Recurrent Multilayer Perceptrons for Identiication and Control: the Road to Applications

This study investigates the properties of artiicial recurrent neural networks. Particular attention is paid to the question of how these nets can be applied to the identiication and control of non-linear dynamic processes. Since these kind of processes can only insuuciently be modelled by conventional methods, diierent approaches are required. Neural networks are considered to be useful for this purpose due to their ability to approximate a wide class of continuous functions. Among the numerous network structures, especially the recurrent multi-layer perceptron (RMLP) architecture is promising from application point of view. This network architecture has the wellknown properties of multi layer perceptrons and moreover these nets have the ability to incorporate temporal behavior. Departing from the original process description the applicability of RMLPs is investigated and diierent learning algorithms for this network class are outlined. Furthermore, besides the conventional algorithms, like Back-propagation through time, Real-Time recurrent learning (RTRL) and Dynamic Back-propagation, a more sophisticated training method which uses second order information, the Global Extended Kalman Filter (GEKF) is introduced. Finally, three applications of RMLPs in the environment of automotive and telecommunication systems are discussed.