Passivity-Based State Estimation of Markov Jump Singularly Perturbed Neural Networks Subject to Sensor Nonlinearity and Partially Known Transition Rates

• Published in: Neural processing letters Vol. 55; no. 9; pp. 12205 - 12222
• Main Authors: Wang, Ya-Nan, Li, Feng, Su, Lei, Xia, Rongsheng
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.12.2023; Springer Nature B.V
• Subjects: Artificial Intelligence; Complex Systems; Computational Intelligence; Computer Science; Liapunov functions; Neural networks; Neurons; Nonlinearity; Parameter estimation; Sensors; Singular perturbation; State estimation; Singularly perturbed systems; Partial information; Markov jump neural networks; State estimation
• ISSN: 1370-4621; 1573-773X
• DOI: 10.1007/s11063-023-11416-9

In this paper, the passivity-based state estimation problem is investigated for Markov jump singularly perturbed neural networks, in which the partially known transition rate matrix and the nonlinear characteristics of sensors are considered simultaneously. By using a new inequality, a novel perturbed parameter dependent Lyapunov function is constructed for Markov jump singularly perturbed neural networks. Based on those, some sufficient conditions are established to guarantee the stochastically mean-square stable for the considered system with the property of passivity. Besides, a less conservativeness state estimator design method is established for Markov jump singularly perturbed neural networks subject to sensor nonlinearity and partially known transition rates. At last, a numerical example is presented to demonstrate the validity of the obtained results.