Premium
Event‐based neural network predictive controller application for a distillation column
Author(s) -
Hadian Mohsen,
Mehrshadian Milad,
Karami Mahboobeh,
Biglary Makvand Amin
Publication year - 2021
Publication title -
asian journal of control
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.769
H-Index - 53
eISSN - 1934-6093
pISSN - 1561-8625
DOI - 10.1002/asjc.2265
Subject(s) - setpoint , artificial neural network , control theory (sociology) , model predictive control , controller (irrigation) , fractionating column , mimo , computer science , cuckoo search , nonlinear system , process (computing) , event (particle physics) , control engineering , engineering , distillation , artificial intelligence , control (management) , machine learning , chemistry , physics , quantum mechanics , agronomy , biology , computer network , channel (broadcasting) , organic chemistry , particle swarm optimization , operating system
In this work, the case study is a distillation column, which is a multi‐input multi‐output (MIMO) nonlinear process. An event‐based neural network predictive controller is utilized for the case study, considering control and energy policies. Computation and communication reduction are the main purposes of the event‐based strategy. The event‐based model predictive controller also copes successfully with the multi‐input multi‐output (MIMO) time‐delayed nonlinear processes. In order to achieve a suitable nonlinear data‐based model of the process, an event‐based neural network predictive controller is proposed. Moreover, new Cuckoo Optimization Algorithm (COA) is employed to improve the efficiency of the neural network. Evaluation of the proposed controller has illustrated a satisfactory performance in both setpoint tracking and disturbance rejection while computational load has been significantly decreased.