Auto tuned PID and neural network predictive controller for a flow loop pilot plant

Abstract

This paper presents an advanced control strategy that uses the neural network (NN) predictive controller to govern the dynamics of a Flow loop pilot plant. The set point tracking using NN Predictive controller and conventional PID strategies are investigated. The control objective is to keep the outlet flow of the Single Input Single Output Flow loop at a reference value. An orifice meter as a flow measuring device and Variable Frequency Drive as a final control element is selected to collect Input, Output data. System Identification toolbox in MATLAB is used to construct the model of a flow loop from measured input–output data. Various models are estimated, validated and realized that the transfer function model gives the best fit. This model is used to build the PID and NN Predictive controller. NN predictive controller parameters are set, by the designer's expertise. The performance of a NN predictive controller is then compared with the conventional auto-tuned PID controller. Experimental results are presented, which emphasizes the superiority and effectiveness of the NN predictive controller.