İnşaat Mühendisliği
Bu koleksiyon için kalıcı URI
Gözat
Son Başvurular
1 - 5 / 18
-
Öge10. Türkiye Deprem Mühendisliği Konferansı, 8-10 Ekim 2025 : Türkçe bildiriler kitabı(İTÜ Yayınevi, 2025)10. Türkiye Deprem Mühendisliği Konferansı, TMMOB İnşaat Mühendisleri Odası İstanbul Şubesi ile Türkiye Deprem Vakfı – Deprem Mühendisliği Komitesi ortaklığında 8–9–10 Ekim 2025 tarihlerinde İstanbul Teknik Üniversitesi Süleyman Demirel Kültür Merkezi’nde gerçekleştirilecektir. Bu yıl ikinci kez uluslararası nitelikte düzenlenen konferansımız, 1985 yılında gerçekleştirilen ilk sempozyumdan bu yana ülkemizde ve dünyada deprem mühendisliği alanındaki güncel bilgi birikimini, deneyimleri ve yaklaşımları bir araya getiren önemli bir bilimsel platformdur.
-
ÖgeA C0 continuous mixed FE formulation for bending of laminated composite plates based on unified HSDT(Wiley, 2024)This study proposes a unified C0 continuous mixed finite element (MFE) formulation for the accurate and efficient prediction of stress components in laminated composite plates relying on Higher Order Shear Deformation Theory (HSDT). This unified form of the MFE accepts any convenient function for the representation of transverse shear deformation. The Hellinger–Reissner variational principle is employed for the derivation of MFE equations within a two-field formulation involving stress resultants along with kinematical variables. Thus, the displacement and stress resultant fields are obtained directly from the global solution of the system of equations. In this manner, the in-plane stress components are calculated over constitutive relations at the nodes without any need for error-prone spatial derivatives. Furthermore, the independent interpolation of kinematic and stress resultant type variables allows the numerical solution to overcome the shear-locking problem and ensure C0 continuity requirement. Numerical examples include convergence and comparison tests of predicted displacements and stress components under various boundary conditions and material configurations. Various test cases are considered for both the thin and thick plates subjected to sinusoidal and uniformly distributed loads. It is demonstrated that the proposed MFE formulation can capture stress components with high accuracy while being computationally efficient.
-
ÖgeMaximizing daily rainfall prediction accuracy with maximum overlap discrete wavelet transform-based machine learning models(Wiley, 2024)Rainfall is an important phenomenon for various aspects of human life and the environment. Accurate prediction of rainfall is crucial for a wide range of sectors, including agriculture, water resources management, energy production, disaster management and many more. The ability to predict rainfall in an accurate fashion enables stakeholders to make informed decisions and take necessary actions to mitigate the impacts of natural disasters, water scarcity and other issues related to rainfall. In addition, advances in rainfall prediction technologies have the potential to contribute to sustainable water management and the preservation of water resources by providing the necessary information for decision-makers to plan and implement effective water management strategies. Hence, it is important to continuously improve the accuracy of rainfall prediction. In this paper, the integration of the maximum overlap discrete wavelet transform (MODWT) and machine learning algorithms for daily rainfall prediction is proposed. The main objective of this study is to investigate the potential of combining MODWT with various machine-learning algorithms to increase the accuracy of rainfall prediction and extend the forecast time horizon to 3 days. In addition, the performances of the proposed hybrid models are contrasted with the models hybridized with commonly used discrete wavelet transform (DWT) algorithms in the literature. For this, daily rainfall raw data from three rainfall observation stations located in Turkey are used. The results show that the proposed hybrid MODWT models can effectively improve the accuracy of precipitation forecasting, based on model evaluation measures such as mean square error (MSE) and Nash-Sutcliffe coefficient of efficiency (CE). Accordingly, it can be concluded that the integration of MODWT and machine learning algorithms have the potential to revolutionize the field of daily rainfall prediction.
-
ÖgeFormative drought rate to quantify propagation from meteorological to hydrological drought(Wiley, 2024)In this study, we propose a probabilistic metric, the formative drought rate (FDR), to quantify drought propagation. It is the probability that a meteorological drought in precipitation forms a hydrological drought in streamflow. Drought events were identified based on the standardized precipitation index and streamflow drought index, respectively, at 1-, 3-, 6- and 12-month timescales. The method was tested in three river basins in Turkey (Kucuk Menderes, Gediz and Ergene). In each river basin, meteorological stations were coupled with streamflow gauging stations to form pairs of stations depending on their distance from each other and the length of their common record periods. The FDR was calculated across all timescales for each pair of stations. It was found capable to describe the river basin-specific spatial and temporal variability of drought propagation. As the FDR is defined in the form of probability, it is expected to be a useful metric for quantifying propagation from meteorological to hydrological drought. Thus, it carries a potential for scientific research and practice in water resources management.
-
ÖgeLocalizing structural damage based on auto-regressive with exogenous input model parameters and residuals using a support vector machine based learning approach(Springer, 2024)Machine learning algorithms operating in an unsupervised fashion has emerged as promising tools for detecting structural damage in an automated fashion. Its essence relies on selecting appropriate features to train the model using the reference data set collected from the healthy structure and employing the trained model to identify outlier conditions representing the damaged state. In this paper, the coefficients and the residuals of the autoregressive model with exogenous input created using only the measured output signals are extracted as damage features. These features obtained at the baseline state for each sensor cluster are then utilized to train the one class support vector machine, an unsupervised classifier generating a decision function using only patterns belonging to this baseline state. Structural damage, once detected by the trained machine, a damage index based on comparison of the residuals between the trained class and the outlier state is implemented for localizing damage. The two-step damage assessment framework is first implemented on an eight degree-of-freedom numerical model with the effects of measurement noise integrated. Subsequently, vibration data collected from a one-story one-bay reinforced concrete frame inflicted with progressive levels of damage have been utilized to verify the accuracy and robustness of the proposed methodology.