Energy-to-Peak State Estimation for Switched Neutral-Type Neural Networks With Sector Condition via Sampled-Data Information

• Published in: IEEE transaction on neural networks and learning systems Vol. 32; no. 3; pp. 1339 - 1350
• Main Authors: Sang, Hong, Zhao, Jun
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.03.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Asynchronous phenomena; Biological neural networks; Cellular communication; Controllers; Delays; Energy; energy-to-peak state estimation; Neural networks; Perturbation; Perturbation methods; piecewise time-dependent Lyapunov–Krasovskii functional; sampled data; Sampling; State estimation; Subsystems; switched neutral neural networks; Switches; Switching
• ISSN: 2162-237X; 2162-2388
• DOI: 10.1109/TNNLS.2020.2984629

In this article, the energy-to-peak state estimation problem is investigated for a class of switched neutral neural networks subject to the external perturbations with bounded energy. Both the values of the measurement outputs and switching signal of the subsystems are only available for the controllers at the discrete sampling instants. Unlike the results for nonswitched neural networks, the coexistence of the switching and sampling actions directly causes the asynchronous phenomena between the indexes of subsystems and their corresponding controllers. To address this situation, the piecewise time-dependent Lyapunov-Krasovskii functional and slow switching mechanism are introduced. Under the developed theorem conditions, we prove that the designed state estimator exponentially tracks the true value of the neural state with the accessible sampled-data information. Also, the influence of the exogenous perturbations on the peak value of the estimation error is constrained at a prescribed level. Finally, a neutral cellular neural network with switching parameters is employed to substantiate the effectiveness and applicability of the theoretical results.