Browsing by Author "Unluturk, Ali"

Now showing 1 - 7 of 7

Comparison of Current Ratio Errors of Support and Toroidal Type CTs in Electric Power Systems: A Case Study
(IEEE-Inst Electrical Electronics Engineers Inc, 2025) Ozer, Ishak; Unluturk, Ali
A current transformer (CT) is a specialized device used to reduce high current values to safe and manageable levels in measurement and protection systems. Current ratio error (CRE) is an inevitable error in CTs due to factors such as magnetic saturation, magnetic core properties, primary and secondary winding errors, temperature effects and frequency changes, and manufacturing tolerances. Keeping this error close to zero is critical to the reliability of Electric Power System (EPS) because it directly affects the operation of protective relays and the accuracy of energy measurement systems. This study has performed a field-based quantitative comparison of absolute percentage current ratio error (AP-CRE) between S-CTs and T-CTs within ARAS's (Erzurum/Turkey) operational electric power system (EPS). The AP-CRE measurement has been obtained from S-CTs and T-CTs in EPS for protection with accuracy class 5P. Experimental measurement tests on a total of 34 CTs, including 17 S-CT and 17 T-CT, actively used in EPS. AP-CREs have been obtained by means of the TURA-01 device. In addition, during each AP-CRE measurement, absolute phase displacement (A-PD) and excitation current values have been also measured in real time. The performance of S-CT and T-CT have been evaluated based on three main metrics: mean absolute error (MAE), root mean square error (RMSE) and standard deviation (STD) values of the AP-CRE values obtained from CTs. According to AP-CRE; T-CT: MAE=0.44, RMSE=0.47 and STD=0.15, while S-CT: MAE=0.55, RMSE=0.58 and STD=0.21. The AP-CRE performance proves that T-CTs are better than S-CTs in EPS, which increases reliability.
Image Processing-Based Assessment of Dust Accumulation on Photovoltaic Modules
(IEEE, 2019) Unluturk, Muhammed; Kulaksiz, Ahmet Afsin; Unluturk, Ali
Numerous environmental factors significantly affect the energy yield of solar photovoltaic (PV) power plants. Among these, solar irradiance, photovoltaic module temperature, dust and shading are prominent. The level of soiling is directly related to the installation site of the PV plant. In this study, to investigate the impact of dust shading factor on energy efficiency, artificial light source in laboratory environment is used and power outputs are compared for three different densities of dust accumulation on the module surface. For each level of dust accumulation, images are obtained from PV modules. From the PV module images obtained by a camera for different levels of dust accumulation, new features are obtained based on Gray Level Co-occurrence Matrix. The obtained data with new features are classified on the basis of Artificial Neural Networks to determine dust level and its effect on PV module performance.
Machine Learning Based Self-Balancing and Motion Control of the Underactuated Mobile Inverted Pendulum with Variable Load
(IEEE-Inst Electrical Electronics Engineers Inc, 2022) Unluturk, Ali; Aydogdu, Omer
In this paper, a novel Machine Learning (ML) based Adaptive Fuzzy Logic-Proportional Integral (AFL-PI) controller was developed for the self-balancing and precision motion control of a two wheeled Underactuated-Mobile Inverted Pendulum (U-MIP) under variable payloads. One of the external disturbances in balance and motion control of the U-MIP is the amount of payload it carries on. To investigate the effectiveness of the proposed controller, a load bar was mounted on top of the U-MIP. The weights of 55gr each can be attached to this bar for variable payloads. The weights on the bar were labeled as three different classes: Low Load (LL), Normal Load (NL) and Heavy Load (HL). Artificial Neural Network (ANN), Linear Discriminant Analysis (LDA), Support Vector Machine (SVM) and k-Nearest Neighbors (k-NN) models were tested to obtain the highest payload class estimation. The highest load classification accuracy was achieved with ANN. Therefore, the ANN model was applied on the U-MIP. The balance performance of the U-MIP was compared by applying the classical FL-PI and ANN based AFL-PI controller on the robot. In order to compare the body tilt angle performance of the U-MIP, the optimal FL-PI parameter in LL was applied for NL and HL conditions without changing. Then, the proposed ANN based AFL-PI controller was implemented on U-MIP. With the proposed novel controller, the body tilt angle variation of the U-MIP was improved by %29.42 for NL and %55.62 for HL compared to the classical FL-PI controller. The validity of the proposed controller was proved by real experiments.
Önceden Eğitilmiş Derin Öğrenme Modelleri Kullanılarak Damlacık Yoluyla Bulaşan Salgın Hastalıkları Önlemek için Robotik Tabanlı Maske Tespiti
(2023) Unluturk, Ali
Aralık 2019’da Çin’in Wuhan şehrinde ortaya çıkan ve tüm dünyada hızla yayılan Koronavirüs hastalığı solunum yolu sonucu oluşan küçük damlacıklar ile bulaşarak sağlıklı insanları enfekte etmiştir. Tıp uzmanları Koronavirüs hastalığına karşı en etkili mücadelenin temas halindeki kişilerin maske takması gerekliliğini belirtmişlerdir. Buna rağmen bazı kişiler maske takma zorunluluğunu ihlal etmişlerdir. Bu çalışmada maske takma zorunluluğunu ihlal eden kişilerin otomatik olarak tespit edilebilmesi için önceden eğitilmiş olan NaNetMobile, MobileNetV3Small, ResNet50, DenseNet121 ve EfficientNetV2B0 gibi derin sinir ağı modellerinin maske tanıma performansları değerlendirilmiştir. Bu değerlendirme sonucunda en başarılı DenseNet121 modeli ele edilmiştir. Bu model 6- Serbestlik Derecesine (6-DOF) sahip robotik bir sisteminin üzerinde yer alan kameradan elde edilen görüntü ile doğrulanmıştır. Kameradan alınan insane ait yüz görüntüleri yüksek kare hızlarında NVIDIA tarafından geliştirilen Jetson Xavier geliştirme kartı kullanılarak işlenmiştir. Sonuç olarak, bu çalışma toplu alanlarda maske denetimi gerçekleştiren görevlilere yardımcı olacak ve Koronavirüs benzeri çıkabilecek yeni salgınların yayılımı önemli ölçüde azaltacaktır.
Optimization Based Control of Overcurrent Relays in Distribution Network Considering Real-Time Measurements: A Case Study
(Elsevier Sci Ltd, 2025) Unluturk, Ali; Ozer, Ishak
The coordination time interval (CTI) is very important in the coordination of overcurrent relays (OCRs). Although the CTI constraint is usually taken as 0.2 in the literature, it is also stated that it can be taken at different values. In the relay coordination carried out on a real power system serving in Erzurum/Turkey, the triping delay times (TDT) of OCRs and the contact opening delay times (CODT) of circuit breakers (CB) were measured and the CTI constraints in the coordination were determined according to the obtained measurements. This coordination process was transformed into an objective function (OF). This OF was solved with metaheuristic optimization algorithms. The Dandelion Optimization (DO) solution is better than spider wasp, golden jackal, zebra and dingo based optimization. Then, time multiplier setting (TMS) values are obtained from OF according to the CTI value determined according to the proposed real-time measurement and the CTI = 0.2 value frequently preferred in the literature. The performance of the relay TMS values obtained according to the proposed and classical methods was compared. Considering the power model and solution, 18.67% improvement in the operation times of the relays was achieved in Relay 2, 11.67% in Relay 3, 19.94% in Relay 4, 28.6% in Relay 6 and 23.31 % in Relay 7. The TMS value of Relay 5 is the same for the proposed and the classical method. As a result, the fast operation, reliability and selectivity of the power system were improved by ensuring correct relay coordination with the proposed method.
Performance Comparison of Advanced Control Strategies Based on Optimization for Active Suspension Under Real Vertical Speed Reducers Excitation
(IEEE-Inst Electrical Electronics Engineers Inc, 2025) Akgul, Tugrulhan; Unluturk, Ali
In this study, real vertical speed reducers (VSRs) were modeled according to the Institute of Transportation Engineers (ITE) standards and applied as road inputs to an active suspension system (ASS). Proportional-Integral-Derivative (PID), Fractional-Order-PID (FO-PID), Sigmoid-PID (S-PID), Sigmoid-Based Fractional-PID (SFO-PID), Exponential-PID (E-PID) and Linear Quadratic Regulator (LQR) controllers are designed for the ASS. The parameters of the controllers are optimized using methods such as Artificial Bee Colony (ABC), Golden Jackal Optimization (GJO), Mayfly Optimization (MFO), Particle Swarm Optimization (PSO), and Whale Optimization Algorithm (WOA). The root mean square (RMS) values of vertical body acceleration (VBA), vertical tire acceleration (VTA), suspension travel (SM), and dynamic load coefficients (DLC), which are the key performance indices of ASS, as well as error-performance indices such as integral of absolute value of error (IAE), integral of squared error (ISE), time integral of absolute value of error (ITAE), and time integral of squared error (ITSE), are compared with the advanced control methods and Passive Suspension (PS). The proposed MFO-E-PID provides 56.07% improvement in RMS values for VBA, 26.71% for VTA, 10.17% for SM, and 29.37% for DLC compared to PS; and 7.97% improvement in VBA, 3.99% for VTA, 2.37% for SM, and 2.77% for DLC compared to the second best, MFO-LQR. The MFO-E-PID method provided 30.45%, 49.99%, 23.58%, and 46.27% improvement in error-performance indices for IAE, ISE, ITAE, and ITSE, respectively, compared to PS; and 6.03%, 16.14%, 4.71%, and 17.20% improvement compared to MFO-LQR. Real-time tests have shown that MFO-E-PID improves ASS performance, safety, and comfort, and holds promise for future vehicles.
Üç Fazlı Merkezi İnvertör Topolojisine Sahip Güneş Enerjisi Santralinde Güç Üretiminin Gerçek Zamanlı İzlenmesi ve İşletimi
(2021) Unluturk, Ali; Sultan, Fatih
Bu makalede, üç fazlı merkezi inverter topolojisine sahipŞenyurt (Erzurum/Türkiye) Güneş Enerjisi Santrali (GES)güç üretiminin gerçek zamanlı olarak izlenmesi denetimi veişletimi ele alınmıştır. Çalışmada ilk olarak doğrudan şebekebeslemeli ve merkezi inverter topolojisine sahip ŞenyurtGES’in güç üretim modeli incelenmiştir. İkinci olarak,GES'in güç üretiminin izlenmesi ve denetimi için oldukçahayati öneme sahip güneş ışınımı sensörü, Fotovoltaik (FV)panel sıcaklık sensörü, dış ortam sıcaklık sensörü ve rüzgarhızı sensöründen elde edilen veriler değerlendirilmiştir. Busensörlerden elde edilen gerçek zamanlı veriler GES'debulunan Merkezi Denetim ve Veri Toplama (MD&VT)sistemi ile uyumlu olan uzaktan izleme arayüzü yardımıylaelde edilmiştir. Sensörlere ait verilerle GES’in bir günlükaktif güç üretiminin değişimine ait elde edilen grafikleryorumlanmıştır. Böylece GES’in kesintisiz aktif güçüretimine dair işletime denetimi gerçekleştirilmiştir. Sonolarak GES’de verimli bir şekilde güç üretiminingerçekleştirilebilmesi için gerekli olan FV panel yüzeyindebiriken karların temizliği, FV panellerde oluşan sıcak bölgearızalarının tespiti, FV panel dizilerine ait akım-gerilim (I-V)karakteristiklerinin ölçümleri gibi pratik saha uygulalarına dayer verilmiştir.