Identification and Predictive Control Using Recurrent Neural Networks

In this thesis, a special class of Recurrent Neural Networks (RNN) is employed for system identification and predictive control of time dependent systems. Fundamental architectures and learning algorithms of RNNs are studied upon which a generalized architecture over a class of state-space represented networks is proposed and formulated. Levenberg-Marquardt (LM) learning algorithm is derived for this architecture and a number of enhancements are introduced. Furthermore, using this recurrent neural network as a system identifier, a Model Predictive Controller (MPC) is established which solves the optimization problem using an iterative approach based on the LM algorithm. Simulation results show that the new architecture accompanied by LM learning algorithm outperforms some of existing methods. The third approach which utilizes the proposed method in on-line system identification enhances the identification/control process even more.