Using genetic programming to find Lyapunov functions
Iac Iris Soute, René van de Molengraft, GZ Georgo Angelis, C Ryan, L. Spector · TU/e Research Portal · 2001
In this paper Genetic Programming is used to find Lyapunov functions for (non)linear dif ferential equations of autonomous systems. As Lyapunov functions can be difficult to find, we use OP to make the decisions concerning the form of the Lyapunov function. As an e5cample two systems are taken to compute Lyapunov functions for. Although the OP algorithm is programmed to search for local stability, for most runs the result is a Lya punov function that assures global stability. Further testing is necessary to demonstrate if similar results can be obtained for more complex systems.