Design of non-fragile state estimators for discrete time-delayed neural networks with parameter uncertainties

Abstract

This paper is concerned with the problem of designing a non-fragile state estimator for a class of uncertain discrete-time neural networks with time-delays. The norm-bounded parameter uncertainties enter into all the system matrices, and the network output is of a general type that contains both linear and nonlinear parts. The additive variation of the estimator gain is taken into account that reflects the possible implementation error of the neuron state estimator. The aim of the addressed problem is to design a state estimator such that the estimation performance is non-fragile against the gain variations and also robust against the parameter uncertainties. Sufficient conditions are presented to guarantee the existence of the desired non-fragile state estimators by using the Lyapunov stability theory and the explicit expression of the desired estimators is given in terms of the solution to a linear matrix inequality. Finally, a numerical example is given to demonstrate the effectiveness of the proposed design approach.

Application of artificial neural network in the diagnostic system of osteoporosis

“…In future work, the advanced approaches in [40][41][42][43][44][45] can be combined for further research. Chao Ye graduated from School of Automation in Harbin Engineering University.…”

Stability analysis for discrete time-delay systems based on new finite-sum inequalities

“…For example, since a large number of practical control systems are implemented over a communication 215 network, which may lead to network-induced time delays, these new methods will be very important in the analysis and synthesis of networked control systems [5,17,28]. Moreover, our methods can also be applied to other related areas, such as genetic regulatory networks [18,19] and time-delayed neural networks [27]. …”

Distributed Event-Based Set-Membership Filtering for a Class of Nonlinear Systems With Sensor Saturations Over Sensor Networks

“…These phenomena are customarily referred to as the incomplete information that has attracted much research interest in developing filtering schemes [1], [8]- [10], [16]- [18], [22], [23], [25], [32], [37], [39], [41], [43], [46]. However, when it comes to the event-based distributed filtering problems with incomplete information, the corresponding results have been very few owing mainly to the lack of appropriate techniques for coping with 1) the complicated node coupling according to the topological information and 2) the demanding triggering mechanism accounting for the limited capability.…”