Modeling of steam distillation pot with ARX model

Abstract

This paper present a autoregressive with exogenous input (ARX) was applied in modelling of steam distillation pot system. The system of steam distillation pot are design with special specification interm of material and shape additional with induction heating system that provide a new technologies in extraction of essential oil to fullfill demand for this industry. The performance of ARX was investigates and the training data that provide robust model and fresh data set was evaluate. ARX model was estimated by means of prediction error method and training function of Levenberg-Marquardt algorithm. Data was collected with probability band 0.2 of PRBS input signals. By ARX model structure, the input output data are model. The performance of the model based on coefficient of determination (R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ), mean square error(MSE) and loss function of one-step-ahead and residuals. In overall, results shows that ARX have capability in capturing dynamic of the system.