Adaptive Predictive Controllers Using a Growing and Pruning RBF Neural Network

An adaptive version of growing and pruning RBF neural network has been used to predict the system output and implement Linear Model-Based Predictive Controller (LMPC) and Non-linear Model-based Predictive Controller (NMPC) strategies. A radial-basis neural network with growing and pruning capabilities is introduced to carry out on-line model identification. An Unscented Kalman Filter (UKF) algorithm with an exponential time-varying forgetting factor has been presented to enable the neural network model to track any time-varying process dynamic changes. An adaptive NMPC has been designed based on the sequential quadratic programming technique. The paper makes use of a dynamic linearization approach to extract a linear model at each sampling time instant so as to develop an adaptive LMPC. The servo and regulating performances of the proposed adaptive control schemes have been illustrated on a non-linear Continuous Stirred Tank Reactor (CSTR) as a benchmark problem. The simulation results demonstrate the capability of the proposed identification strategy to effectively identify compact, accurate and transparent model for the CSTR process. It is shown that the proposed adaptive NMPC controller presents better improvement with faster response time for both servo and regulatory control objectives in comparison with the proposed adaptive LMPC, an adaptive generalized predictive controller based on Recursive Least Squares (RLS) algorithm and well-tuned PID controllers.