Open AccessNeural Network Control for a Batch Distillation Column
Author(s) -
Duraid Fadhil Ahmed,
Ahlam Mohamad Shakoor
Publication year - 2016
Publication title -
mağallaẗ tikrīt li-l-ʻulūm al-handasiyyaẗ/tikrit journal of engineering sciences
Language(s) - English
Resource type - Journals
eISSN - 2312-7589
pISSN - 1813-162X
DOI - 10.25130/tjes.23.1.02
Subject(s) - pid controller , artificial neural network , control theory (sociology) , offset (computer science) , matlab , controller (irrigation) , fractionating column , control engineering , batch distillation , binary number , computer science , distillation , engineering , temperature control , control (management) , artificial intelligence , mathematics , chemistry , chromatography , fractional distillation , agronomy , arithmetic , biology , programming language , operating system
The present work deals with studying the dynamic behavior of a batch distillation column and implemented two types of control strategies for the separation different types of binary systems. The model was derived and then simulated using "MATLAB" program. The experimental data of dynamic behavior were to tune the parameters of PID controller and developed the training of neural networks controller by using supervised learning algorithms. The simulation results show a qualitatively acceptable behavior. This study shows also that the response of PID controller was oscillatory behavior with high offset value while neural network controller gave less offset value and less time to reach the steady state. In general, a good improvement is achieved when the neural network controller is used compared with PID control.