H∞ Filtering for Neural Networks with Time-Varying Delays and Quantized Outputs

DOI: https://doi.org/10.62517/jes.202602242

Author(s)

Jing Han, Zi Wang, Ruoxian Wang

Affiliation(s)

School of Electronical Information Engineering, Wanjiang University of Technology, Ma’anshan, Anhui, China

Abstract

Based on a neural network model, the problem of H∞ filtering for systems with time-varying delays and quantized outputs was studied. The main objective is to develop a quantized H∞ filter that ensures, on the one hand, that the filtering error system (FES) exhibits an asymptotically stable state in the absence of external disturbances, and on the other hand, that the system has H∞ performance with zero initial conditions. The first step is to combine appropriate Lyapunov Krasovskii functionals with some inequality techniques, and through differentiation reasoning and other methods, provide sufficient criteria for the error system to achieve H∞ performance. The second step is to propose a design scheme for the required H∞ filter using several decoupling methods and a series of proof processes. In the final step, the effectiveness of the designed H∞ filter method was confirmed through numerical simulation examples and simulation images. In summary, this work provides a systematic and computationally manageable method for designing quantized H∞ filters for time-varying delay neural networks.

Keywords

Neural Network Model; Time-Varying Delay; Quantitative Output; H∞ Performance; Lyapunov Krasovskii Functionals

References

[1]Hopfield J J. Neural networks and physical systems with emergent collective computational abilities. Proceeding of the National Academy of Science, 1982, 79(8): 2554-2558. [2]Yan Z, Guo T, Zhao A, et al. Reliable exponential H∞ filtering for a class of switched reaction-diffusion neural networks. Applied Mathematics and Computation, 2022, 414: 126661. [3]Tai W, Xu D, Guo T, et al. Exponential passive filter design for switched neural networks with time-delay and reaction-diffusion terms. Modern Physics Letters B, 2021, 35(25): 2150434. [4]Lee Y J, Pae D S, Choi H D, et al. Sampled-data L 2-L∞ filter-based fuzzy control for active suspensions. IEEE Access, 2023, 11: 21068-21080. [5]Zhou Y, Chang X H, Park J H. Quantized asynchronous filtering for fuzzy semi-Markov switching systems with multiple stochastic delays under deception attacks. IEEE Transactions on Fuzzy Systems, 2024, 32(4): 2378-2389. [6]Cai L J, Chang X H. Finite‐time mixed H∞ and passive filtering for nonlinear singular systems under fading channels. International Journal of Robust and Nonlinear Control, 2024, 34(12): 7891-7911. [7]Liu C, Liu G, Wang W, et al. Quantized H∞ Filtering for Nonlinear Systems via Lyapunov Functions//2025 China Automation Congress (CAC). IEEE, 2025: 1412-1417. [8]Han J, Xia Y, Zhang L, et al. H∞ filtering of a constant time delay neural networks with quantized output//2023 3rd International Conference on Intelligent Power and Systems (ICIPS). IEEE, 2023: 598-602. [9]Meng X, Kao Y, Karimi H R, et al. Global Mittag-Leffler stability for fractional-order coupled systems on network without strong connectedness. Science China Information Sciences, 2020, 63(3): 132201. [10]Liu Y, Fang F, Park J H, et al. Asynchronous output feedback dissipative control of Markovian jump systems with input time delay and quantized measurements. Nonlinear Analysis: Hybrid Systems, 2019, 31: 109-122. [11]Zames G. Feedback and optimal sensitivity: Model reference transformations, multiplicative seminorms, and approximate inverses. IEEE Transactions on automatic control, 1981, 26(2): 301-320. [12]Seuret A, Gouaisbaut F. Hierarchy of LMI conditions for the stability analysis of time-delay systems. Systems & Control Letters, 2015, 81: 1-7. [13]Zhou K, Khargonekar P P. Robust stabilization of linear systems with norm-bounded time-varying uncertainty. Systems & Control Letters, 1988, 10(1): 17-20. [14]Park P G, Ko J W, Jeong C. Reciprocally convex approach to stability of systems with time-varying delays. Automatica, 2011, 47(1): 235-238.