Yazar "Ahmet Selim Dalkilic" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Öğe
    A comprehensive method for exploratory data analysis and preprocessing the ASHRAE database for machine learning
    (Elsevier BV, 2025-08) Amir Rahmanparast; Muhammed Milani; Muhammet Camci; Yakup Karakoyun; Ozgen Acikgoz; Ahmet Selim Dalkilic
    Thermal comfort prediction is crucial for building energy efficiency and occupant comfort. ML methods are commonly used to predict thermal comfort. This research presents a comprehensive process for exploring and preprocessing the ASHRAE Database, providing a substantial dataset comprising 107,583 records of thermal comfort observations to create ML algorithms that can estimate Fanger's PMV. With the most detailed cleaning and preprocessing stages in the literature, which included the imputation of missing values and the management of outliers, the final dataset is reduced to 55,443 records for the analyses. For practical applications and indoor comfort assessments, its estimation offers significant advantages due to its speed, ease of use, and cost-effectiveness. This study aimed to investigate which parameters are important in Fanger's PMV model and which subset of variables is best for variable selection using different feature selection and analysis methods. The Ta and Tr had a high correlation value of 0.92, indicating a robust link between these two variables. The study employed Feature importance, the SelectKBest, SHAP, P-box, and PDP analyses, which showed consistency and suggested condensing the first six elements into three, and also was validated with the Chinese Database with 41,977 entries. The study targeted three parameters: Ta, clo, and M, using less expensive and simple measurement devices. To evaluate the accuracy of the research performance, RF and SVM models were created based on these three parameters. The results indicated that they have the accuracies of 85% and 70%, respectively, which are far better than the conventional models.
  • Küçük Resim
    Öğe
    A new hybrid CFD approach to study the impact of forced convection on radiant cooled wall with baseboard diffuser including various vane angles
    (Elsevier BV, 2025-07) Melek Caliskan Temiz; Aykut Bacak; Muhammet Camci; Yakup Karakoyun; Ozgen Acikgoz; Ahmet Selim Dalkilic
    The current work examines the effect of forced convection on thermal comfort in a space, including radiant wall cooling and an innovative floor-level diffuser system. It examines the impact of various vane angles on thermal comfort in room air conditioning at 15°, 30°, 45°, 60°, and 75°, and employs experimental data to confirm a hybrid 3D computational fluid dynamics (CFD) model. A new floor-level diffuser system delivers air at temperatures between 18 °C and 22 °C, with supply air velocities of 5 m/s and 10 m/s measured at the exit side of diffuser while the supply water temperature is kept constant at 14 °C. In the hybrid 3D solution, experimentally derived convective heat transfer coefficients (CHTCs) for forced airflow are utilized. This is accomplished by merging a k-ω model with a hydronic radiant panel system that incorporates forced convection. The analysis examines temperature and velocity distributions, CHTCs on the radiant-cooled wall, and the PMV-PPD components. Results indicate that at a supply air velocity of 5 m/s, thermal comfort parameters do not satisfy PMV and PPD indices, except in proximity to the diffuser. Nevertheless, elevating the supply air velocity to 10 m/s ensures thermal comfort across the space, with the exception of regions next to the cooled wall surfaces. The examination of several vane angles indicated that a 45° angle yields the most advantageous thermal comfort conditions, irrespective of air velocity. The CHTC adjacent to the radiant wall is roughly 6 W/m2K at a velocity of 5 m/s and rises to 8 W/m2K at 10 m/s. The temperature disparity between the head and ankle regions at 5 m/s adheres to the 3 °C tolerance established by international standards. The study determines that a 45° vane angle ensures best thermal comfort, and the devised numerical method yields significant insights for the construction of analogous indoor settings.