Adaptive RBFNN versus conventional self-tuning: comparison of two parametric model approaches for non-linear control

In this work a practical study evaluates two parametric modelling approache s - linear and non-linear (neural) - for automatic adaptive control. The ne ural adaptive control is based on a developed hybrid learning technique usi ng an adaptive (on-line) learning rate for a Gaussian radial basis function neural network. The linear approach is used for a self-tuning pole-placeme nt controller. A selective forgetting factor method is applied to both cont rol schemes: in the neural case to estimate on-line the second-layer weight s and in the linear case to estimate the parameters of the linear process m odel. These two techniques are applied to a laboratory-scaled bench plant w ith the possibility of dynamic changes and different types of disturbances. Experimental results show the superior performance of the neural approach particularly when there are dynamic changes in the process. (C) 2000 Elsevi er Science Ltd. All rights reserved.