research centers


Search results: Found 12

Listing 1 - 10 of 12 << page
of 2
>>
Sort by

Article
Investigation and Estimation of Seepage Discharge Through Homogenous Earth Dam with Core by Using SEEP/W Model and Artificial Neural Network

Author: Asmaa Abdul Jabbar Jamel اسماء عبد الجبار جميل
Journal: DIYALA JOURNAL OF ENGINEERING SCIENCES مجلة ديالى للعلوم الهندسية ISSN: 19998716/26166909 Year: 2018 Volume: 11 Issue: 3 Pages: 54-61
Publisher: Diyala University جامعة ديالى

Loading...
Loading...
Abstract

This paper concerns to investigate the amount of seepage through the homogenous earth dam with core by finite elements software SEEP/W. By SEEP/W investigates groups were executed with three different upstream and down.stream slopes of earth dam, four different upstream and downstream slopes of core, for homogenous cases. For each run the amount of seepage discharge was specified. Dimensional analysis was used for the product and with aiding of the SPSS statically program to advancement an empirical equation in order to estimate the amount of seepage discharge through the homogenous earth dam with core resting on impervious base. In addition using ANN the SEEP/W results and the recommended equation in this paper have been verified, which show great agreement with SEEP/W results with using one hidden layer for ANN.

Keywords

ANN --- Earth Dam --- FEM --- Seepage


Article
ANN Technique to Predict Performances of Diesel Engine Runs by Butanol-Diesel Blends

Author: Duraid F. Maki
Journal: Journal of University of Babylon مجلة جامعة بابل ISSN: 19920652 23128135 Year: 2018 Volume: 26 Issue: 2 Pages: 320-327
Publisher: Babylon University جامعة بابل

Loading...
Loading...
Abstract

Performance of a diesel engine running under butanol-diesel blends one of important cases to evaluate the variance in the engine performance due to the fuel type change. Many efforts exerted in this field. Artificial neural network (ANN) model one of modern technique is used to predict the engine performance. ANN using a multi layer feed forward back propagation learning algorithm is developed to evaluate diesel engine performance. The brake efficiency, fuel consumption and exhaust temperature are predicted. The data required for training of ANN model are collected from experimental tests carried out on multi cylinder diesel engine. More than forty different architectures are tested for obtaining best fitting model. Maximum, minimum as well as average percentage errors are calculated for each architecture and R &  test is carried out to decide upon the best architecture for this model. The training process is set to stop when all errors are below 0.01 for training and below 3% for the validation. The results obtained from trained model are compared with experimental data of engine performance. The numerical investigation demonstrated that the ANN model is the best approach and assessment program for diesel engine performance with only 0.7% absolute average errors. The precise results of the model indicated an excellent and prompting training of ANN model.

تعتبر دراسه الاداء لمحركات الديزل التي تعمل بخليط من البيوتانول– ديزل واحدة من حالات البحث المهمة. و قد بذلت جهود كبيره في ابحاث و دراسات عمليه و نظريه في هذا المجال. ان تقنيه استخدام الشبكات العصبيه الصناعيه واحدة من الطرق المستخدمه لدراسه وتخمين اداء محركات الديزل التي تعمل بخلائط البيتانول – الديزل. ان الشبكه العصبيه الصناعيه تستخدم مايسمى بخوارزميه التغذيه الاماميه و التقدم الرجعيه. تمثلت خواص الاداء ب الكفاءه المكبحيه و كميه صرف الوقود و درجه حرارة غازات العادم.تم دراسه اكثر من اربعين تشكيل للموديل موضع البحث. ولكل تشكيل تم حساب معدل الخطا و اعلى خطا و اقل خطا و قد استخدمت الانحرافات المعياريه من الاحصاء لدراسه افضل تشكيل و الذي يعطي اقل خطا و اسرع وصول الى الحل. تم ضبط الخطا في برنامج الموديل ليكون فقط 1% و نسبه الخطا في التعديل و التصويب و3%. لقد اكدت النتائج المستقاه من هذا الموديل كفاءه الشبكات العصبيه الصناعيه في تخميين سلوك الاداء لمحرك يعمل بوقود الديزل و استخدم خليط البيوتانول كوقود نظيف له .


Article
A Neuro-Fuzzy and Neural Network Approach for Rutting Potential Prediction of Asphalt Mixture Based on Creep Test

Author: Israa Saeed Jawad Al-Haydari
Journal: AL-NAHRAIN JOURNAL FOR ENGINEERING SCIENCES مجلة النهرين للعلوم الهندسية ISSN: 25219154 / eISSN 25219162 Year: 2018 Volume: 21 Issue: 2 Pages: 275-284
Publisher: Al-Nahrain University جامعة النهرين

Loading...
Loading...
Abstract

This study implements the soft computing techniques such as Artificial Neural Network (ANN) and an adaptive Neuro-Fuzzy (ANFIS) approach. Thus to model the rutting prediction with the aid of experimental uniaxial creep test results for asphalt mixtures. Marshall samples, having Maximum Nominal Size of 12.5 mm, have been selected from previous studies. These samples have been prepared and tested under different conditions. They were also subjected to different loading stress (0.034, 0.069, 0.103) MPa, and tested at various temperature (10, 20, 40. and 55) °C The modeling analysis revealed that both approaches are powerful tools for modeling creep behavior of pavement mixture in terms of Root Mean Square Error and Correlation Coefficient. The best results are obtained with the ANFIS model.


Article
Classification of brain tumors using the multilayer perceptron artificial neural network
تصنيف أورام الدماغ بإستخدام الشبكة العصبية الاصطناعية لمستقبلات متعددة الطبقات

Authors: Raid Adnan Omar رائد عدنان عمر --- Jassim Mohammed Najim جاسم محمد نجم --- Imad H. Abood عماد هجول عبود
Journal: Iraqi Journal of Physics المجلة العراقية للفيزياء ISSN: 20704003 Year: 2018 Volume: 16 Issue: 36 Pages: 190-198
Publisher: Baghdad University جامعة بغداد

Loading...
Loading...
Abstract

Information from 54 Magnetic Resonance Imaging (MRI) brain tumor images (27 benign and 27 malignant) were collected and subjected to multilayer perceptron artificial neural network available on the well know software of IBM SPSS 17 (Statistical Package for the Social Sciences). After many attempts, automatic architecture was decided to be adopted in this research work. Thirteen shape and statistical characteristics of images were considered. The neural network revealed an 89.1 % of correct classification for the training sample and 100 % of correct classification for the test sample. The normalized importance of the considered characteristics showed that kurtosis accounted for 100 % which means that this variable has a substantial effect on how the network perform when predicting cases of brain tumor, contrast accounted for 64.3 %, correlation accounted for 56.7 %, and entropy accounted for 54.8 %. All remaining characteristics accounted for 21.3-46.8 % of normalized importance. The output of the neural networks showed that sensitivity and specificity were scored remarkably high level of probability as it approached % 96.

جمعت معلومات من 54 صورة لورم الدماغ من صور جهاز الرنين المغناطيسي (27 صورة لورم الدماغ الحميد و 27 صورة لورم الدماغ الخبيث) و عرضت هذه المعلومات لشبكة اعصاب افتراضية متعددة الطبقات متوفرة على البرنامج الاحصائي IBM SPSS 17. بعد محاولات عديدة تم اختيار معمارية شبكة الاعصاب الافتراضية الذاتية لمعلومات هذا البحث. ثلاثة عشر معلومة عن الجوانب الاحصائية و الشكلية للصورة تم اعتمادها في هذا البحث. لقد اظهرت شبكة الاعصاب المستخدمة نسب تصنيف صحيح في مجموعة التدريب بلغت 89.1 % بينما بلغت 100 % في مجموعة الاختبار. لقد اظهرت الاهمية المعدلة طبيعيا ان التفرطح (kurtosis) كان المعلومة الاكثر اهمية (100 %) في التمييز بين نوعي ورم الدماغ، و هذا يؤشر الاهمية الجوهرية لهذه المعلومة في التنبؤ بنوع الورم للحالات الجديدة من خلال معلومات صورة الورم. لقد كان لتباين لمعان الصورة (contrast) اهمية طبيعية 64.3 %، و للارتباط 56.7 % و 54.8 % للانتروبي (Entropy) و الذي هو عبارة عن مقياس احصائي للعشوائية التي تستخدم لتمييز نسيج الصورة. لقد تراوحت الاهمية المعدلة طبيعيا لكل المعلومات الباقية بين 21.3 %-46.8 %. لقد اظهرت النتائج التي افرزتها شبكة الاعصاب الافتراضية ان احتمال تنبؤ نوع الورم الحميد تصل الى 96 % (sensitivity) و حالة الورم الخبيث (specificity) تصل الى نفس المستوى .


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
Adaptive Inverse Neural Network Based DC Motor Speed and Position Control Using FPGA

Authors: Abbas H. Issa عباس حسين عيسى --- Aula N. Abd علا نجم عبد
Journal: DIYALA JOURNAL OF ENGINEERING SCIENCES مجلة ديالى للعلوم الهندسية ISSN: 19998716/26166909 Year: 2018 Volume: 11 Issue: 3 Pages: 71-78
Publisher: Diyala University جامعة ديالى

Loading...
Loading...
Abstract

In this research two types of controllers are designed in order to control the speed and position of DC motor. The first one is a conventional PID controller and the other is an intelligent Neural Network (NN) controller that generate a control signal DC motor. Due to nonlinear parameters and movable laborers such saturation and change in load a conventional PID controller is not efficient in such application; therefore neural controller is proposed in order to decreasing the effect of these parameter and improve system performance. The proposed intelligent NN controller is adaptive inverse neural network controller designed and implemented on Field Programmable Gate Array (FPGA) board. This NN is trained by Levenberg-Marquardt back propagation algorithm. After implementation on FPGA, the response appear completely the same as simulation response before implementation that mean the controller based on FPGA is very nigh to software designed controller. The controllers designed by both m-file and Simulink in MATLAB R2012a version 7.14.0.


Article
Study the Effect of Ingate Area on Mechanical Properties of As Cast (AL-0.4%Cu) Using ANN

Author: Mazin Nabih Ali مازن نبيه علي
Journal: DIYALA JOURNAL OF ENGINEERING SCIENCES مجلة ديالى للعلوم الهندسية ISSN: 19998716/26166909 Year: 2018 Volume: 11 Issue: 4 Pages: 73-77
Publisher: Diyala University جامعة ديالى

Loading...
Loading...
Abstract

In the present work the effect of Ingate Area on the Mechanical properties (σmax, σyield, E and hardness, stiffness) of as cast Al-4%Cu alloy had been studied, molds were made by sand casting with different ingate area (1cm×1cm, 1.2cm×1.2cm, 1.4cm×1.4cm, 1.6cm×1.6cm, 1.8cm×1.8cm, 2cm×2cm, 2.2cm×2.2cm, 2.4cm×2.4cm and 2.6cm×2.6cm). The process was done in normal condition (T=25Cᵒ, dry sand, constant speed, constant pour distance), while the casts prepared for the testing as a work piece to get the results. Also, Artificial Neural Network (ANN) had been adopted to predict the values of outputs (mechanical properties) and getting the mathematical equations that describe the relations between input and outputs parameters. From the results of the proposed work it conclude that mechanical properties magnitudes had been increased due to increasing in ingate area cast, and the relations between the ingate area and mechanical properties) had been detected depending on the results that gotten from ANN.


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%.


Article
Prediction of Municipal Solid Waste Generation Models Using Artificial Neural Network in Baghdad city, Iraq
التنبؤ بنماذج توليد النفايات الصلبة البلدية باستخدام الشبكة العصبية الاصطناعية في مدينة بغداد، العراق

Authors: Basim Hussein Khudair باسم حسين خضير --- Sura Kareem Ali سرى كريم علي --- Duaa Tawfeeq Jassim دعاء توفيق جاسم
Journal: Journal of Engineering مجلة الهندسة ISSN: 17264073 25203339 Year: 2018 Volume: 24 Issue: 5 Pages: 113-123
Publisher: Baghdad University جامعة بغداد

Loading...
Loading...
Abstract

The importance of Baghdad city as the capital of Iraq and the center of the attention of delegations because of its long history is essential to preserve its environment. This is achieved through the integrated management of municipal solid waste since this is only possible by knowing the quantities produced by the population on a daily basis. This study focused to predicate the amount of municipal solid waste generated in Karkh and Rusafa separately, in addition to the quantity produced in Baghdad, using IBM SPSS 23 software. Results that showed the average generation rates of domestic solid waste in Rusafa side was higher than that of Al-Karkh side because Rusafa side has higher population density than Al-Karkh side. The artificial neural networks show a high coefficient of determination between the predicted and observed domestic solid waste, with R2 value reaching to 0.91, 0.828 and 0.827 for Al-Karkh, 0.9986,0. 9903 and 0.9903 for Rusafa side, and 0.9989, 0.9878 and 0.9847 in Baghdad city, and also, these models were used to estimate the generation of municipal solid waste for short period with highly efficient which assistance in planning to design landfills sites.

نظرا لأهمية بغداد بوصفها عاصمة للعراق ومركز اهتمام الوفود بسبب تاريخها الطويل، فمن الضروري الحفاظ على بيئتها. ويتحقق ذلك من خلال الإدارة المتكاملة للنفايات الصلبة، لأن ذلك لا يمكن إلا إذا كنا قادرين على معرفة الكميات التي ينتجها السكان على أساس يومي. لهذا السبب، تم التركيز في هذه الدراسة على إيجاد نماذج رياضية للتنبؤ بكمية النفايات الصلبة المتولدة في الكرخ والرصافة بشكل منفصل، بالإضافة إلى الكمية التي تنتجها مدينة بغداد باستخدام برنامج IBM SPSS 23. وأظهرت النتائج أن متوسط معدلات توليد النفايات الصلبة المنزلية في الرصافة كان أعلى من الكرخ لأن جانب الرصافة له كثافة سكانية أعلى من الكرخ. واستخدمت الشبكات العصبية الاصطناعية للعثور على النماذج المطلوبة حيث أظهرت النتائج وجود قيم ارتباط عالية لكل نموذج تم التنبؤ به . وقد أظهرت نتائج الشبكات العصبية الاصطناعية قيم ارتباط عالية لكل نموذج متوقع، حيث تصل قيمة R2 إلى 0.91 و 0.828 و 0.827 للكرخ و0.9903 و 0.9980 و 0.9903 لجانب الرصافة و 0.9989 و 0.9878 و 0.9847 لمدينة بغداد كما يمكن استخدام هذه النماذج لتقدير توليد النفايات الصلبة البلدية لفترة قصيرة بكفاءة عالية والتي تساعد في التخطيط لتصميم مواقع مدافن القمامة.


Article
Fault Diagnosis in Wind Power System Based on Intelligent Techniques

Authors: Kanaan A. Jalal --- Lubna A. Abd alameer
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2018 Volume: 36 Issue: 11 Part (A) Engineering Pages: 1201-1207
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

Wind energy is one of the most important sources as well as beingenvironmentally friendly and sustainable. In this paper, different types of faults ofDoubly-Fed Induction Generator (DFIG) have been studied based on ArtificialNeural Network (ANN), Particle Swarm Optimization (PSO) and FieldProgrammable Gate Array. To simulate the wind generators modelMATLAB/Simulink program has been used. Artificial Neural Network (ANN) istrained for detection the faults and (PSO) technique is used to get the best weights.After the training process, the network was transformed into a Simulink programand then converted into the Very High Speed Description Language (VHDL) fordownloading on the (FPGA) card, which in turn is used to detect and diagnosis thepresence of faults where it can be re-programmed with high response andaccuracy.

Listing 1 - 10 of 12 << page
of 2
>>
Sort by
Narrow your search

Resource type

article (12)


Language

English (12)


Year
From To Submit

2018 (12)