Figure 4 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
Silica fume (SF) is a frequently used mineral admixture in producing sustainable concrete in the construction sector. Incorporating SF as a partial substitution of cement in concrete has obvious advantages, including reduced CO2 emission, cost-effective concrete, enhanced durability, and mechanical properties. Due to ever-increasing environmental c...
Context in source publication
Citations
... In addition to the waste types discussed above, the literature also emphasizes the use of lightweight aggregate pumice stone as a substitute for pure coarse aggregate in concrete. In the last two decades, there has been a notable rise in the comprehension and utilization of high-strength, lightweight concrete that relies on artificial lightweight particles (Shideler 1957, Hoff 1996, Nafees, Amin et al. 2021. A volcanic material called pumice resembles a sponge that is created when lava suddenly freezes and traps millions of tiny air bubbles (Ali, Alam et al. 2021). ...
The primary objective of this study is to investigate the production and performance characteristics of structural concrete incorporating varying proportions (0%, 25%, and 50% by volume) of pumice stone, as well as aluminum lathe as an additive at 0%, 1%, 2%, and 3%, under fire conditions. The experiment will be conducted over a period of up to 1 hour, at temperatures ranging from 24°C, 200°C, 400°C and 600°C. For the purpose of this, a total of twelve test samples were manufactured, and then tests of compressive strength (CS), splitting tensile strength (STS), and flexural strength (FS) were performed on these samples.Next, a comparison was made between the obtained values and the influence of temperature. To achieve this objective, the manufactured samples were placed at temperatures of 200°C, 400°C, and 600°C for a duration of 1 hour, and were subjected to the influence of temperature.These values at 24 °C were then contrasted with the CS results obtained from test samples that were subjected to the temperature effect for an hour at 200 °C, 400 °C, and 600 °C. A comprehensive analysis of the test outcomes reveals that the incorporation of aluminum lathe wastes into a mixture results in a significant reduction in the compressive strength of the concrete. As a result of this adjustment, the CS values dropped by 32.93%, 45.70%, and 52.07%, respectively. Furthermore, It was shown that testing the ratios of pumice stone alone resulted in a decrease in CS outcomes. Additionally, it was found that the presence of higher temperatures is clearly the primary factor contributing to the decrease in the strength of concrete. Due to elevated temperatures, the CS values decreased by 19.88%, 28.27%, and 38.61% respectively.After this investigation, an equation that explains the connection between CS and STS was provided through the utilization of the data of the experiments that were carried out.
... Moreover, latest studies used modern techniques such as artificial intelligence and machine learning techniques to study mechanical properties of concrete incorporating different wastes to enhance the model stability and efficiency. For instance, Nafees et al. 35 , studied the mechanical properties of silica fume-based green concrete using ML techniques. Asghar et al. 8 , compiled a review on the structural and mechanical performance of geopolymer concrete to promote green and sustainable construction. ...
Recent and past studies mainly focus on reducing the dead weight of structure; therefore, they considered lightweight aggregate concrete (LWAC) which reduces the dead weight but also affects the strength parameters. Therefore, the current study aims to use varied steel wire meshes to investigate the effects of LWAC on mechanical properties. Three types of steel wire mesh are used such as hexagonal (chicken), welded square, and expanded metal mesh, in various layers and orientations in LWAC. Numerous mechanical characteristics were examined, including energy absorption (EA), compressive strength (CS), and flexural strength (FS). A total of ninety prisms and thirty-three cubes were made. For the FS test, forty-five 100 × 100 × 500 mm prism samples were poured, thirty-three 150 × 150 × 150 mm cube samples were made, and forty-five 400 × 300 × 75 mm EA specimens were costed for fourteen days of curing. The experimental findings demonstrate that the FS was enhanced by adding additional forces that spread the forces over the section. One layer of chicken, welded, and expanded metal mesh enhances the FS by 52.96%, 23.76%, and 22.2%, respectively. In comparison to the remaining layers, the FS in a single-layer hexagonal wire mesh has the maximum strength, 29.49 MPa. The hexagonal wire mesh with a single layer had the greatest CS, measuring 36.56 MPa. When all three types of meshes are combined, the CS does not vary in this way and is estimated to be 29.79 MPa. In the combination of three layers, the chicken and expanded wire mesh had the most energy recorded prior to final failure, which was 1425.6 and 1108.7 J, whereas it was found the highest 752.3 J for welded square wire mesh. The energy absorption for the first layer with hexagonal wire mesh increased by 82.81% prior to the crack and by 88.34% prior to the ultimate failure. Overall, it was determined and suggested that hexagonal wire mesh works better than expanded and welded wire meshes.
... The research paper presents a novel approach to assessing the impact of thermal loads on silica fumemodified lightweight concrete by employing hyper-parameter tuning to enhance the performance of different ML models. This study stands out for its focus on feature importance as part of interpretability, providing valuable insights into the factors influencing concrete's residual compressive strength under thermal conditions which was lacking in the previous researches [17][18][19]. ...
... The root mean square error (RMSE) is a statistical metric to quantify the disparities between model-predicted and actual observed values. A smaller RMSE indicates more accurate predictions, while a larger RMSE suggests more significant prediction errors in the model [62]. Table 10 delineates the RMSE of the model based on the third optimization scenario. ...
The utilization of ultra-high-molecular-weight polyethylene fibers (UHMWPEFs) to enhance recycled-brick-aggregate concrete represents an efficacious approach for ameliorating the concrete’s performance. This investigation addresses the influences of recycled-brick aggregates (RAs) and UHMWPEFs on the concrete’s slump, shrinkage, flexural strength, resistance to chloride-ion ingress, and freeze–thaw durability. The mechanisms through which UHMWPEFs ameliorate the performance of the recycled-brick-aggregate concrete were elucidated at both the micro and macroscopic levels. The findings underscore that the three-dimensional network structure established by the UHMWPEFs, while resulting in a reduction in the concrete slump, substantially enhances the concrete’s mechanical properties and durability. A regression model for the multifaceted performance of the UHMWPEF-reinforced recycled-brick-aggregate concrete (F-RAC) was formulated by employing response-surface methodology, and the model’s reliability was confirmed through variance analysis. The interactive effects of the RA and UHMWPEFs on the concrete were analyzed through a combined approach involving response-surface analysis and contour plots. Subsequently, a multiobjective optimization was conducted for the F-RAC performance, yielding the optimal proportions of RA and UHMWPEFs. It was determined that the optimal performance across the dimensions of the shrinkage resistance, flexural strength, chloride-ion resistance, and freeze–thaw durability of the F-RAC could be simultaneously achieved when the substitution rate of the RA was 14.02% and the admixture of the UHMWPEFs was 1.13%.
... Second check applied was that the coefficient between predicted and experimental values or squared correlation coefficient between the experimental and predicted values should also approach 1 [88,89]. Table 7 shows verification of the aforementioned check. ...
A recently introduced bendable concrete having hundred times greater strain capacity provides promising results in repair of engineering structures, known as strain hardening cementitious composites (SHHCs). The current research creates new empirical prediction models to assess the mechanical properties of strain-hardening cementitious composites (SHCCs) i.e., compressive strength (CS), first crack tensile stress (TS), and first crack flexural stress (FS), using gene expression programming (GEP). Wide-ranging records were considered with twelve variables i.e., cement percentage by weight (C%), fine aggregate percentage by weight (Fagg%), fly-ash percentage by weight (FA%), Water-to-binder ratio (W/B), super-plasticizer percentage by weight (SP%), fiber amount percentage by weight (Fib%), length to diameter ratio (L/D), fiber tensile strength (FTS), fiber elastic modulus (FEM), environment temperature (ET), and curing time (CT). The performance of the models was deduced using correlation coefficient (R) and slope of regression line. The established models were also assessed using relative root mean square error (RRMSE), Mean absolute error (MAE), Root squared error (RSE), root mean square error (RMSE), objective function (OBF), performance index (PI) and Nash-Sutcliffe efficiency (NSE). The resulting mathematical GP-based equations are easy to understand and are consistent disclosing the originality of GEP model with R in the testing phase equals to 0.8623, 0.9269, and 0.8645 for CS, TS and FS respectively. The PI and OBF are both less than 0.2 and are in line with the literature, showing that the models are free from overfitting. Consequently, all proposed models have high generalization with less error measures. The sensitivity analysis showed that C%, Fagg%, and ET are the most significant variables for all three models developed with sensitiveness index higher than 10 %. The result of the research can assist researchers, practitioners, and designers to assess SHCC and will lead to sustainable, faster, and safer construction from environment-friendly waste management point of view.
... Zheng et al. [58] reported that gradient boosting (GB) showed excellent precision compared to the RF model in forecasting the flexural strength of steel fiber concrete. Nafees et al. [59] utilized ensemble models of DT and SVR for estimating silica fume-based concrete properties and reported that the ensemble model of DT and SVR model achieved 11% and 1.5% higher accuracy, respectively, compared to the individual models. Moreover, in the study conducted by Cakiroglu et al. [60], three boosting techniques and RF methods were employed to predict the tensile strength of basalt fiber-reinforced concrete. ...
... Regression methods may overvalue the significance of some components [16]. Artificial intelligence (AI)-based strategies, such as machine learning (M-L), are notable among the cutting-edge prediction approaches used in this sector [17][18][19][20]. In the realm of civil engineering, the application of AI has recently gained popularity for the purpose of predicting the performance of concrete [21,22]. ...
... The concept of organizing recyclable materials for ecofriendly technology was created in order to present the most recent achievements in the field of green building and construction materials [11,12]. Natural fillers such as lime stone, clay ceramic waste, silica fume, and others are employed in polymer-based structural composites in civil industries to help make the world a more sustainable environment [13,14]. The chemical treatment of the fiber was determined using FTIR, and the morphological analysis was done using FESEM. ...
The performance of hybrid composites in automotive applications has been improved using natural filler. Numerous researchers are analyzing to create the substitute hybrid materials for ecological sustainability and responsibility in environment. Hybrid composites are made by combining natural filler (CD—Cordia dichotoma) with reinforced polymer (PLA—polylactic acid) resin matrix composites which offer unique mechanical qualities because they contain more renewable, recyclable, and biodegradable materials than synthetic fillers. The objective of this research is to evaluate the dynamic mechanical behavior and thermal property of the addition of natural filler (CD) on the PLA resin for finding the structural effect in hybrid composites. CD natural filler loading on the PLA composites are fabricated by 3D printing. The experimental results demonstrate that composites containing 15 vol% of CD natural filler/PLA have a tensile strength of 14.2 MPa, a flexural strength of 29 MPa, and an impact strength of 1304 J/m² compared to other hybrid composites and the outcomes of the other tests are fully described in this paper. The composite material’s highest modulus of storage and temperature of glass transition are found in the 20 vol% filler CD component. The dielectric strength of the composite made with CD natural filler and PLA at a 20 vol% concentration is 4.73 KV/mm which is higher than that of the other composites. The lowest measurement for water absorption of 15 vol% of CD natural filler/PLA composite has been found the value of 6.5% lower than other composites.
... This method uses input parameters for modeling and depiction, and the output parameters show its validity . For construction applications, machine training algorithms estimate concrete stability (Awoyera et al. 2020;Nafees et al. 2021Nafees et al. , 2022Aslam et al. 2022;Amin et al. 2021), tarry mixture efficiency and concrete permanence (Shi et al. 2023). ...
The present article developed a regression-based analysis to estimate the compressive strength (\(\mathrm{CS}\)) of self-compacting concrete (\(\mathrm{SCC}\)). For the predicting purposes of \(\mathrm{SCC}\), a dataset was created by making experimental samples which included several admixtures more addition to the components of normal concrete (i.e., cement, recycled coarse aggregate, recycled fine aggregate, and water), such as lime powders, fly ash, granulated blast furnace slag, silica fume, steel slag powder, super-plasticizer, and viscosity-modifying admixture. The performance of \(\mathrm{SVR}\) analysis strongly depends on their key parameters, where two population-based optimization algorithms were considered for this purpose, named Black widow optimization algorithm (\(\mathrm{BWOA}\)), and \(\mathrm{COOT}\)-bird optimization algorithm (\(\mathrm{COOT}\)) (abbreviated as \(\mathrm{BWSV}\) and \(\mathrm{COSV}\)). The calculation and analysis show that both optimized \(\mathrm{BWSV}\) and \(\mathrm{COSV}\) regression could strikingly accomplish preferable performance during the estimation procedure, with values of \({R}^{2}\) at 0.9809 and 0.969 related to \(\mathrm{BWSV}\), and 0.9911 and 0.9887 related to \(\mathrm{COSV}\), for the training and investigating data segments, respectively. In the train section, \(\mathrm{COSV}\) could increase the lowest \(\mathrm{PI}\) by 0.0158, less than half of \(\mathrm{BWSV}\) by 0.0252, and over a 50% decrease in the test part. Therefore, it seems that the \(\mathrm{COSV}\) assessment is quite trustworthy for identifying the \(\mathrm{CS}\) of \(\mathrm{SCC}\), although the \(\mathrm{BWSV}\) approach has its abilities in the forecasting phase. So, the outperformed model could be applied to reduce time, money, lab setups, material preparation, and testing with adequate equipment.
... The accuracy of the models was assessed by examining the regression slopes, as shown in Fig. 8. Such kind of evaluation technique has been commonly practiced by various researchers to determine the model's accuracy [133][134][135][136]. For instance, Nafees et al. [136] studied the CS of concrete incorporated with plastic waste and reported regression slopes of 0.93 for training data and 0.86 for testing data, providing the excellent performance of the model. ...
... It can be noticed that the developed models satisfied the external validation criteria as provided in Section 3. Fig. 10 presents the error assessment of the suggested models, illustrating a comparison between experimental results and corresponding predictions. This analysis is conducted in conformity with existing literature [133][134][135]. Fig. 10a-c illustrate that the developed models predicted values followed very closely the actual results of CS. ...
