CIVILICA We Respect the Science
(ناشر تخصصی کنفرانسهای کشور / شماره مجوز انتشارات از وزارت فرهنگ و ارشاد اسلامی: ۸۹۷۱)

Design Model Predictive Control based Neural Network for Temperature Control of Fermentation Chemical Bioreactor

عنوان مقاله: Design Model Predictive Control based Neural Network for Temperature Control of Fermentation Chemical Bioreactor
شناسه ملی مقاله: ICESCON03_249
منتشر شده در سومین کنفرانس بین المللی علوم و مهندسی در سال 1395
مشخصات نویسندگان مقاله:

Mohammad Mehdi Kianpour - Master of Science in Electrical Engineering (Control) Islamic Azad University of Mashhad Branch, Mashhad, Iran
Mehdi Zarif - Associate Professor in Electrical Engineering Department Islamic Azad University of Mashhad Branch, Mashhad, Iran
Mohammad Hasan Hafez Akbarian Jahani - Phd Student in Electrical Engineering (Control) Islamic Azad University of Mashhad Branch, Mashhad, Iran
Mohammad Reza Hafez Akbarian Jahani - Phd Student in Electrical Engineering (Control) Islamic Azad University of Mashhad Branch, Mashhad, Iran

خلاصه مقاله:
A chemical production system in recent years has made great progress. This system is different for each type of chemical substance and it is dependent on the type of reaction and dynamic. And the respective tanks are also designed and manufactured according to the type of equation. Control procedures caused a reaction and production process is optimized materials. The optimal production of high purity materials and high-speed response and more efficient use of raw materials is less. This paper is aimed at the production of ethanol. First, the equations governing the process are examined. And on the temperature parameter to control is selected and model-based predictive control method is used. MATLAB simulation results shows that the model based on neural network-based controller is much faster and more efficient than other methods of operation

کلمات کلیدی:
Bioreactor, temperature control, MPC, neural network, ethanol

صفحه اختصاصی مقاله و دریافت فایل کامل: https://civilica.com/doc/491693/