A new strategy, to augment the pH process control is offered in this paper. The intelligent controller proposed herein is based on an inverse neural plant model. An integration term is introduced to improve the pure inverse neural controller performance. This element, adjusted by a fuzzy system with respect to the control error, operates in parallel with the neural controller to ensure offset-free performance, in case of system uncertainties or modelling mismatch. Four fuzzy rules were applied to generate the integrator parameters. Experimental results, carried out under pH control on a laboratory scale set-up, demonstrate the feasibility of the proposed control system.
This paper deals with intelligent controller design using artificial neural networks (ANN) in the role of feedback controllers. Neural controllers are built up and trained as inverse neural process models. Their performance and robustness are, gradually, improved and augmented by introducing, first, an adaptive simple integrator and, then, a controller with fuzzy integrator part. The proposed ANN control system performance is demonstrated using examples of both: control of a perturbed linear system of second order and a non-linear continuous biochemical process with simulated uncertainties. MATLAB programme package environment has been used to build up and train the ANN feedback controllers. I. INTRODUCTIONARTIFICIAL neural networks have good general approximation capabilities for modeling complex non-linear processes because they are able to match the input/output behavior of any continuous non-linear system [1]. Many results, well-known in modeling or other scientific fields, have been re-discovered in neural networks context. The use of ANNs in identification and control, which has been recognized as an effective tool for handling difficult nonlinear problems, has recently attracted a great deal of attention, because ANN appear to provide a convenient means for modeling complicated non-linear processes at low cost.A neural network can be trained to develop an inverse model of the plant. The network input is the process output, and the network output is the corresponding process input. Typically, the inverse model is a steady-state/static model, which can be used for feedforward control [2]. Obviously, an inverse model exists only when the process behaves monotonically as a "forward" function at steady state. If not, this approach is inapplicable. In principle, an inverse neural network model can learn the inverse dynamics under some restrictions (e.g. minimum phase and causality are required). Then, the inverse model is arranged in a way similar to an internal model control (IMC) structure [3].In this paper, neural network based feedback controllers
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.