New SISO and MIMO Adaptive Generalized Predictive Controllers based on Self-Organizing RBF Neural Networks

Abstract

This paper proposes an adaptive generalized predictive control (GPC) scheme for control of non-linear time- varying processes. An online identification approach based on an adaptive neural network with growing and pruning radial basis function (GAP-RBF) structure is presented to model the process dynamics in real-time. A single-input, single-output (SISO) adaptive GPC controller is designed based on dynamic linearization of the identified process model. The adaptive GPC control procedure is extended to multi-input, multi-output (MIMO) processes. The proposed SISO and MIMO GPC controllers are evaluated on a highly non-linear time-varying nonisothermal continuous stirred tank reactor (CSTR) benchmark problem. The simulation results demonstrate the potential capabilities of the two developed GPC controllers to identify and control the CSTR process with superior performance over the conventional PID controller.