Yazar "Bicen, Yunus" seçeneğine göre listele

Listeleniyor 1 - 6 / 6
  • Küçük Resim
    Öğe
    Assessment of machine learning, time series, response surface methodology and empirical models in prediction of global solar radiation
    (Elsevier Sci Ltd, 2020) Gurel, Ali Etem; Agbulut, Umit; Bicen, Yunus
    Solar radiation (SR) knowledge plays a vital role in the design, modelling, and operation of solar energy conversion systems and future energy investment policies of the governments. However, these data are not measured for all regions due to the non-availability of SR measurement equipment at the weather stations. Therefore, SR has to be accurately predicted using various prediction models. In this research, four models from different classes are being used to predict monthly average daily global SR data. The models used in this study are based on a machine-learning algorithm (feed-forward neural network), empirical models (3 Angstrom-type models), time series (Holt-Winters), and mathematical model (RSM). As the prediction locations, four provinces (Ankara, Karaman, Kilis, and Sirnak) in Turkey are selected. The dataset including pressure, relative humidity, wind speed, ambient temperature, and sunshine duration is supplied from the Turkish State Meteorological Service and it covers the years 2008-2018. In the study, monthly average daily global SR data for the year 2018 is being predicted, and the performance success of the models is discussed in terms of the following benchmarks R-2, MBE, RMSE, MAPE, and t-stat. In the results, R-2 value for all models is varying between 0.952 and 0.993 and MAPE and RMSE value for all models is smaller than 10% and 2 MJ/m(2)-day, respectively. Evaluation in terms of t-stat value, no models exceed the t-critic limit. Considering all the models together, ANN has presented the best results with an average R-2, MBE, RMSE, MAPE, and t-stat of 0.9911, 0.1323 MJ/m(2)-day, 0.78 MJ/m(2)-day, 4.9263%, and 0.582, respectively. Then Holt-Winters, RSM, and empirical models closely followed it, respectively. (C) 2020 Elsevier Ltd. All rights reserved.
  • Küçük Resim Yok
    Öğe
    Experimental determination of electrical and thermo-physical characteristics of dielectric nanofluids based on volume fraction change
    (Elsevier Science Sa, 2023) Karatas, Mehmet; Bicen, Yunus
    Dielectric insulating fluids perform critical tasks such as electrical insulation and cooling functions in power system equipment. Improving the thermal properties of insulating fluids extends the service life of power equipment, while improving their dielectric properties ensures a reliable and safe electricity supply. Therefore, studies on enhancing the thermal and dielectric qualities of dielectric fluids using nanoparticles have become more popular in recent years. In this study, the dielectric and thermo-physical properties of mineral oil-based SiO2 nanoparticle suspensions, namely nanofluids, have been investigated. An approximately 25.6% enhance-ment in AC breakdown voltage level has been obtained at a 0.05% critical volume fraction. It has been noted that the level of the AC breakdown voltage decreases when the critical volume fraction is exceeded. The thermal conductivity of the prepared nanofluid has changed logarithmically in the positive direction according to the rising number of nanoparticles per unit volume. Thermal conductivity has increased by around 8.55% for the critical volume fraction value, whereas thermal diffusivity has increased by approximately 22%. Similarly, when the number of particles in the nanofluid rises, the viscosity increases nonlinearly. The viscosity increase, which is undesirable for heat transfer, has been determined to be around 10.64% for the crucial volume fraction. These findings indicate that dielectric nanofluids hold significant potential for the future. The SEM analysis, on the other hand, explains the difficulties of assuring the long-term stability of nanofluids in the volume fraction with the highest AC dielectric breakdown voltage.
  • Küçük Resim
    Öğe
    Measurements and performance evaluations of natural ester and mineral oil-immersed identical transformers
    (Elsevier Sci Ltd, 2021) Cilliyuz, Yusuf; Bicen, Yunus; Aras, Faruk; Aydugan, Guzide
    The use of natural esters as an insulating liquid has become popular since the early 2000s. Studies in the literature emphasize the superiority of natural esters as compared to mineral oils. In these studies, the prominent properties of natural esters are presented as being environmentally friendly, safe, and delaying the aging of cellulosic insulation material. Although there is no doubt in terms of their characteristics, such as being environmentally and safe, exaggerated comments are made about the delay of aging of the paper material used in the insulation of transformer windings. This is because comparative experimental applications on mineral oil and natural esters are carried out under artificial and equal conditions provided in the laboratory environment. Whereas, performing these experiments on identical transformers will give more realistic results. In this study, two identical transformers were designed and equipped with precision fiber optic temperature sensors. Temperature differences that vary depending on the load between high voltage and low voltage windings were measured with a high degree of accuracy for both identical transformers. Besides these measurements, physical and chemical changes were analyzed on samples taken from insulation liquids. It was observed that the physical and chemical properties of the insulation liquids directly affect the operating performance of the transformers. Thanks to the differences in viscosity of insulating liquids, the heat dissipation due to losses in the windings were different for both transformers. Both heat distribution and temperature differences in the windings varied depending on the loading factors. Considering all these factors together, comprehensively evaluations were made on the aging rate of cellulosic insulation and the service life of the transformers.
  • Küçük Resim
    Öğe
    Numerical analysis and application of electric field grading device for metal-enclosed switchgear
    (Springer International Publishing Ag, 2021) Arslan, Serdal; Bicen, Yunus; Binarbasi, Omur
    Electric field grading devices have great importance for both the electric power transmission and distribution systems. This paper presents an improved electric field grading device used in the medium voltage metal-enclosed switchgear. The solutions have been carried out by using Ansys Maxwell 3D software. The structure of two electrodes designed as cylindrical and elliptical have been compared to determine the electric field grading device to be used in practice. The transient and steady-state analyses have been performed in both designs. The field grading device manufactured for the metal-enclosed switchgear has been tested according to IEC standards in a high voltage laboratory environment. This study revealed that the newly designed field-grading device can be used in the metal-enclosed switchgear more safely. It also encourages researchers to optimize the electric field distribution using different geometric structures and to create running conditions in smaller indoor environments.
  • Küçük Resim
    Öğe
    Prediction of daily global solar radiation using different machine learning algorithms: Evaluation and comparison
    (Pergamon-Elsevier Science Ltd, 2021) Agbulut, Umit; Gurel, Ali Etem; Bicen, Yunus
    The prediction of global solar radiation for the regions is of great importance in terms of giving directions of solar energy conversion systems (design, modeling, and operation), selection of proper regions, and even future investment policies of the decision-makers. With this viewpoint, the objective of this paper is to predict daily global solar radiation data of four provinces (Kirklareli, Tokat, Nevsehir and Karaman) which have different solar radiation distribution in Turkey. In the study, four different machine learning algorithms (support vector machine (SVM), artificial neural network (ANN), kernel and nearest-neighbor (k-NN), and deep learning (DL)) are used. In the training of these algorithms, daily minimum and maximum ambient temperature, cloud cover, daily extraterrestrial solar radiation, day length and solar radiation of these provinces are used. The data is supplied from the Turkish State Meteorological Service and cover the last two years (01.01.2018-31.12.2019). To decide on the success of these algorithms, seven different statistical metrics (R-2, RMSE, rRMSE, MBE, MABE, t-stat, and MAPE) are discussed in the study. The results shows that R2, MABE, and RMSE values of all algorithms are ranging from 0.855 to 0.936, from 1.870 to 2.328 MJ/m(2), from 2.273 to 2.820 MJ/m(2), respectively. At all cases, k-NN exhibited the worst result in terms of R-2, RMSE, and MABE metrics. Of all the models, DL was the only model that exceeded the t-critic value. In conclusion, the present paper is reporting that all machine learning algorithms tested in this study can be used in the prediction of daily global solar radiation data with a high accuracy; however, the ANN algorithm is the best fitting algorithm among all algorithms. Then it is followed by DL, SVM and k-NN, respectively.
  • Küçük Resim Yok
    Öğe
    Smart asset management system for power transformers coupled with online and offline monitoring technologies
    (Pergamon-Elsevier Science Ltd, 2023) Bicen, Yunus; Aras, Faruk
    Predictive maintenance strategies have gained popularity in recent years due to the advantages they provide over traditional maintenance strategies. Online monitoring technologies are critical for implementing predictive maintenance strategies. However, in some cases, the information generated by online systems may not be accurate and may need to be verified with offline monitoring technologies. In this study, a fault-sensitive matrix-based smart asset management system that is compatible with both online and offline technologies has been developed for power transformers. The developed system has the ability to assess multi-input parameters simultaneously and holistically. Because of the system's matrix structure, having a large number of input parameters or expanding them later is not an issue. Furthermore, the algorithms that will evaluate the input parameters are independent and distinct from one another. Because of its compatibility with the data acquisition card and its design options for the user interface, LabVIEW has been chosen for the system's development. The functionality of the system has been tested by deliberately generating faults in a test cell. While the high-resolution sensor data obtained and the calculated results are displayed on the interface, the failure probabilities are evaluated and displayed in a separate window. Intentionally generated faults have been diagnosed with high accuracy after going through the online monitoring and offline verification processes.