An intelligent paradigm for electric generator control based on supervisory loops

In this paper a new approach to a neural network based intelligent adaptive controller, which consists of an online growing dynamic radial basis function neural network (RBFNN) structure along with a model reference adaptive control (MRAC), is proposed. RBFNN control is used to approximate the nonlinear function and the MRAC control adapts when plant parametric set changes. The adaptive laws, including neural network approximation error, are derived based on a Lyapunov function. The update details of the RBFNN width, centers, and weights are derived in order to ensure the error reduction and for improved tracking accuracy. Main advantage and uniqueness of the proposed scheme is the controller's ability to complement each other in case of parametric and functional uncertainty. Moreover, the online neural network produces a plant functional approximation control with growing and pruning nodes. The theoretical results are validated by conducting simulation studies on a single machine infinite bus (SMIB) system for electric generator control.