Yazar "Turk, Kazim" seçeneğine göre listele
Listeleniyor 1 - 20 / 32
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Bond strength of reinforcing bars in hybrid fiber-reinforced SCC with binary, ternary and quaternary blends of steel and PVA fibers(Springer, 2021) Kina, Ceren; Turk, KazimIn this study, the effect of inclusion of single fiber and binary, ternary and quaternary fiber hybridization on the bond performance of high strength self-compacting concrete (SCC) was investigated and 12 beam specimens having lap-spliced reinforcing bars in tension at the mid-span were designed. Four different fibers were used with different hybridizations. Fiber reinforced concrete beams demonstrated higher failure loads with a greater number of cracks. Especially the specimens with ternary fiber hybridization showed the best performance that the ultimate load resistance was 60% higher than that of the specimen without fiber. After splitting failure, the beam specimens with binary hybridization of macro steel fiber and polyvinyl-alcohol (PVA) fiber and also, the specimens with ternary hybridization of macro steel fiber, micro steel fiber with 13 mm in length (OL 13/.16) and PVA fiber showed a gradually drop in performance with increasing deflections. Besides, results indicate that the least improvement in bond strength was observed in the specimen having quaternary fiber hybridization of macro steel fiber, OL 13/.16 and micro steel fiber with 6 mm in length (OL 6/.16) and PVA fiber. The bond strength results were also compared with the ones calculated from the existing prediction equations. It was found that Zuo and Darwin and Esfahani and Rangan equations gave better results than the equations of Orangun et al. and ACI 318 on the hybrid fiber reinforced SCC. Based on the results, it was indicated that in these proposals, a new parameter was necessary for the fiber content so in this study, a new empirical equation was derived by using fiber reinforced index for fiber reinforced SCC. The proposed equation gave better estimation in the specimens with single fiber and binary and ternary fiber hybridization.Öğe Comparison of extreme learning machine and deep learning model in the estimation of the fresh properties of hybrid fiber-reinforced SCC(Springer London Ltd, 2021) Kina, Ceren; Turk, Kazim; Atalay, Esma; Donmez, Izzeddin; Tanyildizi, HarunThis paper studied the estimation of fresh properties of hybrid fiber-reinforced self-compacting concrete (HR-SCC) mixtures with different types and combinations of fibers by using two different prediction method named as the methodologies of extreme learning machine and long short-term memory (LSTM). For this purpose, 48 mixtures, which were designed as single, binary, ternary and quaternary fiber-reinforced SCC with macro-steel fiber, two micro-steel fibers having different aspect ratio, polypropylene (PP) and polyvinylalcohol (PVA), were used. Slump flow, t(50) and J-ring tests for designed mixtures were conducted to measure the fresh properties of fiber-reinforced SCC mixtures as per EFNARC. The experimental results were analyzed by Anova method. In the devised prediction model, the amounts of cement, fly ash, silica fume, blast furnace slag, limestone powder, aggregate, water, high-range water-reducer admixture (HRWA) and the fiber ratios were selected as inputs, while the slump flow, t(50) and the J-ring were selected as outputs. Based on the Anova analysis' results, the macro-steel fiber was the most important parameter for the results of slump-flow diameter and t(50), while the most important parameter for the results of J-ring was fly ash. Furthermore, it was found that the use of more than 0.20% by volume of 6/0.16 micro-steel fiber positively influenced the fresh properties of SCC mixtures with hybrid fiber. On the other hand, the inclusion of steel fiber instead of synthetic fiber into SCC mixture as micro-fiber was more advantageous in terms of workability of mixtures as result of hydrophobic nature of steel fibers. This study found that extreme learning machine model estimated the slump flow, t(50) and J-ring with 99.71%, 81% and 94.21% accuracy, respectively, while deep learning model found the same experimental results with 99.18%, 77.4% and 84.8% accuracy, respectively. It can be emphasized from this study that the extreme learning machine model had a better prediction ability than the deep learning model.Öğe Coupled effects of limestone powder and high-volume fly ash on mechanical properties of ECC(Elsevier Sci Ltd, 2018) Turk, Kazim; Nehdi, Moncef L.Owing to its exceptional strain capacity, which can reach hundreds of times that of normal concrete, and its reduced crack width, engineered cementitious composites (ECC) are a very promising solution for mitigating many of the problems that generate colossal backlogs of deteriorated concrete structures worldwide. However, research is needed to develop more sustainable ECC with flexible formulation that uses local materials. This paper investigates the coupled effects of using limestone powder in ECC as partial or total replacement for silica sand aggregate, coupled with using high-volume fly ash as a binder. The compressive and flexural strengths and fracture toughness for the formulated ECCs were examined at 3, 28 and 90 days. The results of this study demonstrate that sustainable ECC for resilient structural applications can be produced. It is aimed that more flexible formulations of ECC using local materials with lower environmental footprint could emerge and contribute to more durable and sustainable civil infrastructure. (C) 2017 Elsevier Ltd. All rights reserved.Öğe Deep learning and machine learning-based prediction of capillary water absorption of hybrid fiber reinforced self-compacting concrete(Ernst & Sohn, 2022) Kina, Ceren; Turk, Kazim; Tanyildizi, HarunDeep auto-encoders and long short-term memory methodology (LSTM) based on deep learning as well as support vector regression (SVR) and k-nearest neighbors (kNN) based on machine learning models for the capillary water absorption prediction of self-compacting concrete (SCC) with single and binary, ternary, and quaternary fiber hybridization were developed. A macro and two types of micro steel fibers having different aspect ratios, and PVA fiber were used. One hundred and sixty-eight specimens produced from 24 mixtures were used in the prediction models. The input was the content of cement, fly ash, silica fume, fine and coarse aggregate, water, superplasticizer (SP), macro and micro steel fibers, PVA, time that the specimen was immersed in water, and splitting tensile strength. Water absorption was used as output. As per the ANOVA analysis of the experiment results, the most effective parameters were macro steel fiber and time for tensile strength and water absorption, respectively. Finally, binary hybridization of 1% macro steel fiber and PVA improved the splitting tensile strength while the use of PVA as binary, ternary, and quaternary fiber hybridization increased the water absorption of SCC specimens. The auto-encoder, LSTM, SVR, and kNN models predicted the water absorption of fiber reinforced SCC with 99.99%, 99.80%, 94.57%, and 95.50% accuracy, respectively. The performance of deep autoencoder in the estimation of water absorption of fiber-reinforced SCC was superior to the other prediction models.Öğe Durability of Engineered Cementitious Composites Incorporating High-Volume Fly Ash and Limestone Powder(Mdpi, 2022) Turk, Kazim; Kina, Ceren; Nehdi, Moncef L.This study investigates the effects of using limestone powder (LSP) and high-volume fly ash (FA) as partial replacement for silica sand (SS) and portland cement (PC), respectively, on the durability properties of sustainable engineered cementitious composites (ECC). The mixture design of ECC included FA/PC ratio of 1.2, 2.2 and 3.2, while LSP was used at 0%, 50% and 100% of SS by mass for each FA/PC ratio. Freeze-thaw and rapid chloride ions penetrability (RCPT) tests were performed to assess the durability properties of ECC, while the compressive and flexural strength tests were carried out to appraise the mechanical properties. Moreover, mercury intrusion porosimetry (MIP) tests were performed to characterize the pore structure of ECC and to associate porosity with the relative dynamic modulus of elasticity, RCPT and mechanical strengths. It was found that using FA/PC ratio of more than 1.2 worsened both the mechanical and durability properties of ECC. Replacement of LSP for SS enhanced both mechanical strengths and durability characteristics of ECC, owing to refined pore size distribution caused by the microfiller effect. It can be further inferred from MIP test results that the total porosity had a vital effect on the resistance to freezing-thawing cycles and chloride ions penetration in sustainable ECC.Öğe The effect of hybrid fiber and shear stud on the punching performance of flat-slab systems(Elsevier, 2023) Bassurucu, Mahmut; Turk, Kazim; Turgut, PakiIn this paper, for the first time, the binary/ternary hybrid fiber and/or shear stud reinforcement as a measure was used to improve the punching performance of flat-slab systems by innovative selfcompacting concrete (SCC). Because in these slab systems, sudden and brittle punching failure can be seen due to application and design errors, early removal of formwork, changes in the purpose of use of the building, earthquakes, etc. Besides, numerous studies investigated the punching performance of the single fiber and/or shear stud reinforced flat-slab systems, but research into the measures of the hybrid fiber or the combined use of hybrid fiber and shear stud reinforcement, which were the variable parameters of this study, was quite lacking. For this purpose, the half-scale slab-column connection elements were produced from SCC containing different punching measures (binary/ternary hybrid and/or shear stud) and tested to investigate the punching performance of flat-slab systems. In conclusion, it was found that hybrid fiber reinforcement was the best punching measure to improve the punching performance of slabcolumn connection elements with/out shear stud. Besides, 3D graphs were drawn so that designers and researchers could estimate the punching strength and energy absorption capacity for flat-slab systems with/out shear stud based on the parameters of micro fiber type and total volume fraction. On the other hand, empirical formulas were developed to predict the punching strength of binary/ternary hybrid fiber reinforced flat-slab systems with/out shear stud by compressive strength, fiber reinforcement index, the slab useful height, and the punching perimeter parameters.Öğe Effect of limestone powder on the rheological, mechanical and durability properties of ECC(Taylor & Francis Ltd, 2017) Turk, Kazim; Demirhan, SerhatThis paper presents the results of an investigation on the influence of a replacement of limestone powder (LSP) by silica sand (SS) on properties of engineered cementitious composites (ECC). For this purpose, five different ECC mixtures were adopted: ECC mixture with only SS (M1) for control purposes and four ECC mixtures in which SS is partially replaced by four levels of replacements (25, 50, 75 and 100% by weight of total SS) of LSP. The mechanical properties of ECC were investigated for 3, 28 and 90 days, while the durability tests were performed for 90 days. It was concluded that increase in LSP content resulted in a decrease in fluidity of ECC mixtures indicating longer flow times. Increase in the LSP content had a positive effect on the performance of the compressive strength, fracture toughness and flexural strength at the ages of 3 and 28 days, while this was not valid at the age of 90 days when compared to the reference mixture M1. Moreover, it can be said that the use of LSP instead of SS in ECC mixtures had the positive effect on ductility and good dispersion of fibres due to its fine particle structure compared to SS. On the other hand, the mass loss due to acid attack and the sorptivity coefficient of ECC specimens decreased, while the carbonation resistance increased in all ECC mixes compared to the reference mixture M1 with only SS when LSP content in ECC mixtures increased.Öğe Effect of macro and micro fiber volume on the flexural performance of hybrid fiber reinforced SCC(Techno-Press, 2020) Turk, Kazim; Kina, Ceren; Oztekin, ErolThe aim of this study is to investigate the flexural performance of hybrid fiber reinforced self-compacting concrete (HFRSCC) having different ratio of micro and macro steel fiber. A total of five mixtures are prepared. In all mixtures, the sum of the steel fiber content is 1% and also water/binder ratio is kept constant. The amount of high range water reducer admixture (HRWRA) is arranged to satisfy the workability criteria of self-compacting concrete. Four-point bending test is carried out to analyze the flexural performance of the mixtures at 28 and 56 curing days. From the obtained load-deflection curves, the load carrying capacity, deflection and toughness values are investigated according to ASTM C1609, ASTM C1018 and JSCE standards. The mixtures containing higher ratio of macro steel fiber exhibit numerous micro-cracks and, thus, deflection-hardening response is observed. The mixture containing 1% micro steel fiber shows worst performance in the view of all flexural parameters. An improvement is observed in the aspect of toughness and load carrying capacity as the macro steel fiber content increases. The test results based on the standards are also compared taking account of abovementioned standards.Öğe Effect of rebar arrangements on the structural behavior of RC folded plates manufactured from hybrid steel fiber-reinforced SCC(Elsevier, 2024) Turk, Kazim; Katlav, Metin; Turgut, PakiIn this paper, for the first time in the literature, the effect of different rebar arrangements on the structural behavior of reinforced concrete (RC) folded plates was investigated. For this purpose, RC folded plate specimens having various rebar arrangements fabricated from high-strength hybrid steel fiber-reinforced self-compacting concrete (HSFR-SCC) were tested by subjecting them to four-point bending loading. Then, the structural behavior properties of RC folded plates, such as crack patterns, failure mode, load-midspan displacement relationship, flexural stiffness, ductility, load-strain behavior, and moment-curvature response, were compared and thoroughly assessed. According to the experimental results, different rebar arrangements except for the detailing of transverse rebar induced the RC folded plates to exhibit a combined plate/beam-slab movement behavior, which resulted in higher load-carrying capacity. Notably, it can be said that the detailing of 90-degree hooked steel was generally more effective on the structural behavior of RC folded plates. In addition, the use of hybrid steel fiber instead of transverse rebar provided resistance against shear stresses at the joints and prevented the plates from separating. This application, in constructing the RC folded plates, can reduce labor costs, increase costeffectiveness, and shorten erection time. Therefore, it is obvious that the use of hybrid steel fiber as an alternative to the detailing of transverse rebar for the construction of RC folded plates will ensure some advantages. In conclusion, it is thought that the findings of the study can provide important guidance on the rebar arrangement of RC folded plates in structural engineering applications for structural engineers and designers.Öğe Electrical conductivity and heating performance of hybrid steel fiber-reinforced SCC: The role of high-volume fiber and micro fiber length(Elsevier, 2023) Turk, Kazim; Cicek, Nazli; Katlav, Metin; Donmez, Izzeddin; Turgut, PakiRecently, it has become very popular to develop electrically conductive concrete composites for active deicing and snow-melting of transportation infrastructure. These composites should have stable electrical conductivity and a uniform heating performance, as well as high mechanical and durability properties, for a sustainable solution. In this context, the main motivation of this study is to develop an electrically conductive hybrid steel fiber reinforced self-compacting concrete (HSFR-SCC) composite for ice and snow removal applications. The electrical conductivity and heating performance of self-compacting concrete (SCC) mixtures having different fiber volumes (1.00, 1.25, and 1.50%) and the combination of macro steel fiber with micro steel fibers having lengths of 13 and 6 mm as single and hybrid were experimentally investigated for the first time. For this purpose, a total of ten SCC mixtures were designed, one of which was non-fiber Control, the others had steel fiber volumes of 1.00, 1.25, and 1.50% and different fiber combinations. Workability (slump-flow, T500 and J-ring) tests on HSFR-SCC mixtures were performed with reference to EFNARC. Then, mechanical (compressive and flexural strengths), electrical resistivity, and heating performance tests of 90-day HSFR-SCC samples were carried out. Before the electrical resistivity and heating performance tests, HSFR-SCC samples were kept in an oven at 105 & PLUSMN; 5 degrees C for 24 h to measure their most critical state (dry) performance. Moreover, using multiple linear regression analysis, empirical equations and contour plots were developed to predict the electrical resistivity and temperature increase values of HSFR-SCC samples depending on fiber volumes and combinations. Considering the experimental results, electrically conductive HSFR-SCC mixtures with satisfactory workability and high strength were obtained. The addition of various volumes and combinations of steel fiber to SCC significantly improved the electrical conductivity and heating performance of the concrete, while the mixtures with hybrid fiber were the best for all fiber volumes. As for the different micro fibers added to the HSFR-SCC mixtures, the 13 mm length micro steel fiber was much more effective in improving the electrical resistivity and heating performance of the samples compared to the 6 mm length micro steel fiber. Also, it was found that the fiber-reinforced index of electrically conductive HSFR-SCC samples could be 0.87 for effective and efficient electrical conductivity.Öğe Estimation of strengths of hybrid FR-SCC by using deep-learning and support vector regression models(Ernst & Sohn, 2022) Kina, Ceren; Turk, Kazim; Tanyildizi, HarunIn this work, to estimate the compressive, splitting tensile, and flexural strength of self-compacting concrete (SCC) having single fiber and binary, ternary, and quaternary fiber hybridization, the deep-learning (DL) and support vector regression (SVR) models were devised. The fiber content and coarse aggregate/total aggregate ratio (CA/TA) were the variables for 24 designed mixtures. Four different fibers, which were a macro steel fiber, two types of micro steel fibers with different aspect ratio, and polyvinyl alcohol (PVA) fiber, were used in SCC mixtures. The specimens of each mixture were tested to measure the engineering properties for 7, 28, and 90 days. The amount of cement, fly ash, fine aggregate, CA, high-range water-reducing admixture, water, macro steel fiber, PVA fiber, two types of micro steel fibers, and curing time were selected as input layers while the output layers were strength results. The experimental results were compared with the estimation results. The engineering properties were estimated using the SVR model with 95.25%, 87.81%, and 93.89% accuracy, respectively. Furthermore, the DL model estimated compressive strength, tensile strength, and flexural strength with 99.27%, 98.59%, and 99.15% accuracy, respectively. It was found that the DL estimated the engineering properties of hybrid fiber-reinforced SCC with higher accuracy than SVR.Öğe An experimental and statistical investigation on the fresh and hardened properties of HFR-SCC: the effect of micro fibre type and fibre hybridization(Taylor & Francis Ltd, 2023) Bassurucu, Mahmut; Turk, KazimIn this study, experimental and statistical analyses were conducted to reveal the effect of micro steel and/or polypropylene (PP) fibre with macro steel fibre as binary and ternary hybridization on the fresh, mechanical and flexural performance of hybrid fibre reinforced self-compacting concrete (HFR-SCC). For this purpose, some tests were conducted related to fresh and hardened properties. It was seen that PP had negative effect on the fresh properties of HFR-SCC mixtures compared to micro steel fibre. Moreover, multiple linear regression (MLR) was used to estimate the fresh and hardened properties of HFR-SCC as function of the percent of fibres by volume while ANOVA analysis determined the contributions of parameters. It was obtained from statistical analysis that there was a good correlation between experimental results and predicted values with approximately R-2=0.91 except for compressive strength. Finally, the use of PP with micro steel fibre as ternary hybridization increased the compressive, splitting, flexural tensile strengths, toughness and ductility of HFR-SCC with 1.1%, 13.2%, 18.8%, 14.9% and 26.3%, respectively, while the inclusion of PP into the mixture as binary hybridization had less positive effect on the hardened properties compared to binary steel fibre reinforced SCC with 0.25% micro steel fibre.Öğe Extreme Learning Machine for Estimation of the Engineering Properties of Self-Compacting Mortar with High-Volume Mineral Admixtures(Springer Int Publ Ag, 2024) Turk, Kazim; Kina, Ceren; Tanyildizi, HarunThe utilization of supplementary cementitious materials obtained from industrial by-products or wastes is one of the most effective ways to minimize the costs as well as environmental impact associated with cement production. This work investigated the effects of the replacement of Portland cement (PC) with (25, 30, 35 and 40%) fly ash (FA) and (5, 10, 15, and 20%) silica fume (SF) by weight as binary and ternary blends on the compressive strength (f(c)) and flexural strength (f(ft)) of self-compacting mortars (SCMs) at 28 and 91 curing days. Extreme learning machine (ELM), support vector regression (SVR), artificial neural network (ANN), and decision tree (DT) models were devised to predict these strengths of SCMs containing high-volume mineral admixture (HVMA). The selected input variables were the number of curing days, water-cementitious material (W/CM), PC, FA, SF, and sand contents, while the f(c) and f(ft) were the output variables. ANOVA results show that the curing time was the most effective parameter for determining both strengths. The results also indicated that ELM achieved superior performance for the prediction of f(c) and f(ft) of SCMs with HVMA compared to SVR, ANN, and DT due to having the highest coefficient of determination values of 0.9802 for both strengths.Öğe Fire resistance of hybrid fiber reinforced SCC: Effect of use of polyvinyl-alcohol or polypropylene with single and binary steel fiber(Techno-Press, 2023) Turk, Kazim; Kina, Ceren; Balalan, EsmaThis study presents the experimental results performed to evaluate the effects of Polyvinyl-alcohol (PVA) and Polypropylene (PP) fibers on the fresh and residual mechanical properties of the hybrid fiber reinforced SCC before and after the exposure of 250 & DEG;C, 500 & DEG;C and 750 & DEG;C temperatures. The compressive and splitting tensile strength, modulus of rupture (MOR), ultrasonic pulse velocity (UPV) as well as toughness and weight loss were investigated at different temperatures. PVA and PP fibers were added into SCC mixtures having only macro steel fiber and also having binary hybridization of both macro and micro steel fiber. The results showed that the use of micro steel fiber replaced by macro steel fiber improved the fresh and hardened properties compared to the use of only macro steel fiber. Moreover, it was emphasized that PVA or PP enhanced the residual flexural performance of SCC, generally, while it negatively influenced the workability, weight loss, UPV and the residual strengths with regards to the use of single steel fiber and binary steel fiber hybridization. Compared to the effect of synthetic fibers, PP had slightly more positive effect in the view of workability while PVA enhanced the residual mechanical properties more.Öğe Flexural performance of V-shaped RC folded plates: The role of plate thickness and fiber hybridization(Elsevier Sci Ltd, 2023) Katlav, Metin; Turk, Kazim; Turgut, PakiReinforced concrete folded plates (RC-FPs) are frequently used in structures such as industrial buildings, hangars, swimming pools, and sports halls due to their high load-bearing capacity, low self-weight, economic advantages, and architectural appearance. However, experimental studies on the reinforced concrete (RC) behavior of these new-generation structural members are very limited. For this purpose, this article investigated the effect of plate thickness and fiber hybridization on the flexural performance of V-shaped RC-FPs produced from self-compacting concrete (SCC). With this study, the experimental moment-curvature tool was used for the first time to evaluate the flexural performance of V-shaped RC-FP. A total of sixteen large-scale V-shaped RC-FP specimens with different plate thicknesses (50, 60, 70, and 80 mm) and fiber hybridization (single, binary, and ternary) were manufactured and subjected to a four-point loading after a 90-day curing period. After the experimental load-deflection and moment-curvature curves were obtained, load-bearing capacity, toughness, curvature ductility, and effective flexural stiffness values were calculated and also showed in the crack patterns for all large-scale V-shaped RC-FPs. The empirical equations with high-precision have been developed using multiple linear regression analysis for predicting the load-bearing capacity, toughness, curvature ductility, and effective flexural stiffness of V-shaped RC-FPs based on the parameters of plate thickness and fiber hybridization. Consequently, the use of hybrid fiber-reinforced SCC in the production of V-shaped RC-FPs exhibited superior properties in terms of flexural performance and crack behavior, as well as allowing for accelerated erection of the roof carrier system, resulting in significantly reducing construction time and costs. Also, fiber reinforcement rather than an increase in plate thickness induced significant increases in the flexural performance values of the V-shaped RC-FPs, while ternary fiber hybridization was the best.Öğe Flexural toughness of sustainable ECC with high-volume substitution of cement and silica sand(Elsevier Sci Ltd, 2021) Turk, Kazim; Nehdi, Moncef L.This study explores the effects of high-content fly ash and limestone filler partial replacement for portland cement and silica sand, respectively on the flexural toughness parameters of engineered cementitious composites (ECC). Various groups of mixtures having variable fly ash/portland cement ratio and different levels of limestone filler were prepared. ASTM C1609, JSCE-SF4 and the Post-Crack Strength method were employed to appraise the flexural toughness parameters of the ECC mixtures at 3, 28 and 90-d. The results show that according to ASTM C1609, JSCE-SF4 and the Post-Crack Strength method, limestone filler did not significantly affect the flexural toughness, while the flexural toughness of ECC beams decreased when the fly ash content increased. Considering deflection capacity, specimens made with a FA/OPC ratio of 1.2 without limestone filler achieved higher ductility at all curing ages. Owing to its superior crack resistance and toughness compared to normal concrete, ECC with high fly ash content and limestone filler could be a sustainable alternative construction material in diverse civil engineering applications. ECC with enhanced ductility compared to normal concrete could offer increased crack resistance, durability and better resilience. (C) 2020 Elsevier Ltd. All rights reserved.Öğe Forecasting the compressive strength of GGBFS-based geopolymer concrete via ensemble predictive models(Elsevier Sci Ltd, 2023) Kina, Ceren; Tanyildizi, Harun; Turk, KazimThe compressive strength (fc) of the concrete is an important parameter in the structural design. However, the assessment of fc via an experimental program is time-consuming, costly, and needs a labor force. Therefore, the forecasting of fc through different algorithms can accelerate and facilitate this process and also provide guidance for scheduling the progress of the construction. While some studies have explored the use of models for the prediction of fc of concrete, the ensemble models that can predict the fc of GPC with industrial by-products is still lacking. Within this scope, decision tree (DT), Bootstrap aggregating (Bagging), and Least-squares boosting (LSBoost) models were devised to predict fc of ground granulated blast furnace slag (GGBFS)-based geopolymer concrete (GPC). The data points collected to devise a GEP model in the previous study were used and the prediction results of the GEP model were compared with the proposed ensemble models in the current study. The age of the specimen, NaOH solution concentration, natural zeolite (NZ) content, silica fume (SF) content, and GGBFS content were used as input parameters, and fc was used as output parameter. According to ANOVA analysis, the age of the specimen was found as the most influential parameter in the determination of the fc of GGBFS-based GPC. Also, Multiple linear regression equation was proposed to estimate the fc of GGBFS-based GPC with the accuracy of 93%. The most accurate model was introduced through performance metrics and the Taylor diagram. The results proved that the highest accuracy and stable predictions were achieved by the LSBoost model with R-squared value of 98.25% followed by GEP model developed in the previous study, DT and Bagging models. However, it is worth mentioning that due to having a high coefficient of correlation values (>%80), DT and Bagging models also have an acceptable ability for predicting fc of GGBS-based GPC.Öğe Freeze-thaw resistance and sorptivity of self-compacting mortar with ternary blends(Techno-Press, 2018) Turk, Kazim; Kina, CerenThis paper investigated the influence of binary and ternary blends of mineral admixtures in self-compacted mortar (SCM) on the fresh, mechanical and durability properties. For this purpose, 25 mortar mixtures were prepared having a total binder content of 640 kg/cm(3) and water/binder ratio between 0.41 and 0.50. All the mixtures consisted of Portland cement (PC), fly ash (FA) and silica fume (SF) as binary and ternary blends and air-entrained admixture wasn't used while control mixture contained only PC. The compressive and tensile strength tests were conducted for 28 and 91 days as well as slump-flow and V-funnel time tests whilst freeze-thaw (F-T) resistance and capillary water absorption tests were made for 91-day. Finally, in general, the use of SF with FA as ternary blends improved the tensile strength of mortars at 28- and 91-day while the use of SF 15 with FA increased the compressive strength of the mortars compared to binary blends of FA. SCM mixtures with ternary blends had lower the sorptivity values than that of the mortars with binary blends of FA and the control mixture due to the beneficial properties of SF while the use of FA with SF as ternary blends induced the F-T resistance enhancement.Öğe Fresh and hardened properties of self consolidating Portland limestone cement mortars: Effect of high volume limestone powder replaced by cement(Elsevier Sci Ltd, 2019) Demirhan, Serhat; Turk, Kazim; Ulugerger, KubraThe main purpose of this experimental study is to elucidate the performance of self-compacting mortars (SCMs) composed of high volume limestone powder (LSP). In accordance with this purpose, four different SCMs at which limestone content varied as 0%, 15%, 25% and 35% were designed and later on fresh, hardened and durability properties of the mixtures were investigated for different curing ages depending on the testing method. Compressive strength, splitting tensile strength, rheological properties, mini-slump cone, carbonation, UPV and capillary water absorption were investigated in terms of fresh and hardened performance properties. In term of fresh properties, test results showed that there was a clear increase in the yield stress up to LSP content of 15% and beyond this level there was a tendency of reduction of the yield stress with the increase of limestone addition and also slumps values increased and pointed out a satisfactory fresh property in accordance with the increase in the replacement level of LSP. For mechanical properties, there was a steady decrease in the compressive strength values with the increase in LSP content while the addition of LSP in SCMs more than 15% did not improve splitting tensile strength of the mixtures for all curing ages. As a durability property, carbonation resistance of SCMs samples decreased with the increase in LSP replacement level for all of the mixtures and also UPV values were in an acceptable range of good (for 15%) and doubtful (for 35%) category intervals. Furthermore, the control mixture with the only PC had the lowest sorptivity coefficient as 2.73 cm/s(1/2) followed by SCMs with 15%, 25% and 35% LSP as 5.11, 6.13 and 6.14 cm/s(1/2), respectively. (C) 2018 Elsevier Ltd. All rights reserved.Öğe Hybrid deep learning model for concrete incorporating microencapsulated phase change materials(Elsevier Sci Ltd, 2022) Tanyildizi, Harun; Marani, Afshin; Turk, Kazim; Nehdi, Moncef L.The inclusion of microencapsulated phase change materials (MPCMs) in concrete promotes thermal energy storage, thus enhancing sustainable design. Notwithstanding this advantage, the compressive strength of concrete dramatically decreases upon MPCM addition. While several experimental studies have explored the origin of this compressive strength reduction, a reliable and practical framework for the prediction of the compressive strength of MPCM-integrated concrete is yet to be developed. The current research proposes a deep learning approach to estimate the compressive strength of MPCM-integrated cementitious composites based on its mixture proportions and the thermophysical properties of PCM. Extreme learning machines (ELMs), autoencoders, hybrid ELM-autoencoder, and extreme gradient boosting (XGBoost) models were purposefully developed using the largest pertinent experimental dataset available to date encompassing 244 mixture design examples retrieved from the open literature. The results demonstrate the capability of the hybrid deep learning and XGBoost models in accurately modeling the compressive strength of PCM integrated concrete with favorably low prediction error. Furthermore, a sensitivity analysis identified the most influential parameters on the compressive strength development to assist the mixture design of concrete incorporating MPCM.
