Proportional–integral-type estimator design for delayed recurrent neural networks under encoding–decoding mechanism
Authors:
- 26 April 2022
- journal article
- research article
- Published by Taylor & Francis in International Journal of Systems Science
- Vol. 53 (13) , 2729-2741
Abstract
In this paper, the proportional–integral-type estimator design problem is studied for recurrent neural networks under the encoding–decoding communication mechanism. In the process of the measurement data transmission, an encoding–decoding mechanism is introduced to improve the security of the network by encrypting the measurement data. The purpose of this paper is to design a proportional–integral-type estimation algorithm such that the estimation error dynamics is exponentially ultimately bounded in mean square. First, a sufficient condition is obtained for the existence of the desired estimator. Then, the parameters of the estimator are obtained by solving certain matrix inequality. Finally, a simulation example is given to verify the effectiveness of the designed estimation algorithm.Keywords
Funding Information
- National Natural Science Foundation of China (U21A2019, 61933007, 61873058, 62103095)
- Natural Science Foundation of Heilongjiang Province of China (LH2021F005)
- Fundamental Research Funds for Provincial Undergraduate Universities of Heilongjiang Province of China (2018YDL-01)
- Guiding Science and Technology Plan Project of Daqing of China (zd-2019-06)
- Alexander von Humboldt Foundation of Germany
This publication has 47 references indexed in Scilit:
- A Threshold-Parameter-Dependent Approach to Designing Distributed Event-Triggered $H_{\infty}$ Consensus Filters Over Sensor NetworksIEEE Transactions on Cybernetics, 2018
- A proportional integral estimator-based clock synchronization protocol for wireless sensor networksISA Transactions, 2017
- Event-based filtering for time-varying nonlinear systems subject to multiple missing measurements with uncertain missing probabilitiesInformation Fusion, 2017
- Neuronal State Estimation for Neural Networks With Two Additive Time-Varying Delay ComponentsIEEE Transactions on Cybernetics, 2017
- Synchronization of Memristor-Based Coupling Recurrent Neural Networks With Time-Varying Delays and ImpulsesIEEE Transactions on Neural Networks and Learning Systems, 2015
- Further Result on Guaranteed $H_\infty $ Performance State Estimation of Delayed Static Neural NetworksIEEE Transactions on Neural Networks and Learning Systems, 2014
- Distributed Coordination of Multi-Agent Systems With Quantized-Observer Based Encoding-DecodingIEEE Transactions on Automatic Control, 2012
- Detectability and Output Feedback Stabilizability of Nonlinear Networked Control SystemsIEEE Transactions on Automatic Control, 2007
- Global exponential stability of generalized recurrent neural networks with discrete and distributed delaysNeural Networks, 2006
- Linear Matrix Inequalities in System and Control Theory1994