Yazar "Çoban, Melih" seçeneğine göre listele
Listeleniyor 1 - 10 / 10
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Comparative analysis of transformer fault classification based on DGA data using machine learning algorithms(Ieee, 2024) Çoban, Melih; Fidan, Murat; Aytar, OktayDissolved gas analysis (DGA) is considered a leading technique for fault classification in power transformers. However, accurate analysis results can only be achieved if the measured gases are interpreted, appropriately. In DGA interpretation, traditional techniques, artificial intelligence techniques such as machine learning algorithms, and hybrid techniques are generally used. In this study, four well-known machine learning algorithms have been compared in terms of DGA fault classification: Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Naive Bayes (NB) and Decision Tree (DT). The lowest accuracy rate was obtained as 63.63% using the NB algorithm and raw data. In addition to raw data, data converted to logarithmic form has been also used to develop classification models. The highest accuracy rate was determined as 94.54% using the DT algorithm and logarithmic data. The obtained results have been demonstrated the efficiency and stability of the DT algorithm for transformer fault classification, especially when the data was appropriately preprocessed.Öğe Design and application of a multipurpose universal high voltage incubator(Gazi Universitesi, 2024) Fidan, Murat; Çoban, MelihIt can be said that a commercial incubator is used in almost all scientific studies in which electric fields are applied to cell cultures under incubator conditions. This necessitates the use of test systems and electrodes that can fit inside a commercial incubator. For this reason, when the studies in the literature are examined, it is seen that the commercial incubator dimensions used in the studies require special design of the test system and electrodes. These restrictions can also narrow the boundaries of scientific study. Such that, due to the limitation of the internal volume of the commercial incubator used in scientific studies, the voltage values that can be applied to the sample cannot exceed a certain level. In this study, a multi-purpose universal system is introduced in which high voltages up to 100 kVpp can be applied to cell cultures or food samples under temperature, humidity and CO2 controlled incubator conditions. The system also allows the generation and application of pulsed electric fields up to 11.2 kV. The developed and proposed system is named as “High Voltage Incubator”. © 2024 Gazi Universitesi. All rights reserved.Öğe Design and application of a novel motorized traction device(Ieee, 2015) Fidan, Murat; Çoban, MelihTraction therapy which is a method is frequently used in the treatment of cervical disc hernia and hernia of the loins. Traction devices play big role in this therapy. One of the most commonly used traction device type is motorized traction device. Commercially available tackles apply tractive power to do patient depends on the some parameters which are duration and force level. If patients change their positions during the treatment, tractive power will covary with movement. In this study, motorized traction device has been designed and performed by using load sensors, dc motor and mechanical structure. The system has been controlled via microcontroller. Main focus of this design is to implement precision tractive power to the patient thanks to feedback from the sensors. Also realized traction system is cheaper than the other traction devices.Öğe Detection and classification of short-circuit faults on a transmission line using current signal(POLSKA AKAD NAUK, POLISH ACAD SCI, DIV IV TECHNICAL SCIENCES PAS, 2021) Çoban, Melih; Tezcan, Süleyman SungurThis study offers two support vector machine (SVM) models for fault detection and fault classification, respectively. Different short-circuit events were generated using a 154 kV transmission line modeled in MATLAB/Simulink software. Discrete wavelet transform (DWT) is performed on the measured single terminal current signals before fault detection stage. Three level wavelet energy values obtained for each of three-phase currents were used as input features for the detector. After fault detection, half cycle (10 ms) of three-phase current signals was recorded by a 20 kHz sampling rate. The recorded currents signals were used as input parameters for the multi-class SVM classifier. The results of the validation tests have demonstrated that quite a reliable fault detection and classification system can be developed using SVM. The faults generated were used for training and testing of SVM classifiers. An SVM-based classification and detection model was fully implemented in MATLAB software. These models were comprehensively tested under different conditions. The effects of the fault impedance, fault inception angle, mother wavelet and fault location were all investigated. Finally, simulation results verified that the study proposed can be used for fault detection and classification on the transmission line.Öğe Feed-forward neural networks training with hybrid taguchi vortex search algorithm for transmission line fault classification(MDPI, 2022) Çoban, Melih; Tezcan, Süleyman SungurIn this study, the hybrid Taguchi vortex search (HTVS) algorithm, which exhibits a rapid convergence rate and avoids local optima, is employed as a new training algorithm for feed-forward neural networks (FNNs) and its performance was analyzed by comparing it with the vortex search (VS) algorithm, the particle swarm optimization (PSO) algorithm, the gravitational search algorithm (GSA) and the hybrid PSOGSA algorithm. The HTVS-based FNN (FNNHTVS) algorithm was applied to three datasets (iris classification, wine recognition and seed classification) taken from the UCI database (the machine learning repository of the University of California at Irvine) and to the 3-bit parity problem. The obtained statistical results were recorded for comparison. Then, the proposed algorithm was used for fault classification on transmission lines. A dataset was created using 735 kV, 60 Hz, 100 km transmission lines for different fault types, fault locations, fault resistance values and fault inception angles. The FNNHTVS algorithm was applied to this dataset and its performance was tested in comparison with that of other classifiers. The results indicated that the performance of the FNNHTVS algorithm was at least as successful as that of the other comparison algorithms. It has been shown that the FNN model trained with HTVS can be used as a capable alternative algorithm for the solution of classification problems.Öğe Fuzzy logic based temperature control(Institute of Electrical and Electronics Engineers Inc., 2019) Çoban, Melih; Fidan, MuratOne of the advantages of using fuzzy logic controllers is that it does not require a mathematical model. It performs control process with verbal expression. In this study, temperature control of a treatment chamber using PIC16f877A microcontroller is presented and fuzzy logic controller design is made according to expert knowledge. Brief information about fuzzy logic and fuzzy logic controller is given. Triangular membership functions are used for input and output variables for ease of use. With the realized design, the temperature of the treatment chamber can be kept between 24 °C and 45 °C at the desired temperature. © 2019 IEEE.Öğe High voltage pulse generator for pulsed electric field treatments(Institute of Electrical and Electronics Engineers Inc., 2019) Çoban, Melih; Fidan, MuratIn food processing, biotechnology and medicine, pulsed electric field (PEF) applications are used in studies on increasing the permeability of the cell membrane or inactivation of microorganisms. PEF applications require high voltage pulse generators. PEF generators are designed depending on the application types. In this study, design and analysis of Metal Oxide Field Effect Transistor (Mosfet) based high voltage impulse generator for biology and medicine were studied. Two scenarios are considered for analysis. In the first scenario, a parallel connected Mosfet based pulse generator with 1400 V amplitude was analyzed. In the second scenario, a series connected Mosfet based pulse generator with 2500 V amplitude was analyzed. The results of the analysis were briefly compared. © 2019 IEEE.Öğe In vitro effects of direct and alternate electric fields on saos-2 cell line(Verduci Publisher, 2019) Fidan, Murat; Çamsarı, Çağrı; Çoban, Melih; Çetinkaya, Ayhan; Kılınç, ErkanObjective: The exposure of electric fields in daily life is greatly increased through the use of electronic devices, new transportation technologies and various other devices. Alternate current (AC) and direct current (DC) are the types of current flow in a circuit. However, their impacts at the cellular and tissue level, especially in bones, are not well known. Therefore, in the present study, our aim was to investigate the in vitro effects and potential differences of both 50 Hz AC and DC electric fields on osteosarcoma cell lines. We hypothesized that exposure of AC and DC electric fields increased the cell numbers in Saos-2 cell line. Patients and Methods: The cells were exposed to 50 Hz AC electric field at different levels (0, 2, 3, 4 and 5 kV/cm) and the cell numbers were determined after 24 hours of exposure. Likewise, the impact of 50 Hz AC electric field on cells was investigated 48 h after the exposure at the same levels. Moreover, cells were also exposed to DC electric field at different levels (0, 0.5, 1, 1.5 and 2.3 kV/cm). Results: Cell numbers in 4 kV/cm and 2 kV/cm AC electric field doses were increased after 24 h and 48 h of exposure, respectively, compared to controls. Likewise, the number of cells in 0.5 and 2.3 kV/cm exposure groups was increased 24 h after exposure to DC electric field. Conclusions: The results show the potential adverse effects of 50 Hz AC and DC electric fields by increasing the number of cells in osteosarcoma cell lines. However, since investigations were performed on a tumoral cell line, these results cannot indicate how electric fields would impact the transformation of normal cells to malignant cells.Öğe Performance analysis of machine Learning algorithms on power quality disturbances classification(Institute of Electrical and Electronics Engineers Inc., 2024) Gümüş, Birsen; Çoban, Melih; Tezcan, Süleyman SungurThe importance of the concept of power quality in electrical power systems is increasing. This situation causes the acceleration of work on detecting and eliminating power quality events. It is possible to automatically detect and classify these events using signal processing techniques and machine learning systems. In this study, the performances of Decision Tree (DT), Support Vector Machine (SVM), K Nearest Neighbor (KNN) and Naive Bayes (NB) classification algorithms were compared among themselves and with the literature. Signals containing 15 single and multiple power quality events were used for classification. Discrete Wavelet Transform (DWT) technique was preferred to extract the features of the signals. The data sets obtained by feature extraction were divided into test data and training data with a ratio of 20%, 30%, 40%. Thus, the classifiers were trained and tested with data sets of different sizes and their performances were evaluated. The highest accuracy rate was obtained as 99.75% with DT when 20% of the data set of noiseless signals was used as test data. The lowest accuracy rate was obtained as 30.6% with KNN when 30% of the data set of signals with 10dB noise was used as test data. In addition, the performances of the classifiers were examined by performing a 5-fold cross validation test and the average accuracy rates obtained from this were compared with other studies in the literature. © 2024 IEEE.Öğe Yüksek gerilimlerin oluşturduğu elektrik alanların kemik kanseri üzerindeki etkilerinin incelenmesi(Bolu Abant İzzet Baysal Üniversitesi, 2017) Çoban, Melih; Fidan, MuratYüksek gerilimlerin meydana getirdiği elektrik alanların kemik kanserine yakalanmış hastalar üzerindeki etkileri araştırılması gereken önemli bir konudur. Bu çalışma ile osteosarkom hücre kültürü üzerinde elektrik alan uygulaması yapabilen bir deney sistemi oluşturulmuş ve AA/DA yüksek gerilimlerin etkileri laboratuvar koşullarında incelenmiştir. Bu amaç doğrultusunda hücrelerin zarar görmeden yaşayabileceği koşullara ayarlanabilen deney sistemi gerçekleştirilmiş olup düzgün elektrik alan üretebilecek düzlemsel elektrotlar tasarlanmıştır. İncelemelerin yapıldığı 14 adet osteosarkom hücre hattı numunesi; kontrol grubu, birinci grup, ikinci grup ve üçüncü grup olmak üzere rastgele 4 gruba ayrılmıştır. Birinci ve ikinci grup numunelerine farklı şiddetlerde 50 Hz sinüzoidal elektrik alan 10 dakika boyunca uygulanmış olup birinci grubun incelemesi 24 saat sonra, ikinci grubun incelemesi ise 48 saat sonra yapılmıştır. Üçüncü grup numunelerine de farklı şiddetlerde DA elektrik alan 10 dakika boyunca uygulanmış olup grubun incelemesi 48 saat sonra gerçekleştirilmiştir. Uygulama sonuçlarına göre deney gruplarında bulunan osteosarkom hücrelerinin, kontrol grubundakilere oranla anlamlı bir şekilde fazla ürediği söylenebilmektedir (p<0.05). Ayrıca DA elektrik alanın 50 Hz sinüzoidal elektrik alana göre osteosarkom hücre sayısının daha fazla artmasına neden olabileceği gözlemlenmiştir. Bu tez çalışması sonucunda, belirli şiddetteki AA ve DA elektrik alanların, kemik kanseri hastalığının yayılma hızını artırıcı etkiye sahip olabileceği kanısına varılmıştır. ANAHTAR KELİMELER: Elektrik alan, Kemik kanseri, Hücre kültürü
