Identification and control experiments using neural designs

Neural designs are reported for system identification and control using static and dynamic gradient update schemes. Real-time implementation of the designs using a hardware example case system illustrates the inherent capability of neural networks to handle nonlinearities, learn, and perform control effectively for a real world system, based on minimal system information. The advantages of dynamic schemes over static ones are highlighted and a neural control design with feedforward and feedback components that facilitates incorporation of available knowledge about a system is described.<>