Yazar "Olmus, Umutcan" seçeneğine göre listele

Listeleniyor 1 - 6 / 6
  • [ X ]
    Öğe
    Comprehensive modelling of rotary desiccant wheel with different multiple regression and machine learning methods for balanced flow
    (Pergamon-Elsevier Science Ltd, 2021) Guzelel, Yunus Emre; Olmus, Umutcan; Cerci, Kamil Neyfel; Buyukalaca, Orhan
    In this paper, several alternative models were developed with multiple linear regression and machine learning algorithms to determine the output states of silica gel desiccant wheels for balanced flow. The decision tree method was used for this purpose for the first time in open literature. All the models developed include six input parameters and a wider range than those available in the literature. Predictions from the models were compared with the master dataset used to derive the models, each of the five sub-datasets that make up the master dataset and with data available in the literature. It was determined that the most suitable models are those coded as multiple linear regression-IV (MLR-IV), multilayer perceptron regressor-III (MLPR-III) and decision tree-VII (DTVII), and DT-VII is the best among them. The determination coefficient and root mean square error for temperature were found to be 0.9894 and 0.8743 degrees C for MLR-IV, 0.9817 and 1.1526 degrees C for MLPR-III, 0.9986 and 0.3295 degrees C for DT-VII, respectively. The corresponding values for humidity ratio were 0.9912 and 0.3701 g kg(-1) for MLR-IV, 0.9885 and 0.4227 g kg(-1) for MLPR-III, 0.9994 and 0.0995 g kg(-1) for DT-VII, respectively. The results obtained revealed that the proposed models can be used safely in preliminary design, simulation and dynamic energy analysis of systems with desiccant wheels.
  • [ X ]
    Öğe
    Effect of operating parameters on the performance of rotary desiccant wheel energized by PV/T collectors
    (Yildiz Technical Univ, 2023) Olmus, Umutcan; Guzelel, Yunus Emre; Cerci, Kamil Neyfel; Buyukalaca, Orhan
    The main energy input of a desiccant air conditioning system is the low-quality thermal energy required for regeneration, which can be obtained from waste heat, geothermal resources or solar energy. Regeneration thermal energy can be produced as well as energizing components such as fans, pumps, auxiliary air heaters, and control elements of the system by using photovoltaic-thermal solar collectors (PV/T). In this study, parametric analyzes were performed to investigate the effect of regeneration temperature and air frontal velocity on the temperature and dehumidification performance of a solid silica-gel desiccant wheel and on the water-cooled PV/T collectors used to provide the regeneration thermal energy. The regeneration temperature was varied between 50 and 70 degrees C, and air frontal velocity between 1.3 and 4.1 m/s. The analyzes show that the dehumidification efficiency increases from 13.94% to 33.04% as regeneration temperature increased from 50 degrees C to 70 degrees C at 1.3 m/s air frontal velocity at which dehumidification efficiency is maximum. At 4.1 m/s air frontal velocity, the required regeneration thermal energy is maximum and increases from 49.64 kW to 132.48 kW at the same regeneration temperature change. The low regeneration temperature resulted in desirable latent performance and undesirable sensible heat transfer performance in DEW. Finally, considering the whole system, it was concluded that the optimum regeneration air temperature for the performance parameters is 60 degrees C.
  • [ X ]
    Öğe
    New multiple regression and machine learning models of rotary desiccant wheel for unbalanced flow conditions
    (Pergamon-Elsevier Science Ltd, 2022) Guzelel, Yunus Emre; Olmus, Umutcan; cerci, Kamil Neyfel; Buyukalaca, Orhan
    In this study, five Multiple Linear Regression, three Multilayer Perceptron Regressor, seven Decision Tree and four Support Vector Machine models were constructed to predict outlet temperature and humidity ratio of silica gel desiccant wheels using eight input parameters for unbalanced flow condition. The effect of different kernel functions of Support Vector Machine algorithms, on the modeling of desiccant wheel was investigated for the first time in the open literature. Detailed validation of the developed models showed that the Response Surface model outperformed other Multiple Linear Regression models, and the Support Vector Machine model with Pearson VII Universal kernel was the best among all models. The determination coefficient and root mean square error for temperature were found to be 0.9791 and 1.2832 degrees C for the Response Surface model and, 0.9984 and 0.3511 degrees C for the Support Vector Machine model with Pearson VII Universal kernel, respectively. In the case of humidity ratio, the corresponding statistical parameters were 0.9763 and 0.5672 g/kg for the former and, 0.9976 and 0.1810 g/kg for the latter. The proposed models can be used reliably in the analysis of solid desiccant-based air conditioning systems for design and energy analysis.
  • [ X ]
    Öğe
    Numerical analysis and comparison of different serpentine-based photovoltaic-thermal collectors
    (Pergamon-Elsevier Science Ltd, 2025) Olmus, Umutcan; Guzelel, Yunus Emre; Cerci, Kamil Neyfel; Buyukalaca, Orhan
    This study investigated the performance of 25 serpentine-based photovoltaic-thermal (PVT) collector configurations using numerical modeling with COMSOL Multiphysics software. The analysis compared single-inlet, double-inlet and triple-inlet configurations, with tubes arranged both horizontally and vertically, while maintaining constant geometric properties. Some of the configurations examined were studied for the first time in the open literature. The analyses were conducted in two stages. First, all configurations were compared under base- case conditions using various energetic and exergetic performance metrics. The results revealed that configurations K1 and M, which are novel, and configuration B demonstrated superior performance. Second, the effects of water inlet temperature, flowrate, and solar irradiance on the temperature distribution and efficiency metrics were evaluated for the top three performing configurations. The findings showed that these configurations exhibited similar trends in response to changes in operating conditions. Specifically, increasing the flowrate significantly enhanced thermal, electrical, and primary energy saving efficiencies, while higher water inlet temperatures led to reductions in all efficiency metrics. Moreover, pressure drop decreased as the number of inlets increased. The research emphasizes the importance of selecting a design to enhance the performance of PVT collector based on the various performance metrics.
  • [ X ]
    Öğe
    Numerical investigation and ANN modeling of performance for hexagonal boron Nitride-water nanofluid PVT collectors
    (Elsevier, 2023) Buyukalaca, Orhan; Kilic, Haci Mehmet; Olmus, Umutcan; Guzelel, Yunus Emre; Cerci, Kamil Neyfel
    In this study, performance of hexagonal boron nitride (hBN)/water nanofluid used as a coolant in a PVT collector for the first time in the open literature was numerically analyzed based on various input parameters. Numerical analyzes were carried out by varying the flow rate between 14.5 and 43.4 l/h, solar radiation intensity between 200 and 1000 W/m2, hBN nanoparticle volumetric ratio between 0 and 0.22% and nanoparticle diameter between 20 and 80 nm. The results revealed that the thermal efficiency increases up to 0.18 volumetric ratio and then decreases, while the electrical efficiency continuously increases as the volumetric ratio increases. Additionally, an increase in the volumetric ratio leads to an improvement in all exergy parameters. The utilization of 20 nm diameter hBN nanoparticles results in an increase of 0.7%, 3.01%, 2.71%, and 1.80% in electrical, thermal, overall, and exergy efficiency, respectively, in comparison to pure water. In addition to the numerical analysis conducted with hBN/water nanofluid, simulations were also performed for graphene/water nanofluid, which is commonly studied for PVT collectors in the literature, and it was shown that the former exhibits better performance than the latter, albeit to a minimal extent. Finally, two different sets of ANN models were developed to predict five performance parameters of the PVT collector using hBN/water nanofluid. In the first set, each model predicted only one of the five performance parameters, while in the second set, a single ANN model predicted all output parameters. Different numbers of neurons and training functions were tested in the ANN models, and the Feed Forward Backpropagation algorithm was used as the training algorithm for all the models. Additionally, Logsig and Purelin transfer functions were used for the hidden and output layers, respectively. The proposed models were able to successfully reproduce the performance parameters.
  • [ X ]
    Öğe
    Predicting process and regeneration air conditions in LT3 molecular sieve desiccant wheels using machine learning and regression methods
    (Pergamon-Elsevier Science Ltd, 2025) Guruk, Alperen Burak; Guzelel, Yunus Emre; Olmus, Umutcan; Cerci, Kamil Neyfel; Buyukalaca, Orhan
    The performance of desiccant wheels is influenced by various design and operational variables. Existing models in the literature for LT3 molecular sieve desiccant wheels often include only a limited number of input parameters or have restricted operating ranges. This study addresses these limitations by generating a dataset encompassing 32,975 scenarios, which was used to develop 192 models using four methods such as multiple linear regression (MLR), decision tree (DT), support vector machine (SVM), and multilayer perceptron (MLP). The models were categorized into two groups to allow for various analyses. Group A models predict the process air outlet conditions of the desiccant wheel, namely temperature (Tpo) and humidity (omega po). Group B models, in contrast, predict the required regeneration air inlet temperature (Tri) necessary to achieve a desired process air exit humidity (omega po), while also predicting Tpo. MLP models demonstrated the best accuracy across both groups. In Group A, the model coded as MLP-7 achieved an RMSE of 0.2017 degrees C for Tpo, and MLP-6 yielded an RMSE of 0.0656 g/kg for omega po. In Group B, MLP-7 recorded an RMSE of 0.1764 degrees C for Tpo, while Tri had an RMSE of 0.7892 degrees C. Additionally, in Group A, the models coded as RS, 3rdCross, DT-28, and SVM-5 also delivered reliable results, while in Group B, the RS, 2ndCross, 3rdCross, DT-28, and SVM-3 models performed well.