Silvan Meslek Yüksekokulu Koleksiyonu
Bu koleksiyon için kalıcı URI
Güncel Gönderiler
Öğe Detection of road extraction from satellite images with deep learning method(Springer, 2025) Aslan, Emrah; Özüpak, YıldırımRoad extraction from satellite data is of great importance in various fields such as climate change, urban planning, forestry and sustainable development. In addition, fast and accurate road detection plays a critical role in disaster management and smart city applications, especially in emergency situations. In this context, U-net architecture provides an effective solution for tasks such as semantic segmentation and urban planning support. In this work, Edge U-net, a different adaptation of the U-net architecture, is used to map roads and streets and to detect changes over time. When the performance of the architecture is evaluated using Mean Intersection over Union (mIoU) and global accuracy metrics, superior results are obtained compared to other studies in the literature. In addition, the performance of the model was improved by applying transfer learning to the ImageNet dataset and various hyperparameter settings were performed. The results of the study show that path inferences are detected with 98.4% accuracy. These results show that Edge U-Net architecture and deep learning methods can be effectively used in road detection applications from satellite imagery.Öğe Prediction and comparative analysis of emissions from gas turbines using random search optimization and different machine learning-based algorithms(Polska Akademia Nauk, 2024) Aslan, EmrahGas turbines are widely used for power generation globally, and their greenhouse gas emissions have increasingly drawn public attention. Compliance with environmental regulations necessitates sophisticated emission measurement techniques and tools. Traditional sensors used for monitoring emission gases can provide inaccurate data due to malfunction or miscalibration. Accurate estimation of gas turbine emissions, such as particulate matter, carbon monoxide, and nitrogen oxides, is crucial for assessing the environmental impact of industrial activities and power generation. This study used five different machine learning models to predict emissions from gas turbines, including AdaBoost, XGBoost, k-nearest neighbour, and linear and random forest models. Random search optimization was used to set the regression parameters. The findings indicate that the AdaBoost regressor model provides superior prediction accuracy for emissions compared to other models, with an accuracy of 99.97% and a mean squared error of 2.17 on training data. This research offers a practical modelling approach for forecasting gas turbine emissions, contributing to the reduction of air pollution in industrial applications.Öğe Broken magnets fault detection in PMSM using a convolutional neural network and SVM(Galileo Institute of Technology and Education of the Amazon (ITEGAM), 2024) Benkaihoul, Said; Mazouz, Lakhdar Djelloul; Tayeb, Naas Toufik; Özüpak, Yıldırım; Mohammedi, Ridha DjamelThe Permanent Magnet Synchronous Motor (PMSM) stands as a pivotal component in various applications, yet it remains susceptible to an array of faults within both its rotor and stator, there arises an imperative to swiftly and intelligently address these issues. In this study, a novel approach was undertaken wherein a PMSM design was conceptualized within the Ansys Maxwell program, followed by the deliberate introduction of a fault at the rotor's magnetic level. Specifically, three distinct fault scenarios were delineated based on the number of broken magnets (BM), namely 2, 3, and 4, localized within specific rotor areas. Notably, the magnetic flux density was selected as the focal parameter for this investigation. To effectively detect and diagnose faults stemming from BM, an innovative Convolutional Neural Network (CNN) architecture was devised. Leveraging images of the PMSM design captured during operational phases at various time intervals, the CNN exhibited remarkable efficacy in discerning and categorizing fault instances. Upon analysis of the derived outcomes, it becomes evident that the CNN exhibited unparalleled accuracy in fault detection, achieving a remarkable 100% success rate when juxtaposed with alternative methodologies such as Support Vector Machines (SVM) and K-Nearest Neighbors (KNN), which yielded accuracy rates of 97%.Öğe Using artificial neural networks to improve the efficiency of transformers used in wireless power transmission systems for different coil positions(Publishing House of the Romanian Academy, 2024) Özüpak, Yıldırım; Aslan, EmrahThis study uses magnetic resonance-based coupling theory to study the various placements of transmitter and receiver coils in wireless power transfer (WPT) systems. Various coil placements are examined to show where high efficiency can be achieved within the air gap. Basic characteristics such as self-inductance, mutual inductance, and coupling coefficient were calculated. Artificial neural networks (ANNs) in WPT are a powerful technique for predicting performance characteristics. Using ANNs provides an excellent method for streamlining the design process and reducing time-consuming calculations. To quickly determine and optimize coil design, this study compares recent research on ANN applications in WPT and the performance of different types of ANNs in WPT systems. An artificial neural network (ANN) was trained to predict the magnetic properties of a wireless power transfer (WPT) device. Appropriate cost functions have been implemented to train the ANN properly. It was shown that the trained ANN can effectively reproduce the data obtained by the finite element method (FEM). The results show an effective power transmission at different coil placements, with decreased efficiency observed after a certain distance. These data will help determine the proposed WPT system's air gap and angular limits.Öğe Design and co-analysis of a permanent magnet brushless DC motor by using clonal selection principle based wound healing algorithm and ansys-maxwell(2023) Özüpak, Yıldırım; Çınar, MehmetThis paper presents the design and analysis of a 550 W Permanent Magnet (PM) Brushless DC motor (BLDC). The finite element method (FEM) was employed to assess the motor's performance characteristics. The design and dynamic performance analysis were conducted using ANSYS/Rmxprt, while electromagnetic studies were carried out using ANSYS/Maxwell-2D. Additionally, optimization of the DC motor was achieved through a Wound Healing Algorithm (WHA). A PID controller was designed for this purpose. The paper also elaborates on the detailed design equations for creating a BLDC motor. BLDC motors are known for their high dynamic responses, efficiency, extended operating life, wide speed change intervals, and noise-free operation. The motor's geometry was modeled in the ANSYS-Maxwell-Rmxprt software tool and later imported into the Maxwell-2D environment for further analysis. The designed motor was observed to operate with 93% efficiency, meeting the specified torque value. The results of the optimization process were interpreted by comparing them with the values obtained from the ANSYS software.Öğe Analysis of the parameters affecting the efficiency of the wireless power transmission system designed for new generation electric vehicles(Korean Society of Automotive Engineers, 2023) Özüpak, YıldırımIn magnetic resonance coupled wireless power transfer (WPT) systems, parameters were investigated in the WPT system to ensure maximum power transfer under the conditions of changing the distance between the receive coil and the transmit coil. When the distance between the transceiver coils is changed, the inductances of the system and the coupling coefficient for maximum power transfer were calculated with Maxwell-3D, which performed a solution based on the finite element method (FEM). In addition, the effect of the distance variation between the transmitter and receiver coils, the coupling coefficient (k) values, on the input inductance and power transmission was investigated. In the model developed in the ANSYS-Maxwell environment, it has been observed that the variation of the input inductance depending on the distance and therefore the common inductance between the transmitter and receiver coils can be analyzed. In addition, the effect of the coupling factor (k) on the WPT system has also been demonstrated. It has been shown that maximum power transfer can be sustained in WPT systems where the distance between the receive coil and the transmit coil varies within certain limits. Finally, the efficiency of the transformer for a close distance between the coils was also tested experimentally.Öğe Design and analysis of permanent magnet dc machines with FEM based Ansys-Maxwell(Niyazi ÖZDEMİR, 2023) Özüpak, YıldırımIn this paper, permanent magnet direct current (PMDC) motor was designed and analyzed; The obtained speed, efficiency, torque and air gap flux distributions were examined and the results were compared with literature for the motor type. In order to compare the designed machine with literature, magnets made of the same materials and having the same geometric dimensions were used, as well as the basic motor features. The rated current, voltage, speed, torque and efficiency of two surface magnet motors with different rotor structures, including the eddy current effect, torque-speed characteristics and magnetic analysis, were investigated using the ANSYS-MAXWELL program, which performs a solution based on the Finite Element Method (FEM). This study will be a useful study for the literature in terms of examining the basic structure, electromagnetic properties, speed-torque values, efficiency of motor with surface permanent magnet (PM) rotor and comparing with literature.Öğe Analysis of an inductive coupling wireless power transfer system with a finite element method for charging applications of electric vehicles(Bitlis Eren Üniversitesi, 2023) Özüpak, Yıldırım; Çınar, MehmetWith the development of technology, Wireless Power Transfer (WPT) systems have also started to be used in charging applications for electric vehicles. The basic methods of WPT systems are based on power transmission systems with laser, microwave, magnetic induction, and magnetic resonance. Factors such as the limited use of fossil fuels and environmental pollution have led researchers to see electric vehicles as a solution and to charge these vehicles with wireless systems. Most commercial wireless power transmission applications are currently limited to close contact transmission distances. There are challenges in increasing coverage, routing transmissions, and safely exploiting sufficiently strong electric fields. To provide power efficiently, highly directional transmitters must be used. Otherwise, with an omnidirectional transmission, only a small part of the transmitted power will reach the receiver. Especially in order to distribute power over long distances, it is often necessary to resort to radiation transfer methods that tightly combine electric and magnetic fields. In this study, important studies on WPT systems were investigated and examined. Then, a WPT transformer is modeled with the Finite Element Method based ANSYS-Maxwell-3D. The results obtained using the simulation method are presented in comparison with the research findings. Determining the efficiency of wireless power transfer used in electric vehicle charging applications is the expected result of the study.Öğe Performing analysis of current transformer in short circuit and open circuit conditions using ANSYS@Maxwell(Erzincan Binali Yıldırım Üniversitesi, Fen Bilimleri Enstitüsü, 2021) Özüpak, YıldırımCalculation of the design parameters of current transformers (CTs) is very complex due to their magnetic and thermal properties, complexity of their structure, different ferromagnetic properties of the materials and the nonlinearity of the B-H curve of the core material. The secondary output of these transformers is used for both measurement and protection circuits. Therefore, AT's accuracy must be very good and precise. In this study, the transformer is modeled as 2D using the Finite Element Method (FEM). ANSYS@Maxwell program, which realizes a solution based on finite element method, has been used in magnetic and thermal analysis of the current transformer. Analyzes of the transformer were carried out in 2D under open and short circuit conditions. From the results obtained from the analysis, the scattered electromagnetic flux distribution occurred in the core of the current transformer, which caused the secondary current of the CT to be erroneous. Therefore, it has been observed that unwanted operating conditions occur in the protection circuits..Öğe Development of Push-Recovery control system for humanoid robots using deep reinforcement learning(Ain Shams University, 2023) Aslan, Emrah; Arserim, Muhammet Ali; Uçar, AyşegülThis paper focuses on the push-recovery problem of bipedal humanoid robots affected by external forces and pushes. Since they are structurally unstable, balance is the most important problem in humanoid robots. Our purpose is to design and implement a completely independent push-recovery control system that can imitate the actions of a human. For humanoid robots to be able to stay in balance while standing or walking, and to prevent balance disorders that may be caused by external forces, an active balance control has been presented. Push-recovery controllers consist of three strategies: ankle strategy, hip strategy, and step strategy. These strategies are biomechanical responses that people show in cases of balance disorder. In our application, both simulation and real-world tests have been performed. The simulation tests of the study were carried out with 3D models in the Webots environment. Real-world tests were performed on the Robotis-OP2 humanoid robot. The gyroscope, accelerometer and motor data from the sensors in our robot were recorded and external pushing force was applied to the robot. The balance of the robot was achieved by using the recorded data and the ankle strategy. To make the robot completely autonomous, Deep Q Network (DQN) and Double Deep Q Network (DDQN) methods from Deep Reinforcement Learning (DPL) algorithms have been applied. The results obtained with the DDQN algorithm yielded 21.03% more successful results compared to the DQN algorithm. The results obtained in the real environment tests showed parallelism to the simulation results.Öğe Analysis of the effect of air gaps on the electric field in the insulation material of high voltage transmission cables(Erzincan Binali Yıldırım Üniversitesi Fen Bilimleri Enstitüsü, 2022) Özüpak, YıldırımHigh voltage (HV) cables are widely used in the transmission and distribution of electrical energy. The design and manufacture of these cables with great precision are of great importance for power systems. Mistakes made during the manufacturing phase and defects that may occur in the structure of the cable material can cause premature aging and continuous malfunctions in the cables. Factors such as air gaps, foreign substances, and moisture in the insulating material may cause punctures and insulation problems in high voltage cables. In this study, the effects of air gaps left as manufacturing defects on the electric field distribution in the insulation of high voltage cables used in power systems were investigated. The effects of 154 kV high voltage cable, the air gap in different coordinates, and diameters in the insulating layer on the electric field distribution in the cable have been investigated. For this analysis, the Finite Element Method (FEM) and ANSYS@Workbench program which realizes a solution based on this method were used. It has been found that the diameter and location of the air gap significantly affect the electric field distribution of the high voltage cable.Öğe Design and analysis of switched reluctance motor with FEM based Ansys-Maxwell(Kyrgyz-Turkish Manas University, 2022) Özüpak, YıldırımIn this study, radial forces that create noise, which is a fundamental problem in Switched Reluctance Motor (SRM), are investigated. Since radial force causes stator vibrations and noise caused by magnetic field, a new switched reluctance motor model with increased stator and rotor poles has been designed in order to reduce the radial force acting on the rotor poles. In addition, a structure with high torque and low leakage flux compared to conventional winding structure has been proposed for Switched Reluctance Motors (SRM). The windings of the designed SRM are placed in layers, insulated from each other. Rotor poles are formed to move on both sides of each phase winding. Thus, the flux that will occur in the phase windings axially completes its circuit from the stator poles and the rotor poles. This designed ARM model has been examined by Finite Element Method (FEM. The proposed motor geometry has been analyzed with ANSYS Maxwell-3D, which performs FEM-based solution), and parametric analysis with ANSYS-RMxprt.Öğe Bir transformatörün endüktanslarının deneysel analizi ve Ansys@Maxwell ile simülasyon hesabı(2021) Özüpak, YıldırımTransformatörler, elektriğin iletim ve dağıtımı için elektrik güç sistemlerinin hayati bir bileşendir. Bir transformatörün verimliliğini artırmaya yönelik sağlam tasarım, transformatörün imalatındaki ana etkenlerden biridir. Pratik bir transformatörün verimliliği, tasarım ve imalat kusurlarından kaynaklanan kayıplarla sınırlıdır. Kablosuz güç aktarımı (KGA), elektrik enerjisinin iletkensiz aktarılmasıdır. KGA zamanla değişen elektrik, manyetik veya elektromanyetik alanlar kullanan teknolojilere dayanır. Bu teknoloji sensörler, aktüatörler ve iletişim cihazlarında olduğu gibi uygunsuz veya mümkün olmayan elektrikli cihazlara güç sağlamak için kullanışlıdır. Güç, kısa mesafelerde, alternatif manyetik alanlar ve bobinler arasındaki endüktif kuplaj veya alternatif elektrik alanları ve metal elektrotlar arasındaki kapasitif kuplaj ile aktarılabilir. Kablosuz güç aktarım sistemi için M125-027S nüve malzemesi ile tasarlanan bir transformatörün deneysel bir modeli oluşturulmuştur. Transformatörün her iki tarafında 20 mm hava boşluğu bırakılarak, parametreler, parametreler bu şartlar altında ölçülmüştür. Transformatörün bobinlerinin endüktans parametrelerini hesaplamak ve analiz etmek için Sonlu Elemanlar Yöntemini (SEY) kullanılmıştır. Sistem ANSYS@Maxwell ile modellenerek, manyetik alan ve endüktans parametreleri SEY bazlı çözüm gerçekleştiren ANSYS@Maxwell ile hesaplanmıştır. Bu çalışmada, transformatörün endüktif parametreleri hesaplanarak kablosuz güç aktarım sisteminin kapasitansının doğru kompanzasyonu için temel oluşturulmak istenmiştir.Öğe Birleştirilmiş elektromekanik sonlu elemanlar yöntemi ile güç transformatörünün termal alan analizi(Erzincan Üniversitesi Fen Bilimleri Enstitüsü, 2019) Özüpak, Yıldırım; Mamiş, Mehmet SalihTransformatör tasarımına başlamadan önce, sıcaklık dağılımının ve termal sınırların bilinmesi doğru bir tasarımiçin büyük önem teşkil etmektedir. İzin verilen termal sınırların üzerindeki sıcaklık, transformatör bileşenlerindeciddi hasara neden olabilmektedir. Bu çalışmada, termal alan analizi için bir model sunulmuştur. Bu sayede,transformatörün aktif kısımlarında meydana gelen ısıdan ortamın sıcaklığına kadar tüm koşullar esas alınarakbirleştirilmiş elektromekanik Sonlu Elemanlar Yöntemi (SEY) tekniğine dayanan ANSYS@Maxwell veANSYS@Mechanical birleşimi simülasyon yazılımı ile üç fazlı bir transformatörün sıcaklık dağılımı ve termalalan analizi gerçekleştirilmiştir. Önerilen modeli doğrulamak için nominal değeri 15 MVA 33/11 kV olan birtransformatör seçilmiştir. Simülasyondan elde edilen değerler deneysel değerlerle karşılaştırılarak model vesonuçlar doğrulanmıştır. Tasarlanan model sayesinde, transformatörün nüvesinde ve sargılarında meydana gelensıcaklık dağılımı ve transformatörün sıcaklığı ölçülemeyen bölgelerindeki spesifik noktaların sıcaklığı belirlenmiştir.Öğe Elektrikli araçların kablosuz güç transferi sistemi için dairesel bobinli bir transformatörün tasarımı ve veriminin analizi(Çukurova Üniversitesi Mühendislik Fakültesi, 2022) Özüpak, YıldırımKablosuz Güç Transferi (KGT), elektrik enerjisinin iletkenlere ihtiyaç duyulmadan aktarılmasıdır. KGT zamanla değişen elektrik, manyetik veya elektromanyetik alanlar kullanan teknolojilere dayanır. Bu teknolojilerde güç, kısa mesafelerde, manyetik alan ve bobinler arasındaki endüktif kuplaj yoluyla veya elektrik alan ile metal elektrotlar arasındaki kapasitif kuplaj yoluyla aktarılabilmektedir. Diğer bir ifade ile bu sistemin temel çalışma prensibi manyetik rezonansa (MR) dayanmaktadır. Endüktif kuplaja dayalı KGT sistemi, kısa mesafelerdeki elektrikli cihazların şarj edilmesi için kullanılmaktadır. Bu teknolojinin gelişmesi, endüktif kuplajlı güç aktarım sistemini elektrikli araçların şarj uygulamaları için vazgeçilmez hale getirmiştir. Bu çalışmada, elektrikli araçlardaki şarj uygulaması için KGT sisteminin verimliliğini etkileyen faktörler analiz edilmiştir. KGT sisteminde kullanılan transformatörlerin karmaşıklığı nedeniyle, karşılıklı endüktans ve kuplaj katsayısının hesaplanmasını kolaylaştırmak için Sonlu Elemanlar Yöntemi (SEY) kullanılmıştır. Bunun için bir elektrik devresini doğrusal olmayan bir eleman modeliyle birleştiren bir simülasyon modeli ANSYS yazılım paketi kullanılmıştır. Dairesel bobinli bir KGT transformatör modeli, Ansys-Maxwell yazılımında modellenmiş ve farklı koşullar altında simüle edilmiştir. Ayrıca tasarlanan KGT sisteminin performansı analiz edilmiştir.Öğe Sonlu elemanlar yöntemi ile dağıtım transformatörlerinin harmonik yük kayıplarının analizi(Bandırma Onyedi Eylül Üniversitesi, 2021) Özüpak, YıldırımTransformatörlerde meydana gelen kayıpları tahmin etmek, hem üreticiler hem de kullanıcılar için önemlidir. Teknolojinin gelişmesiyle birlikte güç sistemlerinde harmonikler artmaktadır. Güç sisteminin önemli bir bileşeni olan transformatörler de harmonikli yük akımları taşımaktadır. Çalışma sırasında sıcak nokta sıcaklıklarını ve toplam kayıpları tahmin edebilmek için yük kayıplarını doğru bir şekilde hesaplayabilmek önemlidir. Bu konuda farklı yöntemler geliştirilmiştir. Bu yöntemlerden Sonlu Elemanlar Yöntemi iyi bilinmekte ve doğruluğu mühendislik çalışmalarında kanıtlanmıştır. Transformatör tasarımcıları, tasarım ve analiz için geliştirilen ve kullanılan özel programlara sahiptirler. Bu çalışmada, ANSYS@Maxwell yazılım ve simülasyon programı bir güç transformatörünün parametrik bir modelini tasarlamak için kullanılmıştır. Bu sayede transformatörün hem normal çalışma koşullarındaki hem de harmonikli çalışma koşullarındaki yük kayıpları elde edilmiştir. Ayrıca harmonikli yüklerin manyetik akı dağılımına etkisi incelenmiştir.Öğe Examining children's simile comprehension skills(Birlesik Dunya Yenilik Arastirma ve Yayıncilik Merkezi, 2020) Bayat, Nihat; Kuz, EsraThis study aimed to determine the children's skills of comprehending similes. The participants of the research consisted of 120 children that were aged 5-6 and enrolled in preschool education institutions. The data were collected with a 16-item success test. The items in the test were orally administered to the participants during the interviews. The responses were recorded, and the analysis was carried out through the evaluation of the content of the recordings by two experts. The answers were encoded and transferred to the statistics program. Depending on the research questions, descriptive statistics were calculated, and a series of Mann Whitney U test was performed. According to the findings, the success rate of the item about simile comprehension at which participants were most successful appeared to be 56.7%. In addition, it was found that the participants' levels of simile comprehension did not differ based on gender, but they differed based on their duration of continuing preschool education. Participants attending public schools were more successful than those attending private preschools, and the 6-year-old children appeared to be more successful than the 5-year-olds.
