An offset-free neural controller based on a non-extrapolating scheme for approximating the inverse process dynamics

This work presents a novel control scheme based on approximating the inverse process dynamics with a radial basis function (RBF) neural network model, trained with the fuzzy means algorithm. The produced RBF network constitutes an inverse model of the process, which can be applied as an explicit control law. In order to avoid extrapolation in the RBF model predictions, a concept borrowed from chemometrics, namely the applicability domain, is incorporated to the proposed framework. Moreover, an error correction term is added, allowing the inverse neural controller to account for modeling errors and process uncertainty and eliminate offset. The proposed approach is applied to the control of a nonlinear Continuous Stirred Tank Reactor (CSTR) exhibiting multiple equilibrium points, including an unstable one. A comparison with other control schemes on various tests, including set-point tracking, unmeasured disturbance rejection and process uncertainty highlights the advantages of the proposed controller.