Dynamic event-triggered mechanism-based design of H ∞ reliable state estimator for discrete-time neural networks
Siyu Guo, Yuqiang Luo, Kaiqun Zhu, Hong Sheng Lin · International Journal of Systems Science · 2025
In this paper, we investigate the reliable H∞ state estimation problem for discrete-time neural networks, where the activation function is assumed to satisfy a prescribed nonlinearity condition. To alleviate communication burden and save transmission energy, a dynamic event-triggered mechanism (DETM) is employed in the communication procedure. Considering the possible failures experienced by the data receiving register in engineering practice, a failure matrix is introduced to characterise the real received measurements. Initially, based on the obtained measurements, we design a full-order state estimator for the target neural networks. Through introducing new vectors of error and augmentation, the state estimation error dynamics is established. Then, by applying Lyapunov stability theory, matrix theory, nonlinearity analysis, and the relevant lemmas, both the asymptotical stability and the H∞ performance of the augmented error dynamics are thoroughly analysed, and the corresponding criteria are derived. Next, the target estimator parameter is determined based on the analysis of stability and disturbance attenuation. The effectiveness of the proposed estimation approach is demonstrated through a numerical example.