research centers


Search results: Found 6

Listing 1 - 6 of 6
Sort by

Article
Artificial Neural Network Control of Chemical Processes
السیطرة على العملیات الكیمیاویة بطریقة الشبكة العصبیة الاصطناعیة

Author: Duraid Fadhil Ahmed
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2014 Volume: 32 Issue: 1 Part (A) Engineering Pages: 176-196
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

This paper presents an artificial neural network based control scheme for studying the control of continuous stirred tank reactor, distillation column and neutralization process and this method is compared with conventional proportional- /integral-derivative controller. A multi-layer back-propagation neural network isemployed to model the nonlinear relationships between the inputs variables and controlled variables of processes in order to regulate the manipulating variables to a variety of operating conditions and acquire a more flexible learning ability. The robustness of this control structure is studied in the case of setpoint changes andload disturbances. The experimental results suggest that such neural controllers can provide excellent setpoint-tracking and disturbance rejection. The neural network based control has higher speed of response and the offset has a smaller average value than that of the conventional controller. The control action based on the neural network controller shows less oscillation and an improvement in the controlled variables stabilization time with respect to the conventional controllerand gives a better control performance.


Article
Fuzzy logic Control of Chemical Processes
السيطرة على العمليات الكيمياوية بطريقة الدليل الغامض

Author: Duraid Fadhil Ahmed
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2015 Volume: 33 Issue: 1 Part (A) Engineering Pages: 12-29
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

The objective of this study was to investigate the closed-loop control strategies for a batch reactor and batch distillation column by using two different control methods. In this paper, Fuzzy logic control is developed and compared with conventional proportional-/integral-derivative controller. In the design of fuzzy controller, the knowledge obtained from the process reaction curve procedure is employed to determine proper membership functions. Fine tuning is obtained alteration the output scaling factor. The forty nine rules are employed to regulate the manipulating variables to a variety of operating conditions and acquire a more flexible learning ability. The robustness of this control structure is studied in the case of set point changes and the fitness function for fuzzy controller is chosen as the integral of the absolute value of the error (IAE). The experimental results suggest that such fuzzy controllers can provide excellent set point-tracking and disturbance rejection. The results show that the fuzzy logic controller has a higher performance, in terms of robustness, response speed and the offset has a smaller average value than that of the conventional controller. According to experimental results, the fuzzy controller was considered more suitable and reliable for the batch reactor and distillation processes control with respect to the conventional controller.

هدف هذا البحث تطبيق طريقتي سيطرة على المفاعل الدفعي ويرج التقطير الدفعي. في هذا البحث تم تطوير طريقة الدليل الغامض للسيطرة وتم مقارنتها بالمسيطر التناسبي-التكاملي-التفاضلي التقليدي. تم الاعتماد على معلومات تجارب الحلقة المفتوحة في إيجاد قيم دوال الانتماء حيث تم استخدام تسعة وأربعون قانون في تصميم المسيطر من اجل تنظيم متغيرات المعالجة لمدى واسع من الظروف التشغيلية ومرونة كافية لقابلية تدريب المسيطر. تم دراسة متانة الطريقة المقترحة من خلال تغيير القيمة المرغوبة وتم استخدام معيار تكامل القيمة المطلقة للخطأ لتحديد الكفاءة. أظهرت النتائج العملية إن مسيطر الدليل الغامض يعطي مسايرة ممتازة للقيمة المرغوبة وإزالة لأي اضطراب وكفاءة عالية من حيث المتانة وسرعة الاستجابة وحيد اقل من الطريقة التقليدية. وطبقا للنتائج العملية إن مسيطر الدليل الغامض أكثر ثقة وملائمة للعمليات التقطير والمفاعل الدفعية مقارنة بالطريقة التقليدية.


Article
Fuzzy logic Control of Continuous Stirred Tank Reactor
السيطرة على المفاعل ذو الخلط المستمر باستخدام منطق الدليل الغامض

Author: Dr. Duraid Fadhil Ahmed Maha Nazar Esmaeel
Journal: Tikrit Journal of Engineering Sciences مجلة تكريت للعلوم الهندسية ISSN: 1813162X 23127589 Year: 2013 Volume: 20 Issue: 2 Pages: 70-80
Publisher: Tikrit University جامعة تكريت

Loading...
Loading...
Abstract

The mathematical modeling of continuous stirred tank reactor system is developed based on the mass and energy balances for the reactor and heating system. The system is studied by introducing step change in concentration, inlet flow, flow of heating fluid, inlet temperature and heating fluid temperature and measuring the temperature change in the reactor. In this paper, a fuzzy logic controller has been designed and evaluated. Through simulation study by using MATLAB, it has been shown that the proposed fuzzy logic controller has given an excellent tracking and regulation performance compared to that of the PID control system.

تم دراسة الموديل الرياضي لمفاعل ذو الخلط المستمر بالاعتماد على موازنة المادة والطاقة للمفاعل. تم تعرض النظام لتغيير درجي في التركيز ودرجة حرارة ومعدل جريان المادة الداخلة ودرجة حارة ومعدل جريان سائل التسخين وتم قياس درجة الحرارة داخل المفاعل. وكذلك تناول البحث تصميم طريقة سيطرة حديثة وهي طريقة الدليل الغامض وتم مقارنتها مع طريقة السيطرة التقليدية لجهاز التحكم من نوع تناسبي-تكاملي-تفاضلي باستخدام برنامج "الماتلاب". وقد أظهرت النتائج إن طريقة الدليل الغامض هي أفضل وذات كفاءة عالية مقارنة مع المسيطر التقليدي لأنها أقل تذبذب وأسرع بالوصول إلى القيمة المرغوبة.


Article
Dynamics and Control of Heat Exchanger Networks
السلوك الديناميكي و السيطرة على شبكة المبادلات الحرارية

Authors: Duraid Fadhil Ahmed --- Cizan A. Ali
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2014 Volume: 32 Issue: 2 Part (A) Engineering Pages: 465-480
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

In this paper dynamics of plate heat exchanger networks is given by combining dynamic models of plate heat exchangers in the network. A mathematical model for plate heat exchanger is developed based on energy balance. Dynamic simulation of plate heat exchanger networks to different step changes in flow rate of both process fluid and utility fluid is conducted using MATLAB simulink. Plate heat exchanger networks has been controlled using split range control method with two manipulated variables which are process fluid and utility fluid. The simulation results showed that split range controller is the best action and gives better response compared with conventional controller.

تم في البحث الحصول على النموذج الديناميكي لشبكة المبادلات الحرارية الصفائحية من خلال الجمع بين النموذج الديناميكي لمبادلات الحرارية الصفائحية الموجودة في الشبكة. تم تطوير نموذج رياضي لمبادل الحراري الصفائحي بالاعتماد على موازنة الطاقة. أجريت محاكاة ديناميكية لشبكة المبادلات الحرارية الصفائحية باستخدام برنامج ماتلاب من خلال اجراء اضطراب درجي في معدل الجريان لمائعي العملية والخدمات. تمت السيطرة على شبكة المبادلات الحرارية الصفائحية باستخدام مسيطر المدى المنفصل ذو متغيرين للمعالجة و أظهرت نتائج المحاكاة بأن مسيطر المدى المنفصل هو أفضل أداء وأعطت استجابة جيدة مقارنة مع المسيطر التقليدي.


Article
Development of Artificial Neural Network Model of Crude Oil Distillation Column
تطوير موديل بواسطة الشبكة العصبية الصناعية لوحدة التقطير الجوي للنفط الخام

Authors: and Ali Hussein Khalaf --- Duraid Fadhil Ahmed
Journal: Tikrit Journal of Engineering Sciences مجلة تكريت للعلوم الهندسية ISSN: 1813162X 23127589 Year: 2015 Volume: 22 Issue: 1 Pages: 24-37
Publisher: Tikrit University جامعة تكريت

Loading...
Loading...
Abstract

Artificial neural network in MATLAB simulator is used to model Baiji crude oil distillation unit based on data generated from aspen-HYSYS simulator. Thirteen inputs, six outputs and over 1487 data set are used to model the actual unit. Nonlinear autoregressive network with exogenous inputs (NARX) and back propagation algorithm are used for training. Seventy percent of data are used for training the network while the remaining thirty percent are used for testing and validating the network to determine its prediction accuracy. One hidden layer and 34 hidden neurons are used for the proposed network with MSE of 0.25 is obtained. The number of neuron are selected based on less MSE for the network. The model founded to predict the optimal operating conditions for different objective functions within the training limit since ANN models are poor extrapolators. They are usually only reliable within the range of data that they had been trained for.


Article
Neural Network Control for a Batch Distillation Column

Authors: Duraid Fadhil Ahmed --- Ahlam Mohamad Shakoor
Journal: Tikrit Journal of Engineering Sciences مجلة تكريت للعلوم الهندسية ISSN: 1813162X 23127589 Year: 2016 Volume: 23 Issue: 1 Pages: 10-19
Publisher: Tikrit University جامعة تكريت

Loading...
Loading...
Abstract

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.

Listing 1 - 6 of 6
Sort by
Narrow your search

Resource type

article (6)


Language

English (4)


Year
From To Submit

2016 (1)

2015 (2)

2014 (2)

2013 (1)