Journals / Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi / 2006 / Cilt: 21 - Sayı: 4

Control of the concentration in a nonisothermal CSTR with artificial neural network

İzotermal olmayan sürekli karıştırmalı bir tank reaktörde yapay sinir ağı ile derişim kontrolü

Pages
721–727
Publication Date
2022-10-18
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

In comparison to the literature where the same example problem was solved by using Dynamic Neural Network and Nonlinear Internal Model Controllers, the results obtained in this work seemed better to represent the system behavior than the literature.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In this work, controlling of the outlet concentration of a continuous stirred tank reactor (CSTR) was studied using artificial neural network.
📊
Key Findings & Data:Control of the outlet concentration in the reactor where a non-isothermal, exothermic and a first order irreversible reaction took place was accomplished by manipulating the coolant flow rate.
💡
Conclusion & Impact:In comparison to the literature where the same example problem was solved by using Dynamic Neural Network and Nonlinear Internal Model Controllers, the results obtained in this work seemed better to represent the system behavior than the literature.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters

Abstract

In this work, controlling of the outlet concentration of a continuous stirred tank reactor (CSTR) was studied using artificial neural network. Control of the outlet concentration in the reactor where a non-isothermal, exothermic and a first order irreversible reaction took place was accomplished by manipulating the coolant flow rate. Due to the highly nonlinear dynamic behavior of the system, Neural Network Predictive and NARMA-L2 (Nonlinear Auto Regressive Moving Average) controllers were used as neural network control architecture. The results obtained with neural network controllers were compared with those obtained by classical PID controllers. Both neural network controllers were able to succeed in responding toward the set point faster and earlier in time than PID controller. Thus, neural network controller architectures showed better performances when compared to PID control strategies. In comparison to the literature where the same example problem was solved by using Dynamic Neural Network and Nonlinear Internal Model Controllers, the results obtained in this work seemed better to represent the system behavior than the literature.

Özet

Bu çalışmada, sürekli karıştırmalı bir tank reaktörde (CSTR) çıkış derişiminin yapay sinir ağı (YSA) temelli kontrolü incelenmiştir. İzotermal olmayan, ekzotermik ve birinci mertebeden tersinmez bir tepkimenin gerçekleştiği bu reaktörde çıkış derişiminin kontrolü soğutma suyu akış hızı ayarlanarak sağlanmıştır. Sistemin doğrusal olmama yapısının çok yüksek olmasından dolayı kontrol stratejisi olarak yapay sinir ağı kontrol yapılarından YSA-Öngörmeli kontrol ve NARMA-L2 (Nonlinear Auto Regressive Moving Average) kontrol stratejileri oluşturulmuş, klasik PID kontrol edici ile performans karşılaştırması yapılmıştır. Çalışmada kullanılan YSA kontrol edicilerin her ikisi de çok hızlı ve kısa zamanda set noktasına ulaşmayı başarmıştır. YSA-Öngörmeli kontrol edici ve NARMA-L2 kontrol edici yapıları, PID kontrol edici ile kıyaslandığında daha iyi bir performans göstermişlerdir. Sonuçlar, literatürde yer alan ve aynı örnek problem için kurulan YSA temelli DNNC (Dynamic Neural Network Control) ve NIMC’den (Nonlinear Internal Model Control) elde edilen sonuçlardan daha iyi görünmektedir.

🔖

Cite This Article

YÜCEER, M., ATASOY, İ., BERBER, R. (2022). Control of the concentration in a nonisothermal CSTR with artificial neural network. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, Cilt: 21 - Sayı: 4, 721–727. https://ajindex.com/articles/524166

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (14)

  1. Narendra, K. S. ve Parthasarathy, K. “Identification and Control of Dynamical Systems Using Neural Networks”, IEEE Trans. Neural Networks, Cilt 1, No 1, 4-27, 1990
  2. Callinan, T. “Artificial Neural Network Identification and Control of the Inverted Pendulum”, MEng Project Reports, School of Electronic Engineering Dublin City University. August 2003
  3. Hagan T. M. ve Demuth, H. “Neural Networks for Control”, American Control Conference, San Diego, pp. 1642-1656, June, 1999
  4. Yıldırım, Ş., Erkaya, S. ve Uzmay, İ. “Yapay Sinir Ağları Kullanılarak Concorde Uçaklarının Kontrolü”, Erciyes Üniversitesi Fen Bilimleri Enstitüsü Dergisi, Cilt 20, No 1-2, 1-12, 2004
  5. İstif, İ. Ve Kutlu, K. “Oransal Valf Kontrollu Hidrolik Silindir Sisteminin Konum Kontrolu”, İTÜ Dergisi, Cilt 3, No 2-3-4-5, 77-86, 2004
  6. Bhat, N. V. ve McAvoy, T. J., “Use of Neural Nets for Dynamic Modeling and Control of Chemical Process Systems”, Computers Chem Engng, Cilt 42, 573–582, 1990
  7. Nahas, E. P., Henson, M. A. ve Seborg, D. E., “Nonlinear Internal Mode1 Control Strategy for Neural Network Models”, Computers Chem Engng, Cilt 16, No 12, 1039-1057, 1992
  8. Nikravesh, M., Farell, A. E. ve Stanford, T. G. “Control of Nonisothermal CSTR with Time Varying Parameters via Dynamic Neural Network Control (DNNC)”. Chemical Engineering Journal, Cilt 76, 1-16, 2000
  9. Soloway, D. and Haley, P. “Neural Generalized Predictive Control: A Newton-Raphson Implementation”, IEEE Paper No. ISIAC-TA5.2. Proceedings of the IEEE CCA/ISIC/CACSD, Sept 15-18, 1996
  10. Narendra, K. S. ve Mukhopadhyay, S. ”Adaptive Control Using Neural Networks and Approximate Models” IEEE Trans. Neur. Networks, Cilt. 8, No 3, 475-485, 1997
  11. Hagan, T. M., Demuth, H. B.ve Jesus, O. D., “An Introduction to the Use of Neural Networks in Control Systems”, International Journal of Robust and Nonlinear Control, Cilt 12, No 1, 959-985, 2002
  12. Jesus, O. D., Pukrittayakamee, A. ve Hagan, M. T., “A Comparison of Neural Network Control Algorithms”, IEEE, 521-526, 2001
  13. Hong, Z., Kaifang, D. ve Tingqi, L. A. “Online- Trained Neural Network Controller for Electrohydraulic Servo System”, Proceedings of the 4. World Congress on Intelligent Control and Automation, June 10-14, 2002
  14. The Mathworks, Inc. (2003). www.mathworks.com.