Yazar "Katlav M." seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    AI-driven design for the compressive strength of ultra-high performance geopolymer concrete (UHPGC): From explainable ensemble models to the graphical user interface
    (Elsevier Ltd, 2024) Katlav M.; Ergen F.; Donmez I.
    Ultra-high performance geopolymer concrete (UHPGC) has become of interest in recent years as a more economical and sustainable alternative while offering similar mechanical performance to ordinary ultra-high performance concrete (UHPC). The lack of an effective mix design methodology has inhibited the widespread use of UHPGC, despite its potential. This paper adopted an artificial intelligence (AI)-based approach to accurately model the compressive strength (CS) of UHPGC, a critical parameter to ensure structural integrity and reliability. Ensemble machine learning (ML) models such as RF, XGBoost, LightGBM and AdaBoost, which have been very popular lately, were selected as AI algorithms. For the establishment of these models, a comprehensive and reliable dataset of 181 test results was used, including 13 input features. Additionally, feature importance and Shapley additive explanations (SHAP) analyses were used to ensure the explainability of the prediction models and tackle the “black box” challenge of ML models. The results obtained revealed that all ensemble models successfully predicted the CS of UHPGC; in particular, the XGBoost model consistently exhibited the best overall performance in terms of higher R2 (0.948) and lower RMSE (6.68), MAE (4.73), MAPE (4 %), and mean error value (1.095), in the test phase. Moreover, feature importance and SHAP analyses revealed that the most influential features on the CS of UHPGC were age, fiber and silica fume, sodium silicate (Na2SiO3), and water content. Lastly, a graphical user interface (GUI) was developed to easily predict the CS of UHPGC in practical applications. © 2024 Elsevier Ltd
  • Küçük Resim Yok
    Öğe
    Electrical resistivity of eco-friendly hybrid fiber-reinforced SCC: Effect of ground granulated blast furnace slag and copper slag content as well as hooked-end fiber length
    (Elsevier Ltd, 2024) Katlav M.; Donmez I.; Turk K.
    Over the last 20 years, the development of electrically conductive composites for removing snow and ice from transportation infrastructure has received exceptional traction. However, these composites need to exhibit stable electrical conductivity and high mechanical properties to be sustainable and cost-effective. Towards this goal, the article investigates the roles of ground granulated blast furnace slag (BFS) and copper slag (CS) content, in addition to hooked-end steel fiber length, on the electrical properties of eco-friendly ultra-high performance hybrid fiber-reinforced self-compacting concrete (HFR-SCC) for the first time in the literature. For this purpose, sixteen eco-friendly electrically conductive ultra-high-performance HFR-SCC were designed based on the variable parameters of four different BFS/total binder ratios (20, 40, 60, and 80 %), a CS/total fine aggregate ratio of 50 %, and two different hooked-end fiber lengths (30 and 60 mm), while all mixes used 1.75 % by volume fraction of steel fibers. After determining the workability properties (slump-flow and T500 values) of all mixes, compressive strength and electrical resistivity/conductivity tests of 90-day specimens were conducted. Additionally, environmental and economic evaluations of all mixes in terms of sustainability were performed in order to clarify the effects of the variable parameters. Taking into account the experimental results obtained, it was observed that all electrically conductive ultra-high performance HFR-SCC mixes demonstrated satisfactory workability properties, while the compressive strength values reached to impressive values of 127 MPa. The optimum BFS/total binder ratio was identified to be 40 % for higher compressive strength and conductivity of ultra-high performance HFR-SCC specimens. On the other hand, the addition of CS to the mixes resulted in an increase of almost 9 % in compressive strength compared to one without CS, while at the same time, a significant increase of approximately 363 % was observed in the electrical conductivity values of the specimens. As for the influence of different lengths of hooked steel fibers, the use of 30 mm length hooked-end steel fibers in HFR-SCC mixes performed better in terms of compressive strength, whereas 60 mm fibers performed better regarding electrical conductivity. In conclusion, this experimental work has evidenced that it is possible to develop an eco-friendly and sustainable electrically conductive ultra-high performance cementitious composite (the optimal mix compressive strength and electrical resistivity values were 127 MPa and 2242 ?.cm, respectively) by using waste from different industries such as iron and copper. Thus, it will provide important insights for the design and application of future electrically conductive concretes, which can be an important alternative in efficient active deicing and snow-melting applications. © 2024 Elsevier Ltd
  • Küçük Resim Yok
    Öğe
    Machine and deep learning-based prediction of flexural moment capacity of ultra-high performance concrete beams with/out steel fiber
    (Springer Nature, 2024) Ergen F.; Katlav M.
    This paper presents a study to develop the most appropriate machine learning (ML) and deep learning (DL) models for predicting the flexural moment capacity of ultra-high performance concrete beams (UHPC-Bs) with/out steel fibers. As prediction models, five different ML models (support vector regression (SVR), extreme gradient boosting (XGBoost), multilayer perceptron (MLP), random forest (RF), and extremely randomized trees (ERT)) and three different DL models (long short-term memory (LSTM), bidirectional LSTM (BILSTM), and gated recurrent unit (GRU)) are adopted in this study. To train and evaluate these prediction models, a total of 82 experimental results from the literature on rectangular UHPC-Bs with/out steel fibers are used as a database. On the other hand, the Shapley Additive Explanations (SHAP) analysis is used to evaluate the effects of input features on the prediction results. Furthermore, based on the best prediction model obtained in this study, a graphical user interface is designed to facilitate the use of the flexural moment capacity of UHPC-Bs with/out steel fibers in practical applications. The results obtained indicated that both ML and DL models can be effectively used to predict the flexural moment capacity of UHPC-Bs with/out steel fibers. Particularly, ML algorithm such as XGBoost and DL algorithm like BILSTM stand out for their ability to predict the flexural moment capacity with high accuracy. Furthermore, SHAP analysis revealed that the longitudinal tensile reinforcing steel bar area (As), effective depth (d), and fiber-reinforcing index (Vf × lf/df) are the most effective parameters for prediction performance, while the compressive strength (fc) of concrete is less effective. Consequently, the developed prediction models and graphical user interface (GUI) will help structural engineers and designers quickly predict the flexural moment capacity of UHPC-Bs with high accuracy and make the design process more efficient. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.