Browsing by Author "İpek, Süleyman"

Now showing 1 - 6 of 6

Citation - Scopus: 1
Analytical design models in construction engineering: artificial neural network and gene expression programming practices
(Elsevier, 2025) Ayşegül Erdoğan; Süleyman İpek; Kasım Mermerdaş; Esra Mete Güneyisi; Erhan Güneyisi; Erdoğan, Ayşegül; İpek, Süleyman; Mermerdaş, Kasım; Güneyisi, Esra Mete
One important aspect of experimental studies is to supply valuable raw data for the literature. However data at the base of the DIKW (data-information-knowledge-wisdom) pyramid lacks significance unless it has been condensed organized categorized structured and evaluated. In this way the data will be transformed into information. Then processing the information will enable progression to the knowledge stage of the DIKW pyramid and applying this knowledge in action will help to reach the wisdom stage. In this context it is crucial to transform the pure data obtained from the experimental studies into wisdom. Construction engineering a crucial and evolving field of civil engineering advances through experimental research and practical outcomes. Therefore it can be concluded that the core principles of construction engineering are founded on correctly and wisely expressing findings from experimental and practical research. In recent years there have been numerous efforts to gather data from both experimental and practical studies and apply soft-computing techniques to extract valuable insights. In this respect the paper presents empirical design models developed using artificial neural networks (ANNs) and gene expression programming (GEP) noteworthy soft computing methods to solve some engineering problems in the construction field. This chapter aims to explain the significance of evaluating data and transforming it into a clear analytical design model. Following that it examines both soft-computing methods in great detail. Ultimately analytical design models developed to solve construction engineering problems are presented. © 2025 Elsevier B.V. All rights reserved.
BIM-BES-Based Energy Performance Simulation of Library-Type Buildings Considering Cold Winter/Hot Summer Climate Regime with Passive Strategies
(Springer International Publishing, 2026-03-05) Şeker, İbrahim Halil; İpek, Süleyman; Aybek Özdemir, Dilek; Özer Yaman, Gonca
Citation - WoS: 1
Citation - Scopus: 2
Enhancing student learning in architectural design studios: A pentagon and DEMATEL-based study on new learning components and interaction dynamics
(Springer Science and Business Media B.V., 2024-12-10) Fatma Kürüm Varolgüneş; Süleyman İpek; Sedat Aras; Varolgüneş, Fatma Kürüm; İpek, Süleyman; Aras, Sedat
Architectural design pedagogy is indeed complex. At the early stages basic design principles should be addressed and the design process should be taught with its multidisciplinary variables to enable each student to develop an individual approach. In this regard the objective of this study is to propose strategies for enhancing students’ learning and production abilities within the context of architectural education. The present study also considers the interactions and learning processes of students in design studios. The study has yielded hypotheses that underscore the necessity for the incorporation of novel and dynamic learning elements to facilitate and reinforce this process alongside the significance of interactions between all these elements. In this context the educational processes and components of architectural design studios were initially examined and processes and components supporting student development were subsequently identified. In order to provide support for the identified hypotheses a pentagon model was created and relationship network diagrams and DEMATEL analyses were conducted. Furthermore the model was evaluated through a case study conducted with first-year students enrolled in the architectural design course during the fall term of 2022–2023 at the Department of Architecture of Bingöl University. A significant outcome of this study is the provision of a guide for researchers and studio instructors in architectural education which details the progression of design studios. Testing the proposed model in various studios and educational settings will contribute to the development of the identified hypotheses and the created model. © 2025 Elsevier B.V. All rights reserved.
Investigating the Rubberized Concrete-Filled Steel Tube Composite Columns and Developing Artificial Intelligence-Based Analytical Models for Ultimate Axial Strength Prediction
(Wiley, 2026-01-22) Katipoğlu, Okan Mert; Simsek, Oguz; İpek, Süleyman; Güneyisi, Erhan
The application of rubberized concrete (RuC) in structural systems has led to the development of a novel composite system: the rubberized concrete-filled steel tube (RuCFST). The characteristics of infill materials, particularly RuC, significantly influence the structural behavior and performance of these composite systems. This study aims to evaluate the ultimate axial strength of RuCFST columns, considering rubber aggregate content up to 75% and infill concrete compressive strength up to 63 MPa, and propose artificial intelligence (AI)-based design models using deep learning (CNN, DNN, Autoencoder), machine learning (CatBoost), hybrid AI/neuro-fuzzy (ANFIS), and unsupervised neural network (SOM) to predict the ultimate axial strength. A robust dataset was compiled from the literature, comprising the results of 131 RuCFST column specimens. The experimental results underwent a comprehensive statistical assessment using various analytical methods, including Pearson correlation coefficient analysis, histogram analysis, distribution fitting curve analysis, and box-and-whisker plot analysis. Additional statistical metrics such as Kolmogorov-Smirnov, skewness, and kurtosis values were also used. Furthermore, by considering various variables covering the geometrical and material properties of the RuCFST columns, the design models were developed using AI techniques. The statistical evaluation results indicated that the compiled dataset is statistically significant and encompasses various input and output parameters. The design models developed in this study displayed varying prediction performance. However, those created using the Autoencoder and ANFIS methods showed statistically satisfactory performance in determining the load-carrying capacity of the columns.
Rubber-Modified Self-Compacting Mortar: Evaluating Setting Time and Strength Development
(Yildiz Technical University, 2025-06-30) Süleyman İpek; Navvar Makansi; Erhan Güneyisi; İpek, Süleyman; Makansi, Navvar; Güneyisi, Erhan
The influence of using crumb rubber (CR) obtained from the second scraping of used tires as fine aggregate in manufacturing self-compacting mortar (SCM) was investigated experimentally in this study. To explore this natural fine aggregate in SCM mixes was partially replaced with CR at levels ranging from 5% to 25% by total fine aggregate volume. Two mix series one with a total binder of 500 kg/m3 and the other with a 540 kg/m3 binder were designed at water-to-binder ratios of 0.40 and 0.33. Ordinary Portland cement (80% by weight) and fly ash (20% by weight) were used to manufacture mortars. Twelve SCM mixes were cast and tested to evaluate their fresh-state properties including setting times flow diameter and flow time. Moreover the compressive strengths at 3 7 28 56 and 90 days were determined for each mix to investigate their strength development. The test results indicated that the incorporation of CR adversely affected the fresh properties of the SCM mixes and an increase in the CR replacement level systematically diminished their strength characteristics. Nevertheless it was observed that it could be used in a controlled manner to achieve the desired properties.
Time-Based Fire Resistance Performance of Axially Loaded, Circular, Long CFST Columns: Developing Analytical Design Models Using ANN and GEP Techniques
(MDPI, 2025-12-06) Nassani, Dia Eddin; Özelmacı Durmaz, Ç. Özge; İpek, Süleyman; Mete Güneyisi, Esra
Concrete-filled steel tube (CFST) columns are composite structural elements preferred in various engineering structures due to their superior properties compared to those of traditional structural elements. However, fire resistance analyses are complex due to CFST columns consisting of two components with different thermal and mechanical properties. Significant challenges arise because current design codes and guidelines do not provide clear guidance for determining the time-dependent fire performance of these composite elements. This study aimed to address the existing design gap by investigating the fire behavior of circular long CFST columns under axial compressive load and developing robust, accurate, and reliable design models to predict their fire performance. To this end, an up-to-date database consisting of 62 data-points obtained from experimental studies involving variable material properties, dimensions, and load ratios was created. Analytical design models were meticulously developed using two advanced soft computing techniques: artificial neural networks (ANNs) and genetic expression programming (GEP). The model inputs were determined as six main independent parameters: steel tube diameter (D), wall thickness (ts), concrete compressive strength (fc), steel yield strength (fsy), the slenderness ratio (L/D), and the load ratio (mu). The performance of the developed models was comprehensively compared with experimental data and existing design models. While existing design formulas could not predict time-based fire performance, the developed models demonstrated superior prediction accuracy. The GEP-based model performed well with an R-squared value of 0.937, while the ANN-based model achieved the highest prediction performance with an R-squared value of 0.972. Furthermore, the ANN model demonstrated its excellent prediction capability with a minimal mean absolute percentage error (MAPE = 4.41). Based on the nRMSE classification, the GEP-based model proved to be in the good performance category with an nRMSE value of 0.15, whereas the ANN model was in the excellent performance category with a value of 0.10. Fitness function (f) and performance index (PI) values were used to assess the models' accuracy; the ANN (f = 1.13; PI = 0.05) and GEP (f = 1.19; PI = 0.08) models demonstrated statistical reliability by offering values appropriate for the expected targets (f approximate to 1; PI approximate to 0). Consequently, it was concluded that these statistically convincing and reliable design models can be used to consistently and accurately predict the time-dependent fire resistance of axially loaded, circular, long CFST columns when adequate design formulas are not available in existing codes.