Application of Artificial Neural Network Strategies in Process Control
Artificial Neural Networks (ANN) have been enjoying an increasing attention in various fields of theory and application, lately. This contribution addresses the new concepts of introduction of the ANN approach into system identification and control. Both, ANN model based predictive control strategy and adaptive PID control are introduced. To demonstrate the feasibility and the performance of the control schemes, a continuous biochemical reactor is chosen as a realistic non-linear case study. Simulation results demonstrate the usefulness and the robustness of the proposed control algorithms.
KeywordsModel Predictive Control Feedforward Neural Network Prediction Horizon Artificial Neural Network Approach Stochastic Approximation Algorithm
Unable to display preview. Download preview PDF.
- Clarke, D.W. Mohtadi, C. and Tuffs, P.S.: Generalized predictive control - Part I. The basic algorithm, Part H. Extensions and interpretations. Automatica,23 (1987), 137–160.Google Scholar
- Ljung, L. Pflug, G. and Walk, H.: Stochastic approximation and optimization of random systems. Berlin, Springer-Verlag, 1992.Google Scholar
- Mészâros, A., Rusnâk, A. and Fikar, M.: Adaptive neural PID control. Case study: tubular chemical reactor. Computers and Chemical Engineering Supplement (1999), S847 - S850.Google Scholar
- Mészâros, A., Rusnhk, A. and Najim, K.: Intelligent control of continuous bioprocesses using neural network models. Chem. Biochem. Eng. Q., 11 (1997), 81–88.Google Scholar
- Mészâros, A., Brdys’, M. A., Tatjewski, P., Lednickÿ, P.: Multilayer adaptive control of continuous bioprocesses using optimising control technique. Case study: Baker’s yeast culture. Bioprocess Engineering, 12 (1995), 1–9Google Scholar