Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection

Permanent URI for this collectionhttps://hdl.handle.net/11147/7148

Browse

Filters

20252

Settings

Author: search.filters.author.Roozbahan, M.COAR Access Rights: search.filters.coarAccessRights.metadata only access

Search Results

Now showing 1 - 2 of 2
  • Article
    Predicting the Area Moment of Inertia of Beam and Column Using Machine Learning and Hypernetexplorer
    (Springer Science and Business Media Deutschland GmbH, 2025) Aydın, Y.; Nigdeli, S.M.; Roozbahan, M.; Bekdaş, G.; Işıkdağ, Ü.
    Beams and columns are the most important elements of steel frame structures. Damage to the beam or column can lead the structure to serious hazards and cause collapse. In the structural engineering literature, it has been observed that there is not much work for area moment of inertia estimation of beam and column. The aim of this study was to predict the area moment of inertia of beam and column using HyperNetExplorer developed by the authors. This method aims to bring innovation by optimizing artificial neural networks (ANNs). In this study, a prediction study is performed using 306 collected data on beam and column area moment of inertia. Classical ML models (linear regression (LR), decision tree regression (DTR), K neighbors regression (KNN), polynomial regression (PR), random forest regression (RFR), gradient boosting regression (GBR), histogram gradient boosting regression (HGBR)) and NAS and HyperNetExplorer were applied to predict beam and column area moment of inertia. The prediction performances were compared using different performance metrics (coefficient of determination (R2) and mean squared error (MSE)) and HyperNetExplorer developed by the authors showed the highest performance (R2 = 0.98, MSE = 246.88). Furthermore, SHapley additive explanations (SHAP) were used to explain the effects of features in the prediction models and it was observed that the most effective features for model predictions were loading on beam and length. The results show that the proposed NAS base approach and the developed tool, HyperNetExplorer, provides better performance when compared with classical ML methods. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.
  • Article
    Citation - WoS: 1
    Citation - Scopus: 1
    Effect of Soil Water Content Changes on the Behavior of Buildings Equipped With Single and Double Tuned Mass Dampers Subjected To Earthquakes
    (Springer Science and Business Media Deutschland GmbH, 2025) Roozbahan, M.; Turan, G.
    Tuned mass dampers (TMDs) are one of the structural control systems that have been frequently used in the last century. A TMD is designed according to the properties of the main system. In building applications, the substructure’s soil affects the response of buildings, especially in soft-type soils. Therefore, the soil properties should be included in the analysis and design of tuned mass dampers. However, the soil properties are not always identical and vary due to different factor changes such as soil water content changes. Unlike previous research, which typically assumes constant soil properties, this study incorporates the impact of soil water content changes, a key factor that can significantly alter soil behavior. This study aims to evaluate the effectiveness of optimized single and double tuned mass dampers (DTMDs) in response reduction of buildings considering the changes in the water content of soil. In this study, a metaheuristic-based optimization method is programmed to optimize TMDs and DTMDs for low-, mid-, and high-rise buildings considering soil-structure interaction (SSI). The efficiency of the optimized tuned mass dampers on the response reduction of buildings due to changes in soil water content is evaluated. According to the investigated results of 14 near-field earthquake simulations, it is concluded that the efficiency of the TMDs is significantly affected by changes in soil water content. Moreover, according to the result, the DTMD efficiency is slightly better than the TMD-controlled structure. © Springer Nature Switzerland AG 2025.