
[38] Zhang H, Han Q L. Stability analysis of linear systems with time-varying delays via the delay-partitioning approach [J]. Automatica, 2009, 45(6): 1407-1415.
[39] He Y, Wu M, She J H, et al. Delay-dependent robust stability criteria for uncertain neutral systems with mixed delays [J]. Systems & Control Letters, 2004, 51(1): 57-65.
[40] Gu K, Kharitonov V L, Chen J. Stability of Time-Delay Systems [M]. Boston: Birkhäuser, 2003.
[41] Stépán G. Retarded Dynamical Systems: Stability and Characteristic Functions [M]. London: Longman Scientific & Technical, 1989.
[42] Seuret A, Gouaisbaut F. A novel Lyapunov-Krasovskii functional for stability of linear time-delay systems [J]. Automatica, 2013, 49(10): 3008-3014.
[43] Zhang X M, Han Q L. Delay-product-type Lyapunov-Krasovskii functionals for stability analysis of linear time-delay systems [J]. IEEE Transactions on Automatic Control, 2017, 62(7): 3440-3447.
[44] He Y, Wang Q G, Lin C, et al. Delay-dependent stability criteria for linear systems with time-varying delays [J]. Automatica, 2004, 40(8): 1447-1455.
[45] Zeng H B, Zhu Z J, Xiao S P, Zhang X M. A switched system model for exponential stability and dissipativity of delayed neural networks [J]. IEEE Transactions on Neural Networks and Learning Systems, 2025, 36(11): 19708-19717.
[46] Kim J H. Further improvement of Jensen inequality and application to stability of time-delayed systems [J]. Automatica, 2016, 64: 121–125.
[47] Park P G. A delay-dependent stability criterion for systems with time-varying delays [J]. Automatica, 1999, 35(11): 1835-1838.
[48] Moon Y S, Park P G, Kwon W H, et al. Delay-dependent robust stability criteria for uncertain systems with state delay [J]. International Journal of Control, 2001, 74(14): 1447-1455.
[49] Seuret A, Gouaisbaut F. Wirtinger-based integral inequality: Application to time-delay systems [J]. Automatica, 2013, 49(9): 2860-2866.
[50] Seuret A, Gouaisbaut F. Wirtinger-based summation inequality for discrete-time systems with time-varying delays [J]. Systems & Control Letters, 2014, 63: 102-108.
[51] Zhang X M, Han Q L. Bessel-Legendre inequality and its application to stability analysis of time-delay systems [J]. IEEE Transactions on Automatic Control, 2016, 61(10): 3213-3218.
[52] Shen Y, Wang Z, Shu H, et al. Auxiliary-function-based integral inequalities for stability analysis of time-delay systems [J]. IEEE Transactions on Automatic Control, 2015, 60(10): 2726-2730.
[53] Zeng H B, He Y, Wu M, et al. Free-matrix-based integral inequality for stability analysis of systems with time-varying delays [J]. IEEE Transactions on Automatic Control, 2014, 59(10): 2884-2889.
[54] Zhang X M, Han Q L. Wirtinger-based double integral inequality for stability analysis of linear time-delay systems [J]. Automatica, 2015, 51: 286-294.
[55] Park P G, Ko J W, Jeong C. Reciprocally convex approach to stability of systems with time-varying delays [J]. Automatica, 2011, 47(1): 235-238.
[56] Seuret A, Gouaisbaut F. Allowable delay sets for the stability analysis of linear time-varying delay systems using a delay-dependent reciprocally convex lemma [C]//Proceedings of the IFAC World Congress. Toulouse, France, 2017: 1297-1302.
[57] Zhang C K, He Y, Liang J, Wu M, Wang Q G. An extended reciprocally convex matrix inequality for stability analysis of systems with time-varying delay [J]. Automatica, 2017, 85: 481-485.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 International Journal of Advanced Engineering and Technology Research
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
