Finite-time stabilization of memristor-based inertial neural networks with time-varying delays combined with interval matrix method

This paper investigates the finite-time stability problem of memristor-based inertial neural networks (MINNs) with time-varying delays in association with the interval matrix approach. In the light of differential inclusion and set-valued mapping, the delayed MINNs are converted to a category of systems with uncertain terms by means of convex combination transformations of matrices to deal with the problem of the parameter mismatch of MINNs. Afterwards, the second-order differential systems are simplified to the ordinary first-order differential systems utilizing dimension reduction. Then, two types of delayed feedback controllers are designed to ensure that MINNs can achieve finite time stabilization, which handles time-varying delays in different ways. Meanwhile, the finite-time stabilization criterion can be deduced by linear matrix inequalities (LMIs). Therefore, the upper bound on the settling time is estimated as one of the indicators to measure the stability effect. Finally, the accuracy of the theoretical results and the validity of the proposed method are verified by two examples. (C) 2021 Elsevier B.V. All rights reserved.

Automated summary

This paper investigates the finite-time stability problem of memristor-based inertial neural networks (MINNs) with time-varying delays using the interval matrix approach. The study converts MINNs to systems with uncertain terms and employs dimension reduction to simplify the differential systems. Two types of delayed feedback controllers are designed to achieve finite time stabilization, with the stability criterion deduced by linear matrix inequalities. The theoretical results and proposed method are validated through two examples.