Generalized dissipativity state estimation of delayed neural networks under a novel event-triggered strategy
DOI:
https://doi.org/10.54097/ygykwv31Keywords:
Delayed neural networks, Adaptive event-triggered, Generalized dissipativity state estimation, StabilityAbstract
This paper investigates the generalized dissipativity state estimation problem for delayed neural networks (DNNs) under a novel event-triggered strategy. Unlike traditional Lyapunov-Krasovskii Functionals (LKFs) which impose positive definiteness constraints on matrices, this paper constructs a novel delay-dependent LKF. The positive definiteness constraint on the LKF matrix is relaxed via a quadratic inequality, which offers more flexibility in the functional construction. Meanwhile, to guarantee satisfactory estimator performance under limited communication resources, a novel adaptive event-triggered strategy (AETS) with memory-based triggering logic is proposed. Unlike existing event-triggered (ET) strategies, the proposed AETS can dynamically adjust triggering parameters and further reduce communication frequency. Accordingly, two sufficient criteria are derived via linear matrix inequalities (LMIs) to guarantee the dissipativity of the estimation error system. Finally, numerical examples are provided to demonstrate the superiority of the proposed methods.
Downloads
References
[1] Wang, J., Zhang, H., Fu, J., Liang, H., & Meng, Q. (2023). Dissipativity-based consensus tracking control of nonlinear multiagent systems with generally uncertain Markovian switching topologies and event-triggered strategy. IEEE Transactions on Cybernetics, 53(8), 4763-4778. https://doi.org/10.1109/TCYB.2022.3172096
[2] Zhu, X., Xia, Y., Wang, J., & Hu, X. (2024). Finite-time extended dissipative fault estimate for discrete-time Markov jumping neural networks based on an event-triggered approach. Circuits, Systems, and Signal Processing, 43(11), 6931-6952. https://doi.org/10.1007/s00034-024-02778-5
[3] Tian, Y., Wang, Y., & Ren, J. (2022). Event-triggered H∞ state estimation for neural networks with time-varying delays: The continuous-time case. International Journal of Robust and Nonlinear Control, 32(11), 6282-6292. https://doi.org/10.1002/rnc.6098
[4] Liu, T., Chen, Y.-Y., & Ge, X. (2026). Congealed neural network design for uncertain nonlinear spatiotemporal control systems. Automatica, 183, 112636. https://doi.org/10.1016/j.automatica.2025.112636
[5] Raj, R., & Kos, A. (2025). An extensive study of convolutional neural networks: Applications in computer vision for improved robotics perceptions. Sensors, 25(4), 1033. https://doi.org/10.3390/s25041033
[6] Fu, K., & Dang, X. (2024). Light-weight convolutional neural networks for generative robotic grasping. IEEE Transactions on Industrial Informatics, 20(4), 6696-6697. https://doi.org/10.1109/TII.2023.3336905
[7] Wang, Z. D., Ho, D. W. C., & Liu, X. H. (2005). State estimation for delayed neural networks. IEEE Transactions on Neural Networks, 16(1), 279-284. https://doi.org/10.1109/TNN.2004.841813
[8] Gao, Y., Zhang, Z.-Y., Liu, X.-Z., & Wu, K.-N. (2026). State estimation for stochastic delayed neural networks with diffusion terms: A two-step estimation method. Neural Networks, 196, 108339. https://doi.org/10.1016/j.neunet.2025.108339
[9] Deng, J., Li, H.-L., Hu, C., Jiang, H., & Cao, J. (2025). State estimation of discrete-time fractional-order nonautonomous neural networks with time delays. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 55(5), 3707-3719. https://doi.org/10.1109/TSMC.2025.3535929
[10] Willems, J. C. (1972). Dissipative dynamical systems part I: General theory. Archive for Rational Mechanics and Analysis, 45(5), 321-351. https://doi.org/10.1007/BF00276493
[11] Chen, J., Zhang, X.-M., Park, J. H., & Xu, S. (2022). Improved stability criteria for delayed neural networks using a quadratic function negative-definiteness approach. IEEE Transactions on Neural Networks and Learning Systems, 33(3), 1348-1354. https://doi.org/10.1109/TNNLS.2020.3042307
[12] Zhou, X.-Z., An, J. Q., He, Y., & Shen, J. H. (2024). Improved stability criteria for delayed neural networks via time-varying free-weighting matrices and S-procedure. IEEE Transactions on Neural Networks and Learning Systems, 35(11), 16945-16951. https://doi.org/10.1109/TNNLS.2023.3289208
[13] Long, F., Zhang, C.-K., Shen, Y., Mei, Q., & Chen, Q. (2025). Stability analysis of delayed neural networks via novel delay-dependent LKF and integral inequality. ISA Transactions, 165, 165-173. https://doi.org/10.1016/j.isatra.2025.03.032
[14] Pan, Y., & Yang, G. H. (2019). Event-based output tracking control for fuzzy networked control systems with network-induced delays. Applied Mathematics and Computation, 346, 513-530. https://doi.org/10.1016/j.amc.2018.10.038
[15] Long, F., Zhang, C.-K., He, Y., Wang, Q.-G., & Wu, M. (2022). Stability analysis for delayed neural networks via a novel negative-definiteness determination method. IEEE Transactions on Cybernetics, 52(6), 5356-5366. https://doi.org/10.1109/TCYB.2020.3032825
[16] Kong, G., & Guo, L. (2026). Extended dissipativity analysis for delayed Markovian jump neural networks via delay-function-based Lyapunov functional. Neural Networks, 196, 108321. https://doi.org/10.1016/j.neunet.2025.108321
[17] Azikiwe, H., & Bello, A. (2020a). Title of the cited article. Journal Title, Volume (Issue), Firstpage-Lastpage.
[18] Liu, Y., Shen, B., & Shu, H. (2020). Finite-time resilient H∞ state estimation for discrete-time delayed neural networks under dynamic event-triggered mechanism. Neural Networks, 121, 356-365. https://doi.org/10.1016/j.neunet.2019.09.021
[19] Hu, J., Tan, G., & Liu, L. (2024). A new result on H∞ state estimation for delayed neural networks based on an extended reciprocally convex inequality. IEEE Transactions on Circuits and Systems II: Express Briefs, 71(3), 1181-1185. https://doi.org/10.1109/TCSII.2023.3332801
[20] Wu, L. G., Gao, Y. B., Liu, J. X., & Li, H. Y. (2017). Event-triggered sliding mode control of stochastic systems via output feedback. Automatica, 82, 79-92.
https://doi.org/10.1016/j.automatica.2017.04.024
[21] Zheng, C.-D., Zhang, H., & Wang, Z. (2010). An augmented LKF approach involving derivative information of both state and delay. IEEE Transactions on Neural Networks, 21(7), 1100-1109. https://doi.org/10.1109/TNN.2010.2048565
[22] Chen, Y., Zeng, H.-B., & Li, Y. (2024). Stability analysis of linear delayed systems based on an allowable delay set partitioning approach. Automatica, 163, 111603. https://doi.org/10.1016/j.automatica.2024.111603
[23] Wang, Y., Liu, H., & Li, X. (2021). A novel method for stability analysis of time-varying delay systems. IEEE Transactions on Automatic Control, 66(3), 1422-1428. https://doi.org/10.1109/TAC.2020.3003831
[24] Lu, Y., Li, J., Li, S., & Huang, C. (2024). A fine-grained packet loss tolerance transmission algorithm for communication optimization in distributed deep learning. IEEE Transactions on Network and Service Management, 21(6), 6112-6125. https://doi.org/10.1109/TNSM.2024.3461728
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Computing and Electronic Information Management
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
