New results on robust finite-time boundedness of uncertain switched neural networks with time-varying delays

Abstract This paper investigates the finite-time boundedness (FTB) problem for a class of uncertain switched neural networks with time-varying delays. By exploring the mode-dependent properties of each subsystem, all the subsystems could be categorized into stable and unstable ones under the Lyapunov-like function framework. The sufficient conditions and a set of unified switching signals with average dwell time (ADT) are first derived with a known limit to the total activation time ratio between unstable and stable subsystems. Then, the obtained results are extended to a new switching approach with mode-dependent average dwell time (MDADT). Compared with general results, our proposed approach distinguishes the stable and unstable subsystems rather than viewing all subsystems as being unstable, thus getting less conservative switching criteria. Finally, a numerical example is provided to show the validity and the advantages of the finding techniques.

[1]  Francesco Amato,et al.  Finite-time control of discrete-time linear systems , 2005, IEEE Transactions on Automatic Control.

[2]  Jun Wang,et al.  Almost Sure Exponential Stability of Recurrent Neural Networks With Markovian Switching , 2009, IEEE Transactions on Neural Networks.

[3]  Jun Wang,et al.  A general projection neural network for solving monotone variational inequalities and related optimization problems , 2004, IEEE Transactions on Neural Networks.

[4]  Fei Liu,et al.  Finite-time boundedness of uncertain time-delayed neural network with Markovian jumping parameters , 2013, Neurocomputing.

[5]  Francesco Amato,et al.  Finite-time control of discrete-time linear systems: Analysis and design conditions , 2010, Autom..

[6]  Xuyang Lou,et al.  Delay-Dependent Criteria for Global Robust Periodicity of Uncertain Switched Recurrent Neural Networks With Time-Varying Delay , 2008, IEEE Transactions on Neural Networks.

[7]  Jia Liu,et al.  New delay-dependent asymptotic stability conditions concerning BAM neural networks of neutral type , 2009, Neurocomputing.

[8]  Peng Shi,et al.  Observer Design for Switched Recurrent Neural Networks: An Average Dwell Time Approach , 2011, IEEE Transactions on Neural Networks.

[9]  Bin Jiang,et al.  On stabilization of switched nonlinear systems with unstable modes , 2009, Syst. Control. Lett..

[10]  Zidong Wang,et al.  Stability and Synchronization of Discrete-Time Markovian Jumping Neural Networks With Mixed Mode-Dependent Time Delays , 2009, IEEE Transactions on Neural Networks.

[11]  Jinde Cao,et al.  Multistability in bidirectional associative memory neural networks , 2008 .

[12]  Huijun Gao,et al.  Asynchronously switched control of switched linear systems with average dwell time , 2010, Autom..

[13]  Xia Li,et al.  Asynchronously switched control of discrete impulsive switched systems with time delays , 2013, Inf. Sci..

[14]  Jun Cheng,et al.  Finite-time boundedness of state estimation for neural networks with time-varying delays , 2014, Neurocomputing.

[15]  Yang Tang,et al.  Stability analysis of switched stochastic neural networks with time-varying delays , 2014, Neural Networks.

[16]  Andrzej Cichocki,et al.  Neural networks for optimization and signal processing , 1993 .

[17]  Bo Hu,et al.  Stability analysis of switched systems with stable and unstable subsystems: An average dwell time approach , 2001, Int. J. Syst. Sci..

[18]  Hamid Reza Karimi,et al.  Observer-based finite-time fuzzy H∞ control for discrete-time systems with stochastic jumps and time-delays , 2014, Signal Process..

[19]  Yuqiang Wu,et al.  Robust exponential stability analysis of discrete-time switched Hopfield neural networks with time delay ☆ , 2011 .

[20]  Huijun Gao,et al.  Robust Stability Criterion for Discrete-Time Uncertain Markovian Jumping Neural Networks With Defective Statistics of Modes Transitions , 2011, IEEE Transactions on Neural Networks.

[21]  Y. Zou,et al.  Finite-time stability and finite-time weighted l 2 2-gain analysis for switched systems with time-varying delay , 2013 .

[22]  Hamid Reza Karimi,et al.  A new design of H∞ filtering for continuous-time Markovian jump systems with time-varying delay and partially accessible mode information , 2013, Signal Process..

[23]  Huaguang Zhang,et al.  Motif discoveries in unaligned molecular sequences using self-organizing neural networks , 2006, IEEE Trans. Neural Networks.

[24]  Jinde Cao,et al.  Mean square exponential stability for discrete-time stochastic switched static neural networks with randomly occurring nonlinearities and stochastic delay , 2014, Neurocomputing.

[25]  Jun Zhao,et al.  Tracking control for switched time-varying delays systems with stabilizable and unstabilizable subsystems , 2009 .

[26]  Peng Shi,et al.  Stability and Stabilization of Switched Linear Systems With Mode-Dependent Average Dwell Time , 2012, IEEE Transactions on Automatic Control.

[27]  Leszek Rutkowski,et al.  Adaptive probabilistic neural networks for pattern classification in time-varying environment , 2004, IEEE Transactions on Neural Networks.

[28]  Huijun Gao,et al.  Distributed Synchronization in Networks of Agent Systems With Nonlinearities and Random Switchings , 2013, IEEE Transactions on Cybernetics.

[29]  H. Liu,et al.  Asynchronous finite-time stabilisation of switched systems with average dwell time , 2012 .