Yazar "Akbal, Bahadir" seçeneğine göre listele
Listeleniyor 1 - 15 / 15
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Applications of artificial intelligence and hybrid neural network methods with new bonding method to prevent electroshock risk and insulation faults in high-voltage underground cable lines(SPRINGER LONDON LTD, 2018) Akbal, BahadirThe sheath current causes cable faults and electroshocks in the high-voltage underground cable lines. Thus, the sheath current must be determined before a new high-voltage cable line is installed to take the required precautions against the sheath current effects. In this study, PSCAD/EMTDC is used for simulation of high-voltage underground cable line to examine the sheath current. The sheath current is forecasted with artificial neural network (ANN) by using the results of simulation studies, and differential evolution algorithm (DEA), genetic algorithm (GA), clonal selection algorithm (CSA), hybrid DEA-CSA, artificial bee colony (ABC), particle swarm optimization (PSO) and inertia weight PSO (iPSO) are used to find the best weights of ANN. The sheath current formation factors which are obtained in PSCAD/EMTDC are used as inputs of ANN. It is seen at the end of simulation studies that many factors affect the formation of the sheath current, so Pearson correlation is used to determine the most effective sheath current formation factors for inputs of ANN. In the literature, three types of bonding methods are used to reduce the sheath current and voltage, but these methods are not sufficient to reduce both sheath current and the sheath voltage simultaneously. Therefore, in this study, the sectional solid bonding method is developed as new bonding method to reduce the sheath voltage and current in this study. When the sectional solid bonding is used, the sheath voltage can be reduced under touch voltage, and the sheath current can be reduced under the desired value.Öğe Comparatıve Fault Locatıon Estımatıon By Usıng Image Processıng In Mıxed Transmıssıon Lınes(Selçuk Üniversitesi Mühendislik Fakültesi, 2020) Budak, Serkan; Akbal, BahadirOverhead lines are generally used for electrical energy transmission. Also, XLPE underground cable lines are generally used in the city center and the crowded areas to provide electrical safety, so high voltage underground cable lines are used together with overhead line in the transmission lines, and these lines are called as the mixed lines. The distance protection relays are used to determine the impedance based fault location according to the current and voltage magnitudes in the transmission lines. However, the fault location cannot be correctly detected in mixed transmission lines due to different characteristic impedance per unit length because the characteristic impedance of high voltage cable line is significantly different from overhead line. Thus, determinations of the fault section and location with the distance protection relays are difficult in the mixed transmission lines. In this study, 154 kV overhead transmission line and underground cable line are examined as the mixed transmission line for the distance protection relays. Phase to ground faults are created in the mixed transmission line. overhead line section and underground cable section are simulated by using PSCAD/ EMTDC ™. The short circuit fault images are generated in the distance protection relay for the overhead transmission line and underground cable transmission line faults. The images include the R-X impedance diagram of the fault, and the R-X impedance diagram have been detected by applying image processing steps. Artificial neural network (ANN) and the regression methods are used for prediction of the fault location, and the results of image processing are used as the input parameters for the training process of ANN and the regression methods. The results of ANN and regression methods are compared to select the most suitable method at the end of this study for forecasting of the fault location in transmission lines.Öğe Comparison of PSO-Kapur and DE-Kapur Methods to Determine Ice Load on Aerial Lines(IEEE, 2014) Akbal, Bahadir; Aydin, MusaAerial lines are designed according to the calculated a certain ice load amount. If ice load amount on conductor of aerial line is bigger than the calculated ice load amount, aerial line pole bending or conductor breakage can be seen. Joule effect method is proposed to eliminate ice load effect but primarily, the occurred ice load amount on conductor of aerial line must be determined. Ice load amount can be determined with ice thickness of iced conductor. In this study, ice thickness of iced conductor is determined with image segmentation method, but image segmentation is difficult due to high humidity. So, multilevel thresholding method was used to decrease high humidity effect. PSO-Kapur and DE-Kapur Methods were used as multilevel thresholding method. When these results were compared, it was seen that the result of DE-Kapur method was more close to value of real ice thickness according to the result of PSO-Kapur method.Öğe CSA-Kapur Method to Determine Ice Load Amount on Electric Transmission Line Conductors(IEEE, 2014) Akbal, Bahadir; Aydin, MusaIce load causes important faults on electric transmission lines (ETL), and power outages can be seen for days because of ice load. So, ice load effect must be prevented on ETL. One of the effect methods is Joule Effect Method (JEM). In JEM, ETL conductor is heated by current, and ice on conductor is melted. But primarily ice load amount must be determined to determine value of melting current. In this study, the iced conductor thickness was used to determine ice load amount, and image segmentation method was used to determine the iced conductor thickness. Image segmentation of image of iced conductor is difficult because of environmental factor. So, multilevel threshold method was used for image segmentation, and Kapur Method was used as multilevel threshold method. But detecting of optimal threshold levels with traditional Kapur Method is difficult. So, Clonal Selection Algorithm (CSA) was used to detect optimal threshold level.Öğe Detection of the Most Suitable Method to Estimate Short-Circuit Parameter's Values of the Electric Facility(TURGUT OZAL UNIV, 2012) Akbal, Bahadir; Urkmez, AbdullahShort-circuit is a damaging event for electrical facilities and electric networks. Thus short circuit capacity of a main circuit breaker of an electrical facility must be determined correctly. Otherwise, then circuit breaker cannot cut shortcircuit current, and so protection and measuring elements are damaged. Primarily short-circuit parameter values of electric facility which will be connected to an electrical network must be determined correctly to determine short-circuit capacity of main circuit breaker of electric facility. In this study, short circuit parameter's values of electric facility were estimated by using clonal selection algorithm (CSA) and genetic algorithm (GA). The end of this study, accuracy rate of estimated short-circuit parameters with CSA and GA was compared. The best solution algorithm was determined for these problems.Öğe Forecasting applications of the sheath current of high voltage cable with artificial neural network based hybrid methods(PAMUKKALE UNIV, 2017) Akbal, BahadirThe sheath current causes cable faults and electroshock risk in high voltage underground cable lines. Also the sheath current increases cable temperature and it reduces cable ampacity. Hence, cable performance decreases due to the sheath current. Different precautions can be taken to reduce the sheath current effects in high voltage underground cable line. However, primarily the sheath current must be detected at the project phase of high voltage underground cable line. In literature, artificial neural networks are used for forecasting studies. In this study, artificial neural network (ANN) is used with particle swarm optimization, particle swarm optimization with inertia weight and genetic algorithm to generate hybrid ANN methods for forecasting of the sheath current. High voltage underground cable line is modeled in PSCAD/EMTDC to measure the sheath current of different high voltage underground lines, and the obtained data from PSCAD/EMTDC are used to train artificial neural network based hybrid methods to forecast the sheath current of any high voltage underground cable line. When particle swarm optimization with inertia weight is used with artificial neural network, hybrid ANN-iPSO method is developed. The results of ANN-iPSO are better than the results of ANN-GA and ANN-PSO. If ANN-iPSO is used to determine the sheath current, the sheath current of high voltage underground cable line can be determined at the project phase of high voltage underground cable line. Hence, the most suitable precautions can be implemented, and cable faults and electroshock risk can be prevented, also cable performance is increased in high voltage underground cable line.Öğe GENETIC ALGORITHM TO SOLVE ELECTRICAL NETWORK PROBLEMS(IEEE, 2013) Akbal, Bahadir; Urkmez, AbdullahSome events which occur due to loads affect the electrical networks. These events can be sorted as overvoltage, short circuit, voltage drop, and power loss. Short circuit, voltage drop and power loss are related to the parameters of the power line which belongs to the electrical network, and overvoltage is related to parallel resonance. System impedance increases extremely during parallel resonance. If current of system (50Hz) or harmonic currents encounter high impedance, overvoltage occurs. In this study, parameters and parallel resonance power of the power line were estimated by using Genetic Algorithm (GA). If parallel resonance power is determined accurately, it isn't exceeded by load capacitor power, and parallel resonance doesn't occur. It was seen at the end of experimental results that estimation accuracy rate (EAR) of GA is adequate to solve these problems.Öğe Görüntü İşleme Ve Yapay Sinir Ağları İle İletim Hatlarında Arıza Yeri Belirleme(Selçuk Üniversitesi Mühendislik Fakültesi, 2020) Budak, Serkan; Akbal, BahadirElektrik enerjisinin kesintisiz ve kaliteli bir şekilde iletilmesi için, üretim yapıldığı noktadan tüketim olan noktaya kadar kontrol edilmesi gerekmektedir. Dolayısıyla üretimden tüketime kadar her aşamada iletim ve dağıtım hatlarında koruma yapılması şarttır. Elektrik tesislerinde koruma rölelerinin temel görevi, sistemde meydana gelen kısa devrelerde arızalı olan bölgenin mümkün olan en kısa sürede devre dışı etmektir. Sistemin en önemli parçası olan enerji iletim hatları ve bu hatları koruyan mesafe koruma rölelerine bu konuda çok önemli görevler düşmektedir. Hızlı ve verimli çalışmalar yapmak için doğru bir hata yeri tespit tekniği gereklidir. İletim hatlarında transformatör nötr nokta topraklaması bir güç sisteminin tek faz – toprak kısa devre arızası sırasında oluşan sıfır bileşen akımı mesafe koruma rölesinin çalışmasını etkilemektedir. Topraklama sistemi ve koruma sistemleri arasındaki ilişki göz önüne alındığında, uygun bir topraklama seçimi yapılmalıdır. İletim hatlarında farklı topraklama sistemlerinde kısa devre arızalarının yerinin doğru bir şekilde belirlenebilmesi için yapay sinir ağı (YSA) kullanılmıştır. YSA’nın performansını test etmek için destek vektör makineleri (DVM) ile karşılaştırılmıştır. İletim hattı modeli PSCAD ™ / EMTDC ™ benzetim programında oluşturulup YSA için gerekli veriler elde edilmiştir. Farklı topraklama sistemlerinde oluşturulan kısa devre arızalarındaki mesafe koruma rölesinin R-X empedans diyagramının empedans değişiminin görüntüsü kayıt altına alınarak veri setleri oluşturulmuştur. Görüntülerde ilgili odak noktaları özellik çıkarım ve görüntü işleme teknikleri kullanılarak farklı YSA modellerine giriş olarak verilmiş ve en iyi arıza yeri tahmini veren YSA modeli seçilmiştir.Öğe Hybrid ANN Methods to Reduce The Sheath Current Effects in High Voltage Underground Cable Line(IEEE, 2016) Akbal, BahadirThe sheath current generates on metal sheath of underground cable, and it causes cable faults, electroshock risk and reducing of cable performance in high voltage underground cable line. Therefore, the sheath current must be reduced, and if the sheath current can be determined before high voltage underground line is installed, the required precautions can be taken to reduce the sheath current. Hence, cable faults and electroshock risk are prevented, and cable performance increases. In this study, simulations of high voltage underground cable line are made in PSCAD/EMTDC, and the sheath current is forecasted by using hybrid artificial neural network (ANN) method. Differential evolution algorithm (DEA) and particle swarm optimization (PSO) are used to generate hybrid ANN method. The results of hybrid ANN method are better than classic ANN, and the results of DEA-ANN method are better than PSO-ANN. Also DEA-ANN can be used in forecasting studiesÖğe NEURAL-NETWORK-BASED CURRENT FORECASTING ON HIGH-VOLTAGE UNDERGROUND CABLES(ST JOHN PATRICK PUBL, 2016) Akbal, Bahadir[Abstract not Available]Öğe OSSB and Hybrid Methods to Prevent Cable Faults for Harmonic Containing Networks(KAUNAS UNIV TECHNOLOGY, 2018) Akbal, BahadirHigh temperature causes aging of insulation material of high voltage underground cable line (HVUL), so cable faults occurs. The sheath current (SC) is the most important factor for increasing of cable temperature, and SC can include harmonic, so cable temperature quickly increases. Namely harmonics facilitate SC based cable faults. Metallic sheath of HVUL is grounded to prevent SC based faults. Three bonding methods are used for grounding of metallic sheath in literature, but these methods do not exactly prevent SC effects, so the sectional solid bonding (SSB) is developed in literature, but these methods are not evaluated at the high harmonic distortion case. SSB should be optimized according to SC value. However, SC of HVUL which will be installed as a new line at project phase is not known. Thus, artificial neural network (ANN) and hybrid ANN methods are used to forecast SC of new line at the project phase. iPSO, PSO, GA and DEA methods are used for hybrid ANN methods and optimization of SSB. Performance of the optimized SSB (OSSB) at the high harmonic distortion case is evaluated to prove that use of OSSB for HVUL.Öğe The parallel resonance impedance detection method for parameter estimation of power line and transformer by using CSA, GA, and PSO(TUBITAK SCIENTIFIC & TECHNICAL RESEARCH COUNCIL TURKEY, 2016) Akbal, Bahadir; Urkmez, AbdullahPower line parameters are an important factor in relay applications and power quality studies. In the literature, the phasor measurement unit method and measuring of current and voltage at two ends of the power line were usually used to estimate the power line parameters. In this study, the parallel resonance impedance detection method was used to estimate the power line parameter to obtain input data. The real measurement values are used to obtain parallel resonance impedance in this method. The real measurement values include the measurement errors of the current and voltage transformer. Thus, the estimated parameter values are realistic. The electrical network with has 27 busbars that belongs to an organized industrial zone in Turkey was used for the application. Harmonic measurement of the power line of the electrical network was made to obtain parallel resonance impedance. The obtained parallel resonance impedance was used in the maximization problem. The maximization problem was defined as the estimated accuracy rate and was solved by using the clonal selection algorithm, genetic algorithm, and particle swarm optimization to make the most realistic parameter estimation. These methods can be defined as parameter estimators and are selected because they are all used widely in electrical engineering problem solutions. The results of these methods were compared with real parameter values, and accuracy of the estimate was determined for each method.Öğe PSO and CSA to Estimate of Parameter in Power Line(IEEE, 2013) Akbal, Bahadir; Urkmez, AbdullahShort circuits, voltage drop, harmonic distortion and power loss which is factors affect to power quality of power line as negative. Power line parameters affect to values of these factors. Therefore, power line parameters affect the quality of the electrical energy of transmission and distribution lines. Before new load is included to power line, power line parameters must be determined and so adversely effect of these factors can be prevented. In this study, parameters of power line, which will be added new load, were estimated by using clonal selection algorithm (CSA) and particle swarm optimization (PSO). The results of these two methods were compared with real parameter value of power line and accuracy rating of these methods was determined separately. Primarily, harmonic measurement was made from load connection point of power line and was determined parallel resonance impedance to determine power line parameter from the connection point of new load. The obtained parallel resonance impedance from this measurement result was evaluated with CSA and PSO and so power line parameters were tried to estimate. The end of this study, accuracy rate of CSA and accuracy rate of PSO were compared and the algorithm which had the best results was selected.Öğe PSO and Inertia Weight to Determine Parallel Resonance Power in Electrical Networks(IEEE, 2013) Akbal, Bahadir; Urkmez, AbdullahOvervoltage phenomena should be taken into account at planning of transmission and distribution lines. Causes of over voltage are usually switching, lightning and parallel resonance. The most dangerous of these reasons can be the parallel resonance. The parallel resonance occurs between system impedance and capacitors of reactive power compensation of electrical plant. Before an electrical plant (any factory) is connected to connection point of power line of electrical network, parallel resonance of connection point of power of power line must be determined previously to prevent parallel resonance. Otherwise, system impedance increases extremely during parallel resonance, and if current of system (50Hz) encounters high impedance during parallel resonance, high voltage occurs on electric network. So, total capacitor power should be less than the parallel resonance power. In this study, the application which related to determination of parallel resonance power was made by using PSO, and also effect of inertia weight on PSO was examined for this study. Thus parallel resonance power of low voltage electric network can be calculated and maximum capacitor of compensation system can be determined.Öğe Radyal Şebekelerde Destek Vektör Regresyon İle Optimum Kablo Topraklama Sistemi Tasarımı(Selçuk Üniversitesi Mühendislik Fakültesi, 2020) Akbal, BahadirTeknolojinin gelişmesi ile elektrik şebekelerindeki yüklerin çeşitliliği de artmıştır. Bu çeşitli yükler şebekede sıfır bileşen ve harmonik akımlarını artırarak yüksek gerilim yeraltı kablolarında başlık arızalarına neden olmaktadır. Uygulamada kablo başlığı arızalarını önlemek için genellikle IEEE 575-1988 standardında yer alan çift taraflı topraklama (ÇTT) yöntemi kullanılmaktadır. Fakat bu yöntem sıfır bileşen ve harmonik akımlarının neden olduğu kablo başlığı arızalarını önlemek için yeterli değildir. Bu çalışmada yeni bir yöntem olan Parçalı Çift Taraflı Topraklama (PÇT) yöntemi ile ÇTT yöntemi karşılaştırılmıştır. PÇT yönteminin kullanılması için kabloda oluşacak olan kılıf geriliminin bilinmesi gereklidir. Bu yüzden Destek Vektör Regresyon (DVR) yöntemleri ile kılıf gerilimi tahmini yapılmıştır. Daha sonra kablo arızalarını ve elektrik çarpılmalarını önlemek için PÇT yöntemi dokunma gerilimine göre optimize edilmiştir. Optimizasyon yöntemleri olarak da Parçacık Sürü Optimizasyonu, İnertia Ağırlıklı Parçacık Sürü Optimizasyonu, Çekimsel Arama Algoritması ve Genetik Algoritma kullanılmıştır. Çalışma sonunda, yüksek gerilim kablosunun topraklamasının ÇTT yöntemi ile yapılması durumunda kılıf geriliminin dokunma gerilimini aştığı görülmüştür. Bu durum dengesiz elektrik alanı nedeniyle kablo arızasına, yüksek gerilim nedeniyle de elektrik çarpılmasına neden olmaktadır. Aynı hat için tasarlanan optimize edilmiş PÇT yöntemlerinde ise kılıf gerilimi aşılamamıştır. Böylece PÇT yöntemi ile hem kablo arızalarının hem de elektrik çarpılmalarının önüne geçilecektir