Yazar "Ergen, Faruk" seçeneğine göre listele
Listeleniyor 1 - 9 / 9
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Data-driven moment-carrying capacity prediction of hybrid beams consisting of UHPC-NSC using machine learning-based models(Elsevier Science Inc, 2024) Katlav, Metin; Ergen, FarukThis paper presents, for the first time in the literature, a study on the development of data-driven machine learning (ML) models to predict the moment-carrying capacity of ultra-high performance concrete (UHPC)normal strength concrete (NSC) hybrid beams. A database of 56 specimens of rectangular-section UHPC-NSC hybrid beams subjected to flexural loading is adopted to train the models. In this context, ten ML algorithms that are most preferred in structural engineering applications are selected to develop prediction-based models: linear regression (LR), lasso regression (LASSO), ridge regression (RR), support vector regression (SVR), multilayer perception (MLP), random forest (RF), extremely randomized trees (ERT), extreme gradient boosting (XGBoost), K-nearest neighbors regression (KNN), and adaptive boosting regression (AdaBoost). Moreover, the Shapley additive explanation (SHAP) method is used to assess the impact of the input features on the prediction results. Lastly, user-friendly a graphical user interface (GUI) has been developed to ensure the interpretability of the prediction models and to overcome the black box problem of ML methods. The GUI, which is designed based on the model with the most effective prediction ability obtained from this work, allows design engineers to analyze their own data and customize the parameters of the model for the prediction of the moment-carrying capacity of UHPC-NSC hybrid beams. The results indicated that ML models can be an effective tool for predicting the moment-carrying capacity of UHPC-NSC hybrid beams. In this regard, notably, the XGBoost model exhibited superior performance in terms of prediction accuracy and generalization ability (R2 = 0.996 and 0.945 in the training and test datasets, respectively). On the other hand, according to the SHAP analysis results, the three most important input parameters influencing the moment-carrying capacity of UHPC-NSC hybrid beams are the effective depth (d), UHPC thickness at the bottom of the beam (UHPCbottom layer) and compressive strength of UHPC (fc,UHPC), respectively. Moreover, it has been found that the placement of the UHPC layer at the bottom of the beam rather than at the upper part of the beam is more effective in enhancing the moment-carrying capacity of UHPC-NSC hybrid beams.Öğe Development of BIM software with quantity take-off and visualization capabilities(2022) Ergen, Faruk; Bettemir, Önder HalisBuilding Information Modeling (BIM) prepares quantity take-off of construction items, helps the management of the design and construction process and prepares 3D visualization of the construction phases. BIM offers more control over the construction tasks and improves the efficiency. Construction professionals are aware of the benefits of BIM however, the utilization of BIM is still not common yet because of the BIM software cost and training requirement of the staff. In this study, open-source BIM software is developed by Python programming language. The software is capable of preparation of 2-dimensional drawings, 3D visualization as well as execution of quantity take-off computations of formwork and concrete. The codes are developed in Python language by using SQlite library and Ursina engine. A graphical user interface is formed by Python language for the execution of 2 Dimensional drawings and entries of the coordinates of the structural elements as well as attribute data. 3D coordinates of the structural elements are computed by using the joint coordinates of the structural elements. 3D visualizations of the structural elements are performed by the Ursina engine. The connections and intersections of the joints and structural elements are stored in a database that is formed by SQlite. The voids are successfully computed and formwork and concrete quantities are computed. The open-source BIM software would have low investment and operational costs for the construction firms and would increase BIM usage. The utilization of the software would decrease the manmade errors during the quantity take-off preparation step.Öğe Development of ontological algorithms for exact QTO of reinforced concrete construction items(Elsevier Science Inc, 2024) Ergen, Faruk; Bettemir, Onder HalisBuilding Information Modeling (BIM) provides significant benefits to the construction industry throughout the project management process. However, state-of-the-art BIM software provides erroneous quantity take -off (QTO) results above the negligible margin. In this study, QTO calculation algorithms have been developed for rough construction and implemented on BIM software to solve the stated problem. The developed QTO algorithms establish semantic relations and search the neighborhood of the structural elements to detect the intersecting structural elements. Amount of intersection is calculated by the dimensions and the locations of the intersecting structural elements. Exact length and spacing of the rebar and stirrups are calculated by considering the created semantic relationships. QTO of formwork is accurately calculated by considering the voids of the QTO computations which are obtained from the constructed semantic relationships by investigating the column -beam, slabbeam, and slab -column contact areas. Furthermore, the construction type of the scaffolding for the formwork is determined by considering both the dimensions of the structure and the established semantic relations. The developed algorithms are executed on BIM capable software and tested in four case studies with special conditions. The comparison with manual condition revealed that the proposed algorithms provided exact results. The semantic QTO algorithms developed in this study have the potential to be useful for BIM software developers.Öğe Estimation of the shear strength of UHPC beams via interpretable deep learning models: Comparison of different optimization techniques(Elsevier, 2024) Ergen, Faruk; Katlav, MetinIn this article, optimized deep learning (DL) models with different algorithms are adopted to estimate the shear strength of rectangular ultra-high performance concrete beams (UHPC-Bs) in order to overcome the challenges in traditional mechanics-based approaches. Long short-term memory (LSTM) and gated recurrent unit (GRU) are chosen as the DL models, whereas the recent popular optimization algorithms are phasor particle swarm optimization (PPSO), dwarf mongoose optimization (DMO), mountain gazelle optimizer (MGO), and atom search optimization (ASO). A thorough and reliable dataset of 244 UHPC-Bs test results with ten input features has been used to construct the hybrid DL models. The performance of the optimized hybrid LSTM and GRU models with different algorithms is extensively assessed and compared based on various statistical metrics, error, and score analyses. Then, the model with the best estimation performance is determined and compared with the mechanics-based formulas in the current international design codes. Additionally, Shapley additive explanations (SHAP) analysis is used to assist in the interpretability of DL models and to reveal the effects of input features that contribute to the model's estimation. According to the results of the present work, all DL models successfully estimate the shear strength of UHPC-Bs. Among these models, the MGO-LSTM model stands out compared to the other models in terms of several performance measures for both the training and testing phases, like a higher R-2 value, lower RMSE, MAPE, and MAE values, as well as a smaller error ratio and a higher final score. The performance of the algorithms applied to optimize the hyper-parameters of the LSTM and GRU models can be ranked as follows: MGO > DMO > PPSO > ASO. Moreover, a graphical user interface (GUI) was constructed based on the best estimation model that was built so that the shear strength of UHPC-Bs could be estimated in real-world situations without the need for any extra software or tools. This enables more users to quickly and easily estimate the shear strength of UHPC-Bs, optimize design processes, and decrease experimental testing costs.Öğe Improved forecasting of the compressive strength of ultra-high-performance concrete (UHPC) via the CatBoost model optimized with different algorithms(Ernst & Sohn, 2024) Katlav, Metin; Ergen, FarukThis paper focuses on the applicability of CatBoost models constructed using various optimization techniques for improved forecasting the compressive strength of ultra-high-performance concrete (UHPC). Phasor particle swarm optimization (PPSO), dwarf mongoose optimization (DMO), and atom search optimization (ASO), which have been very popular recently, are preferred as optimization algorithms. A comprehensive and reliable data set is used to develop the CatBoost models, which include 785 test results with 15 input features. The performance of the CatBoost models (PPSO-CatBoost, DMO-CatBoost, and ASO-CatBoost) optimized with different algorithms is thoroughly assessed by means of various statistical metrics and error analysis to determine the model with the best forecasting capability, and this model is compared with the models obtained from previous studies. In addition, Shapley additive exPlanations (SHAP) analysis is used to ensure the interpretability of the forecasting models and to overcome the black box problem of machine learning (ML) models. The obtained results demonstrate that all CatBoost models outstandingly forecast the compressive strength of UHPC. Among these models, the DMO-CatBoost model stands out compared to the other models in various performance metrics, such as high coefficient of determination (R2) values, low root mean squared error (RMSE), mean absolute percentage error (MAPE), and mean absolute error (MAE) values, along with a smaller error ratio. In other words, the RMSE, R-2, MAPE, and MAE values of the DMO-CatBoost model for the training set are 3.67, 0.993, 0.019, and 2.35, respectively, whereas those for the test set are 6.15, 0.978, 0.038, and 4.51. Additionally, the performance ranking of the algorithms used to optimize the hyperparameters of the CatBoost model is as follows: DMO > PPSO > ASO. On the other hand, SHAP analysis showed that age, fiber dosage, and cement dosage significantly influence the compressive strength of UHPC. These findings can guide structural engineers in the design and optimization of UHPC, thus assisting them in developing strategies to improve the strength properties of the material. Finally, based on the best forecasting model developed in this work, a graphical user interface has been developed to easily forecast the compressive strength of UHPC in practical applications without additional tools or software.Öğe Investigating the applicability of deep learning and machine learning models in predicting the structural performance of V-shaped RC folded plates(Elsevier, 2024) Katlav, Metin; Ergen, Faruk; Turk, Kazim; Turgut, PakiReinforced concrete folded plates (RC-FPs), which are a special class of shell structures, have recently become very popular in modern architectural and engineering applications because of the need for lightweight and aesthetic structures to cover large areas. However, it is known that studies on the structural performance of RCFPs are insufficient. Therefore, this article presents a study on the development and comparison of different deep learning (DL) and machine learning (ML) models for the prediction of the structural performance of full-scale Vshaped RC-FPs produced from hybrid fiber-reinforced self-consolidating concrete (HFR-SCC) having different plate thicknesses (50, 60, 70, and 80 mm), fiber volumes (1.00% and 1.25%), and combinations (single, binary, and ternary). While vanilla long short-term memory (VLSTM) and bidirectional long short-term memory (BILSTM) are used as DL models, random forest (RF), extremely randomized trees (ERT), and adaptive boosting (AdaBoost) are preferred for ML models. To construct the models, the structural performance results of a total of 44 full-scale V-shaped RC-FPs subjected to four-point bending loading were adopted as the database. In addition to all these, the AdaBoost model is used to determine the relative feature importance of the input parameters. Based on the results, among the DL models, the BILSTM has the best ability to predict the structural performance values of V-shaped RC-FPs (such as R-squared values for maximum load-bearing capacity, cracking load, toughness, and deflection ductility are 0.934, 0.987, 0.972, and 0.812, respectively), while in ML models, this is valid for the ERT (such as R-square values are 0.917 for maximum load-bearing capacity, 0.936 for cracking load, 0.947 for toughness and 0.825 for deflection ductility). On the other hand, DL models predicted all other structural performance values better than ML models, except for deflection ductility. Besides, the most relative important input features for maximum load-bearing capacity and toughness values is plate thickness, whereas for cracking load and deflection ductility values compressive strength is important. In conclusion, it can be emphasized that the use of DL models can provide significant advantages in engineering applications, such as predicting the structural performance of V-shaped RC-FPs.Öğe Investigation of optimized machine learning models with PSO for forecasting the shear capacity of steel fiber-reinforced SCC beams with/out stirrups(Elsevier, 2024) Ergen, Faruk; Katlav, MetinThis article presents a comprehensive investigation of the applicability of optimized machine learning (ML) models with particle swarm optimization (PSO) for forecasting the shear strength of steel fiber-reinforced self-compacting concrete (SFR-SCC) beams with/without stirrups in engineering applications. Firstly, a database containing the results of 101 specimens with nine input features is adopted to train the models. As ML models such as random forest (RF), adaptive boosting regression (AdaBoost), extreme gradient boosting (XGBoost), support vector regression (SVR), and K-nearest neighbors regression (KNN) are considered, whereas the hyper-parameters of these models are set as default by the sklearn module. On the other hand, PSO-ML models (PSO-RF, PSO-AdaBoost, PSO-XGBoost, PSO-SVR, and PSO-KNN) are constructed using particle swarm optimization to find the optimal combination of the hyper-parameters of these default ML models. Afterwards, the forecasting ability of each model is extensively assessed using various performance metrics, error analysis, and score analysis, and the model with the best forecasting ability is determined and compared with existing empirical models. Moreover, Shapley additive explanation (SHAP) analysis is also utilized to ensure the interpretability of the forecasting models and to overcome the black box problem of ML methods. Lastly, based on the best forecasting model developed in this study, a graphical user interface (GUI) has been developed to easily forecast the shear strength of SFR-SCC beams in practical applications. The results of the study clearly illustrate that PSO-ML models exhibit better forecasting capabilities than default models. It can be emphasized from here that the PSO algorithm can be an effective tool to improve the performance of ML models. It should also be pointed out that the use of PSO in simpler algorithms instead of tree-based models can further improve forecasting efficiency. On the other hand, the PSO-RF model has the best performance, with a lower error value and a high final score. And this makes it a more reliable option for predicting the shear strength of the SFRSCC beams compared to empirical equations. In addition, according to the results of SHAP feature importance analysis, the most important input parameters affecting the shear strength of SFR-SCC beams are stirrup rebar ratio (rho v), stirrup yield strength (fyv) and longitudinal rebar ratio (rho t). This information can assist engineers in paying special attention to these features in their design and assessment processes.Öğe Yapı bilgi modellemesi tabanlı kaba metraj hesaplayan ve 3B görselleştiren yazılımın geliştirilmesi(İnönü Üniversitesi, 2022) Ergen, FarukBir inşaat projesinde kullanılacak olan malzemelerin miktarının ve maliyetinin tahmini tasarım sürecinin en önemli aşamalarından birini oluşturmaktadır. Günümüzde Yapı Bilgi Modellemesi (YBM) sürecinde kullanılan yazılımlar ile metraj hesaplamaları ve maliyet tahimini geleneksel yöntemlere göre oldukça hızlı bir biçimde gerçekleştirilmektedir. Fakat YBM yazılımlarının yapı elemanları arasındaki komşuluk ilişkilerini tam olarak belirleyememesi ve yapı elemanlarının anlamsal modelini dikkate almadan sadece geometrik şekilleri dikkate alarak metraj hesabını gerçekleştirmesinden dolayı sonuçlar gerçek değerlere göre önemli ölçüde sapma göstermektedir. Ayrıca kullanılan yazılımların lisanslama ücretleri oldukça pahalıdır ve genellikle yerel mevzuatlara göre özelleştirilmeden kullanılmaktadır. Belirtilen nedenler uluslar arası yazılımların inşaat sektöründeki uygulanabilirliğini azaltmaktadır. Bu tez çalışmasında Türk inşaat sektörünün YBM uygulaması üzerine karşılaştığı sorunları çözebilmek için yerli, ücretsiz ve açık kaynaklı bir YBM yazılımının geliştirilmesi amaçlanmıştır. Yazılım, python programlama dili kullanılarak yapının kaba metrajını yapıyı oluşturan elemanların komşuluk ilişkilerini ve anlamsal temsilllerini dikkate alarak hesaplamaktadır. Ayrıca geliştirilen yazılımın yapıyı 3B görselleştirerek YBM sürecine yardımcı olması amaçlanmaktadır. Yazılımın geliştirilme yöntemi, metraj hesaplamaları için kullanılan algoritmalar ve yapının 3B görselleştirme süreci vaka çalışmaları ile test edilmiştir. Test sonuçlarında beton, kalıp, kalıp iskelesi ve donatı metraj değerlerinin hatasız hesaplandığı belirlenmiştir. Ayrıca yapının 2B çizimlerine sadece derinlik bilgisi girilerek başarılı bir şekilde 3B görselleştirmesinin yapıldığı, binadaki merdiven ve asansör boşluklarının gösterilebildiği ve bina içinde yürümenin kesintisiz biçimde gerçekleştirilebildiği tespit edilmiştir.Öğe Yüksek doğrulukta kaba inşaat kalemlerinin metrajını hesaplayan YBM tabanlı prototip yazılımın geliştirilmesi(2023) Ergen, Faruk; Bettemir, Önder HalisYapı Bilgi Modellemesi (YBM) kullanımı inşaat sektöründe önemli ölçüde yaygınlaşmıştır. Bununla birlikte küçük ve orta ölçekli yükleniciler YBM yazılımlarının getireceği maliyet ile YBM kullanımına adapte olabilmek için gerekli olan personel eğitimi ve iş alışkanlığı değişimi gereksiniminden dolayı YBM kullanımına uzak kalmaktadır. Bu çalışmada YBM yazılımlarının temel fonksiyonlarından olan 3 Boyutlu görselleştirme ve kaba inşaatın metraj hesaplama işlemlerini gerçekleştirebilen bir yazılım geliştirilmiştir. Python programlama dili ile uyumlu Tkinter Kütüphanesi, Python tabanlı Ursina 3B oyun motoru ve SQLite3 veri tabanı uygulaması kullanılarak insan müdahalesi olmadan beton, betonarme kalıbı ile kalıp iskelesi metrajlarını hesaplayıp 3B görselleştirebilen yazılım geliştirilmiştir. Geliştirilen yazılım çok fazla işleve sahip olmadığı için kullanımı kolay kullanıcı ara yüzlerine sahiptir. Bu sayede özel bir personel eğitimi gerektirmeden 2 Boyutlu çizimlere sadece kat yüksekliği gibi derinlik verilerinin girilmesi ile yapının 3 Boyutlu görselleştirmesi yapılabilmektedir. Buna ek olarak beton, betonarme kalıbı ve kalıp iskelesi metrajları da otomatik biçimde çıkarılmaktadır. Elle yapılan metraj hesabı ile karşılaştırıldığında kalıpta %0.04 oranında sapma olduğu tespit edilmiştir. Yapılan literatür taramasında Revit ile elde edilen metraj verilerinin daha fazla sapabildiği görülmüştür. Geliştirilen YBM yazılımını kullanacak küçük ölçekli yükleniciler daha hassas ve hızlı metraj hazırlayarak daha doğru biçimde maliyet analizi yapma imkânına sahip olacaklardır.
