Abstract:
Detection is the process of modeling a system based on its inputs and outputs. Detection techniques for nonlinear systems are based on linear approximations of the system and such approximations perform well for a large range of process. But complex systems need complicated identification techniques. Neural networks have been shown to outperform traditional identification techniques on complex problems. Neural networks have unique pattern recognition characteristics which enable them to identify non linear systems. Tuned Genetic algorithms (TGA) have recently been applied to the design of neural networks. Based on the principles of natural evolution, TGA leads a more directed search than a random procedure, while still exploring, the entire search space. This paper describes technique for optimizing Modified Elman Neural Networks (MENN) using TGA for the identification and control of non linear systems. Cart pole system is used as the standard for this study. MENN is optimized using TGA are applied to cart pole system. It can be safely concluded that training and optimizing MENN using TGA yield substantially robust designs. TGA Elman network will definitely outperform the one using MENN trained by Back Propagation algorithm
