NN-SANARX model based control of a multi tank liquid-level system

摘要

This paper is devoted to application of neural network with a specific restricted connectivity structure for identification and control of a real process. Parameters of the identified model are used to design a controller based on dynamic feedback linearization. The designed neural network based controller is verified on mathematical model within MATLAB/Simulink environment and applied to the real-time control of a laboratory plant. Water tank system was chosen as a case study to illustrate applicability of the proposed approach. Several experimental results as well as comparison with some alternative methods are provided.