Self-tuning control of nonlinear systems using neural network adaptive frame wavelets

Single layer feedforward neural networks with hidden nodes of adaptive wavelet functions have been successfully demonstrated to have potential in many applications. In this paper, an application to a self-tuning design method of an unknown nonlinear system is presented. Different types of frame wavelet functions are integrated for their simplicity, availability, and capability of constructing adaptive controllers. An infinite impulse response recurrent structure is combined by cascading to the network to provide double local structure resulting in improving speed of learning. This particular neurocontroller assumes a certain model structure to approximately identify the system dynamics of the "unknown" plant and generate the control signal. The capability of neurocontrollers to self-tuning of an unknown plant is then illustrated through an example. Simulation results demonstrate that the self-tuning design method is directly applicable for a large class of systems.