Model predictive stabilizer for T–S fuzzy recurrent multilayer neural network models with general terminal weighting matrix

This paper investigates the model predictive stabilization problem for Takagi–Sugeno (T–S) fuzzy multilayer neural networks with general terminal weighting matrix. A new set of linear matrix inequality (LMI) conditions on the general terminal weighting matrix of receding horizon cost function is presented such that T–S fuzzy multilayer neural networks with model predictive stabilizer are asymptotically stable. The general terminal weighting matrix of receding horizon cost function can be obtained by solving a set of LMIs. A numerical example is given to illustrate the effectiveness of the proposed stabilization scheme.

[1]  Wook Hyun Kwon,et al.  Stabilizing receding horizon H∞ controls for linear continuous time-varying systems , 2000, IEEE Trans. Autom. Control..

[2]  Liang Jin,et al.  A Review of: “Static and Dynamic Neural Networks” , 2005 .

[3]  Choon Ki Ahn,et al.  Exponential H∞ stable learning method for Takagi-Sugeno fuzzy delayed neural networks: A convex optimization approach , 2012, Comput. Math. Appl..

[4]  Bing Chen,et al.  Robust Stability for Uncertain Delayed Fuzzy Hopfield Neural Networks With Markovian Jumping Parameters , 2009, IEEE Trans. Syst. Man Cybern. Part B.

[5]  Choon Ki Ahn,et al.  New sets of criteria for exponential L2-L∞ stability of Takagi-Sugeno fuzzy systems combined with hopfield neural networks , 2013 .

[6]  W. Kwon,et al.  On feedback stabilization of time-varying discrete linear systems , 1978 .

[7]  Stephen P. Boyd,et al.  Linear Matrix Inequalities in Systems and Control Theory , 1994 .

[8]  Choon Ki Ahn,et al.  Takagi–Sugeno Fuzzy Hopfield Neural Networks for $${\mathcal{H}_{\infty}}$$ Nonlinear System Identification , 2011, Neural Processing Letters.

[9]  Choon Ki Ahn,et al.  Takagi-Sugeno fuzzy receding horizon H∞ chaotic synchronization and its application to the Lorenz system , 2013 .

[10]  Wook Hyun Kwon,et al.  On stabilizing receding horizon controls for linear continuous time-invariant systems , 2000, IEEE Trans. Autom. Control..

[11]  Choon Ki Ahn,et al.  Some new results on stability of Takagi-Sugeno fuzzy Hopfield neural networks , 2011, Fuzzy Sets Syst..

[12]  Manfred Morari,et al.  Robust constrained model predictive control using linear matrix inequalities , 1994, Proceedings of 1994 American Control Conference - ACC '94.

[13]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[14]  J. Hopfield.  Neurons withgraded response havecollective computational properties likethoseoftwo-state neurons , 1984 .

[15]  C. Ahn.  Delay-dependent state estimation for T-S fuzzy delayed Hopfield neural networks , 2010 .

[16]  F. Allgöwer,et al.  A quasi-infinite horizon nonlinear model predictive control scheme with guaranteed stability , 1997 .

[17]  Kazuo Tanaka,et al.  Stability analysis and design of fuzzy control systems , 1992 .

[18]  Cheng Si-we,et al.  Stochastic stability analysis of fuzzy Hopfield neural networks with time-varying delays , 2008 .

[19]  Cheng-Yu Yeh,et al.  An efficient complexity reduction algorithm for G.729 speech codec , 2012, Comput. Math. Appl..

[20]  Pagavathigounder Balasubramaniam,et al.  Stability analysis of uncertain fuzzy Hopfield neural networks with time delays , 2009 .

[21]  W. Kwon,et al.  A modified quadratic cost problem and feedback stabilization of a linear system , 1977 .

[22]  Choon Ki Ahn,et al.  H ∞ State Estimation for Takagi-Sugeno Fuzzy Delayed Hopfield Neural Networks , 2011, Int. J. Comput. Intell. Syst..

[23]  E. Gilbert,et al.  Optimal infinite-horizon feedback laws for a general class of constrained discrete-time systems: Stability and moving-horizon approximations , 1988 .