Construction of Neural Network Based Lyapunov Functions

A straightforward method for the construction of Lyapunov functions represented by neural networks is presented in this paper. The resulting neural networks are Lyapunov functions on the basis of which asymptotic stability or instability of a nonlinear system's equilibrium point can be mathematically proven. One of the main advantages of this method is that it works for any nonlinear system even when the number of state variables is large. Several different Lyapunov functions can be constructed for each system, including Lyapunov functions of quadratic form. This enables us to select the most appropriate function for a given problem.

[1]  M. M. Bayoumi,et al.  Feedback stabilization: control Lyapunov functions modelled by neural networks , 1993, Proceedings of 32nd IEEE Conference on Decision and Control.

[2]  Antonio Campo,et al.  Turbulent natural convection in an air-filled isosceles triangular enclosure , 2006 .

[3]  Nikita Barabanov,et al.  A new method for stability analysis of nonlinear discrete-time systems , 2003, IEEE Trans. Autom. Control..

[4]  Kamil Kahveci,et al.  A Differential Quadrature Solution of Natural Convection in an Enclosure with a Finite-Thickness Partition , 2007 .

[5]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[6]  A. Rosenfeld,et al.  IEEE TRANSACTIONS ON SYSTEMS , MAN , AND CYBERNETICS , 2022 .

[7]  G. Serpen,et al.  Empirical approximation for Lyapunov functions with artificial neural nets , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[8]  D. V. Prokhorov,et al.  A Lyapunov machine for stability analysis of nonlinear systems , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[9]  Yogesh Jaluria,et al.  Design and Optimization of Thermal Systems , 1997 .

[10]  G. D. Davis.  Natural convection of air in a square cavity: A bench mark numerical solution , 1983 .

[11]  A. Liaqat,et al.  Numerical comparison of conjugate and non-conjugate natural convection for internally heated semi-circular pools , 2001 .

[12]  George N. Barakos,et al.  Natural convection flow in a square cavity revisited: Laminar and turbulent models with wall functions , 1994 .

[13]  C. J. Hoogendoorn,et al.  COMPARISON EXERCISE FOR COMPUTATIONS OF TURBULENT NATURAL CONVECTION IN ENCLOSURES , 1995 .

[14]  C. A. Desoer,et al.  Nonlinear Systems Analysis , 1978 .

[15]  BART KOSKO,et al.  Bidirectional associative memories , 1988, IEEE Trans. Syst. Man Cybern..

[16]  A. Liaqat,et al.  Conjugate natural convection in a square enclosure containing volumetric sources , 2001 .

[17]  V. Babu,et al.  Simulation of high Rayleigh number natural convection in a square cavity using the lattice Boltzmann method , 2006 .

[18]  Gursel Serpen,et al.  Stability of simultaneous recurrent neural network dynamics for static optimization , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[19]  A. Papachristodoulou,et al.  On the construction of Lyapunov functions using the sum of squares decomposition , 2002, Proceedings of the 41st IEEE Conference on Decision and Control, 2002..

[20]  Danil V. Prokhorov,et al.  Application of SVM to Lyapunov function approximation , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[21]  R. Viskanta,et al.  Study of the effects of wall conductance on natural convection in differently oriented square cavities , 1984, Journal of Fluid Mechanics.