research centers


Search results: Found 18

Listing 1 - 10 of 18 << page
of 2
>>
Sort by

Article
New Strategies for Associative Memories

Authors: New Strategies for Associative Memories --- Saja A. Talib
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2018 Volume: 36 Issue: 2 Part (A) Engineering Pages: 207-212
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

Associative memory is a neural network used to save collection of input and output data at its layers. Each output data is produced coincide with a given input. It can be useful as an artificial memory in many applications like (military, medical, data security systems, error detection and correction systems …etc.). There are two matters which limit the uses of associative memory; the limited storage capacity, and the error occurred in the reading of output data. A modified strategy is suggested to overcome these limitations by introducing a new algorithm to the design of the associative memory. This method provides a software solution to the problems. The obtained results from the test examples proved that the proposed associative memory net could train and recall unlimited patterns in different sizes efficiently and without any errors.


Article
Prediction of penetration Rate and cost with Artificial Neural Network for Alhafaya Oil Field
تخمين معدل الحفر والكلفة بواسطة الشبكة العصابية الصناعية لحقل الحلفاية النفطي

Authors: Kadhim Hmood Mnati --- Hassan Abdul Hadi
Journal: Iraqi Journal of Chemical and Petroleum Engineering المجلة العراقية للهندسة الكيمياوية وهندسة النفط ISSN: 19974884/E26180707 Year: 2018 Volume: 19 Issue: 4 Pages: 21-27
Publisher: Baghdad University جامعة بغداد

Loading...
Loading...
Abstract

Prediction of penetration rate (ROP) is important process in optimization of drilling due to its crucial role in lowering drilling operation costs. This process has complex nature due to too many interrelated factors that affected the rate of penetration, which make difficult predicting process. This paper shows a new technique of rate of penetration prediction by using artificial neural network technique. A three layers model composed of two hidden layers and output layer has built by using drilling parameters data extracted from mud logging and wire line log for Alhalfaya oil field. These drilling parameters includes mechanical (WOB, RPM), hydraulic (HIS), and travel transit time (DT). Five data set represented five formations gathered from five drilled wells were involved in modeling process.Approximatlly,85 % of these data were used for training the ANN models, and 15% to assess their accuracy and direction of stability. The results of the simulation showed good matching between the raw data and the predicted values of ROP by Artificial Neural Network (ANN) model. In addition, a good fitness was obtained in the estimation of drilling cost from ANN method when compared to the raw data.

التخمين الدقيق لمعدل الحفر ذو اهمية كبيرة في الحفر الامثل بسبب تاثيره المحوري على كلفة عمليات الحفر. وعادة يكون هذا التخمين صعب بسبب تداخل العوامل التي تؤثر على عملية الحفر.في هذا البحث تم استخدام طريقة الشبكة العصابية الصناعية كاسلوب جديد لتخمين معدل الحفر والكلفة ,حيث تم بناء موديل الشبكة العصابية من ثلاثة طيقات اثنان مخفية وواحدة للنواتج باستعمال بيانات مجسات الطين والمجسات الاخرى لحقل الحلفاية النفطي. العوامل التي تم اسخدام قيمها هي العوامل الميكانيكية (الوزن المسلط ,سرعة الدوران),العوامل الهيدروليكية,وزمن انتقال الموجة الصوتية . تم استخدام خمس مجاميع للبيانات والتي نمثل خمس تكوينات في الحقل حيث تم استخدام 85%من البيانات لتدريب الموديل و15% لاختبار صلاحيته. بينت النتائج التطابق الجيد لقيم معدل الحفر المحتسبة من الموديل مع القيم المقاسة وكذلك لقيم الكلفة المحتسبة مع القيم الاصلية.


Article
Numerical Simulation for Estimating Energy Dissipation over Different Types of Stepped Spillways and Evaluate the Performance by Artificial Neural Network

Author: Asmaa Abdul Jabbar Jamel
Journal: Tikrit Journal of Engineering Sciences مجلة تكريت للعلوم الهندسية ISSN: 1813162X 23127589 Year: 2018 Volume: 25 Issue: 2 Pages: 18-26
Publisher: Tikrit University جامعة تكريت

Loading...
Loading...
Abstract

In this research, Flow-3D software uses to study the energy dissipation for stepped spillways with different end sills. The study is bases on three models. The first model contains rectangular end sills in all steppes. The second model contains rectangular end sills between one step and another. The third model contains triangular end sills in all steppes. For each of these models, three different variables are adopt, slope, height of the spillway and a number of steppes, and four different discharges value, carrying the total number of experiments to (324) tests. Analytical results show that the model (3) is the highest energy dissipation for all discharges value. Empirical equations extraction to find the energy dissipation for each of these models. The artificial neural network is also adopt to prove the accuracy and efficiency of the analytical results which are at high rates of compatibility with the values of the coefficient of determination for (model 1), (model 2) and (model 3) equal to (93.47%), (88.20%) and (86.00%) respectively. Also, artificial neural network identifies the most influential factors on the energy dissipation, the friction Froude number is the highest impact on the energy dissipation for models (1) and (2), while the parameter (b/ks) for the model (1).


Article
APPLICATION OF ARTIFICIAL NEURAL NETWORKS TO PREDICT SOIL RECOMPRESSION INDEX AND RECOMPRESSION RATIO

Authors: Abbas J. Al-Taie --- Ahmed F. Al-Bayati
Journal: KUFA JOURNAL OF ENGINEERING مجلة الكوفة الهندسية ISSN: 25230018 Year: 2018 Volume: 9 Issue: 4 Pages: 246-257
Publisher: University of Kufa جامعة الكوفة

Loading...
Loading...
Abstract

Overconsolidated soils are widely encountered in practice where settlement calculations are crucial. The recompression index (Cr) and the recompression ratio (Cr) are considered as one of the most important parameters used in settlement calculations. To achieve this purpose, expensive and time-consuming laboratory tests are usually conducted using undisturbed specimens to obtain the values of these parameters. Various equations derived from regression analysis were proposed to predict consolidation parameters from the physical properties of a soil. In this paper, however, an artificial neural network model (ANN) is proposed to predict Cr and Cr using natural water content, initial void ratio, total unit weight and effective overburden pressure. The proposed ANN model achieved good agreement with the results of one hundred seventy-nine standard one-dimensional consolidation tests collected from previous geotechnical investigations in Baghdad.


Article
Hybrid Approach of Prediction Daily Maximum and Minimum Air Temperature for Baghdad City by Used Artificial Neural Network and Simulated Annealing

Author: Hind Saleem Ibrahim Harba
Journal: Iraqi Journal of Science المجلة العراقية للعلوم ISSN: 00672904/23121637 Year: 2018 Volume: 59 Issue: 1C Pages: 591-599
Publisher: Baghdad University جامعة بغداد

Loading...
Loading...
Abstract

Temperature predicting is the utilization to forecast the condition of the temperature for an upcoming date for a given area. Temperature predictions are done by gathering quantitative data in regard to the current state of the atmosphere. In this study, a proposed hybrid method to predication the daily maximum and minimum air temperature of Baghdad city which combines standard backpropagation with simulated annealing (SA). Simulated Annealing Algorithm are used for weights optimization for recurrent multi-layer neural network system. Experimental tests had been implemented using the data of maximum and minimum air temperature for month of July of Baghdad city that got from local records of Iraqi Meteorological Organization and Seismology (IMOS) in period between 2010 to 2016. The results show that the proposed hybrid method got a high accuracy prediction results that reach nearly from real temperature records of desired year.


Article
Evaluation and Improvement Performance of a Boiler in a Thermal Power Plant Using Artificial Neural Network

Authors: Hosham S. Anead --- Khalid F. Sultan --- Raheel J. Abd-Kadhum
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2018 Volume: 36 Issue: 6 Part (A) Engineering Pages: 656-663
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

This research aims to avoid damage in power plant boiler steam generation by using Artificial Neural Network techniques (ANN) to improve the boiler performance. The training and testing using ANN by Back Propagation (BP) algorithm. The inputs to the neural network such factors which include air fuel ratio, water level, flame, gas, pressure and temperature. Control of the optimum input variables represent the output of the neural network. Experimental data is obtained by using an industrial boiler operating at AL-Dura power plant.the method of control by ANN is off – line ,the information of boiler taken from real plant and applied in matlab program for training ANN to taken right decision for control of boiler. ANN results were used in the control of thermal parameters based on the software program Matlabsimulink and showed that the maximum deviation between experimental data is less than 0.01 from the predicted results of the neural network in comparison to the results with modeling of the match at High Rate with actual power plant. It is recommend that Artificial Neural Network techniques (ANN) can be used to predicate and optimization the performance of a power plant and many problem can be solve in engineering applications.


Article
Identification of Rotary Inverted Pendulum Using Artificial Neural Network, Fuzzy Identification and Genetic Algorithm on Radial Basis Function
التعرف على منظومة البندول المقلوب الدوار باستخدام الخلايا العصبية الصناعية والتعرف المضبب والخوارزمية الجينية للدوال الشعاعية

Author: Yasir Khaldoon Al-Jubouri ياسر خلدون عبدالجبار
Journal: Journal of Al-Ma'moon College مجلة كلية المأمون ISSN: 19924453 Year: 2018 Issue: 32 Pages: 269-289
Publisher: AlMamon University College كلية المامون الجامعة

Loading...
Loading...
Abstract

This paper studies the physical structure and the mathematical dynamic model for a rotary inverted pendulum system and presents three different methods to identify this system. These methods are the Artificial Neural Network (ANN), Fuzzy Identification and Genetic Algorithm on Radial Basis Functions. In each method we use an LQR controller to generate a control signal which is applied to the system model and then we find the response for both the system model and the identified model using MATLAB. A Neural Network emulator is connected to the system model and receives a control input from the LQR controller such that the learning process which is done on-line. On the other hand, a Recursive Least Squares method is used to tune a standard Fuzzy system. Meanwhile, a Genetic algorithm is used to find the best weights for a Radial Basis Function model which minimizes the error between the measured output and network output. The results show that nonlinear methods such as fuzzy identification and neural network are more convenient to represent such system. The results for these methods show that the fuzzy model did a more accurate identification for the system however, it suffers from discontinuity, while, the response found for the Genetic RBF was also accurate but with longer settling time. Finally, the Artificial Neural Network model had a less accurate result.

يدرس هذا البحث التركيب الفيزيائي والنموذج الديناميكي للبندول المقلوب الدوار ويستعرض ثلاث طرق للتعرف علية باستخدام الشبكة العصبية الصناعية والتعرف المضبب والخوارزمية الجينية للدوال الشعاعية. تم تطبيق متحكم من نوع المنظم الخطي الرباعي لتوليد اشارة سيطرة و التي تطبق كمدخل لكل نموذج و تم تطبيقها باستخدام برنامج الماتلاب. تم ربط نموذج شبكة عصبية مع النموذج البندول الدوار المقلوب و بنفس المدخل لتكون عملية التعليم مباشرة. بينما تم تطبيق نظرية المربعات المصغرة التكرارية على نموذج نظام مضبب قياسي . بينما تم استخدام الخوارزميات الجينية لايجاد الاوزان المثلى لدالة شعاعية بحيث يتم تقليل الخطأ بين القيم المقاسة و مخرج الشبكة. النتائج اظهرت بأن النظريات اللاخطية مثل التعرف المضبب و الشبكات العصبية تكون اكثر ملاءمة لتمثيل النظام. النتائج اظهرت بان النظام المضبب كان اكثر دقة في التعرف على النظام و لكنها تعاني من عدم الاستمرارية، بينما كانت الخوازمية الجينية للدوال الشعاعية دقيقة ايضا و لكن بزمن وصول اكبر, و الشبكات العصبية كانت اقل دقة في تمثيل هذا النظام.


Article
Applying Modern Optimization Techniques for Prediction Reaction Kinetics of Iraqi Heavy Naphtha Hydrodesulferization

Authors: Zaidoon M. Shakor --- Anfal H. Sadeiq
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2018 Volume: 36 Issue: 11 Part (A) Engineering Pages: 1171-1175
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

In this study, a powerful modern optimization techniques such as GeneticAlgorithm (GA), Particle Swarm Optimization (PSO) and Artificial neural network (ANN)were applied to estimate the optimal reaction kinetic parameters for Heavy naphthaHydrodesulferization (HDS), the hydrodesulferization unit located in AL-Daura refineryBaghdad/Iraq.The reactions was carried out in a fixed-bed reactor packed with Co-Mo/γAl2O3catalyst and the operatingwas 315-400 °C temperature 35 bar Pressure and 0.5-2.1hr-1 liquid hourly space velocity. The result showed that hydrodesulferization of heavynaphtha follows the pseudo-first order reaction kinetics. This study signifies that thereaction kinetic parameters calculated by Genetic Algorithm was found to be moreaccurate and gives the highest correlation coefficient (R2= 0.9507) than the other twomethods. ANN technology by using the topology of (3-3-1-1) provides an effective tool tosimulate and understand the non-linear behavior of the process. The modelresult showedvery good agreement with the experimental data with less than 5%. mean absolute error.


Article
SHEAR STRENGTH PREDICTION OF REINFORCED CONCRETE SHALLOW BEAMS WITHOUT SHEAR REINFORCEMENTS

Author: Ahmed Faleh Al-Bayati
Journal: Journal of Engineering and Sustainable Development مجلة الهندسة والتنمية المستدامة ISSN: 25200917 Year: 2018 Volume: 22 Issue: 6 Pages: 85-100
Publisher: Al-Mustansyriah University الجامعة المستنصرية

Loading...
Loading...
Abstract

This paper presents two design equations to predict the shear strength of reinforced concrete shallow beams without shear reinforcements. The proposed equations were derived from two techniques: nonlinear regression analysis and artificial neural network analysis. The analysis were carried out using 279 test results of shallow beams available in the literature with wide range of geometrical and material properties. The proposed equations consider the influence of concrete compressive strength, flexural reinforcement, shear span-effective depth ratio, and the beam’s size. The calculations of the proposed equations are compared with those of the current codes of practice and those available in the literature, and they result as the best fitting to the available tests results.


Article
An Intelligent Detection System Based Road Traffic Sign Recognition

Authors: HazeemBaqerTaher --- Ali Hussain Hasan --- ShaimaHadi Mohammed
Journal: Journal of Education for Pure Science مجلة التربية للعلوم الصرفة ISSN: 20736592 Year: 2018 Volume: 8 Issue: 1 Pages: 77-87
Publisher: Thi-Qar University جامعة ذي قار

Loading...
Loading...
Abstract

AbstractTraffic sign detection and recognition systems provide an additional level of driver assistance,leading to improved safety for passengers, road users and vehicles. The automatic road-signsrecognition is an important part of driver assisting systems which helps driver to increase safety anddriving comfort. In this paper we proposed an efficient system for the detection and recognition ofthe road sign in the road and acquiring the traffic scene images from a fixed source.The road signrecognition system is divided into two parts, the first part is detection stage which is used to detectthe signs from a whole image by using the shape filtering method, and the second part is therecognition stage where the traffic sign obtained is analyzed then the names and directions of citiesare extracted using the artificial neural network (ANN).The system accuracy more than 90%.

Listing 1 - 10 of 18 << page
of 2
>>
Sort by
Narrow your search

Resource type

article (18)


Language

English (16)

Arabic (1)


Year
From To Submit

2018 (18)