Evaluation of machine learning models for predicting TiO2 photocatalytic degradation of air contaminants.

The escalation of global urbanization and industrial expansion has resulted in an increase in the emission of harmful substances into the atmosphere. Evaluating the effectiveness of titanium dioxide (TiO2) in photocatalytic degradation through traditional methods is resource-intensive and complex due to the detailed photocatalyst structures and the wide range of contaminants. Therefore in this study, recent advancements in machine learning (ML) are used to offer data-driven approach using thirteen machine learning techniques namely XG Boost (XGB), decision tree (DT), lasso Regression (LR2), support vector regression (SVR), adaBoost (AB), voting Regressor (VR), CatBoost (CB), K-Nearest Neighbors (KNN), gradient boost (GB), random Forest (RF), artificial neural network (ANN), ridge regression (RR), linear regression (LR1) to address the problem of estimation of TiO2 photocatalytic degradation rate of air contaminants. The models are developed using literature data and different methodical tools are used to evaluate the developed ML models. XGB, DT and LR2 models have high R2 values of 0.93, 0.926 and 0.926 in training and 0.936, 0.924 and 0.924 in test phase. While ANN, RR and LR models have lowest R2 values of 0.70, 0.56 and 0.40 in training and 0.62, 0.63 and 0.31 in test phase respectively. XGB, DT and LR2 have low MAE and RMSE values of 0.450 min-1/cm2, 0.494 min-1/cm2 and 0.49 min-1/cm2 for RMSE and 0.263 min-1/cm2, 0.285 min-1/cm2 and 0.29 min-1/cm2 for MAE in test stage. XGB, DT, and LR2 have 93% percent errors within 20% error range in training phase. XGB has 92% and DT, and LR2 have 94% errors with 20% range in test phase. XGB, DT, LR2 models remained the highest performing models and XGB is the most robust and effective in predictions. Feature importances reveal the role of input parameters in prediction made by developed ML models. Dosage, humidity, UV light intensity remain important experimental factors. This study will impact positively in providing efficient models to estimate photocatalytic degradation rate of air contaminants using TiO2.

Comparative analysis of enriched flyash based cement-sand compressed bricks under various curing regimes.

This study investigates the substitution of traditional burnt clay bricks (BCB), used since 7000 BCE, with environmentally friendly Fly Ash-Cement and Sand Composite Bricks (FCBs), utilizing industrial waste like Coal Fly Ash (CFA) from thermal power plants. The research encompasses two phases: the first involves experimental production of FCBs, while the second focuses on optimizing FCBs by varying CFA (50%, 60%, 70%), Ordinary Portland Cement (OPC) content (9%-21%), and incorporating stone dust (SD) and fine sand. Comprehensive tests under normal and steam curing conditions, adhering to ASTM C 67-05 standards, include X-Ray Diffraction (XRD), Energy Dispersive X-Ray (EDX), and Scanning Electron Microscopy (SEM) analyses. Results indicate that steam curing enhances early strength, with an optimized mix (MD: 5S) achieving a compressive strength of 15.57 MPa, flexural strength of 0.67 MPa, water absorption rate of 20.08%, and initial rate of water absorption of 4.64 g/min per 30 in2, devoid of efflorescence. Notably, a 9% OPC and 50% CFA mix (MD: 1S) shows improved early strength of 4.95 MPa at 28 days. However, excessive CFA replacement (70%) with lesser cement content negatively impacts physio-mechanical properties. This research underscores the potential of FCBs as a sustainable and economically viable alternative to BCBs in the construction industry.

Development and characterization of non-proprietary ultra high performance concrete.

This paper presents the developmental process of ultra-high performance concrete (UHPC), the most advanced form of concrete. The entire process exclusively utilized locally available materials. The mixes were prepared without using any specialized mixer or treatments, such as elevated pressure, etc. The primary objective of the research was to develop low-cost non-proprietary version of UHPC by optimizing both cementitious and non-cementitious materials to attain the highest levels of workability, compressive strength, flexural strength and durability. The research utilizes a trial-and-error approach, subjecting specimens to curing in both regular and heated water. The findings validate the viability of producing self-compacting UHPC with compressive strength ranging from 120 to 160 MPa, employing local materials and manufacturing methods. Raw materials and mixing sequence had a significant influence on the fresh and hardened properties of UHPC. The inclusion of steel fibers and the application of heat treatment remarkably enhanced the compressive strength. Furthermore, cost analysis revealed that this particular UHPC is only slightly over four times more expensive than conventional concrete, in contrast to commercially available UHPC, which is approximately 10 times expensive than traditional concrete.

Predicting the performance of existing pre-cast concrete pipes using destructive and non-destructive testing techniques.

One of the most significant and critical urban assets for a sustainable community is the sewer pipeline network and water distribution system. Water sewer networks and distribution systems have a definite service life span to provide continuous facilities to end users. Therefore, it is pertinent to continuously evaluate the condition of water and sewer concrete pipelines to ensure the reliable, sustainable, and cost-efficient transport of water and sewerage for the safety of society. The condition assessment is commonly carried out by visual observations followed by some non-destructive testing methods. However, it is the need of the hour to shift assessment methods to advance assessment techniques to save time and money for our community. Currently, in this project, the condition assessment of pre-cast concrete pipes was carried out by destructive and non-destructive methods. Different test trials i.e., ultra-sonic pulse velocity, Schmidt hammer also known as rebound hammer test, visual inspection, three edge bearing test, and core cutting test on the old buried and new concrete pipes were performed. It was observed that concrete used for the construction of existing precast concrete pipes still has better quality indices after 20 years as compared to that of concrete of new pipes. However, steel has deteriorated with time and clear corrosion of steel was identified in existing pre-cast concrete pipes. At the same time, it was observed that there should be an automated mechanism to continuously asses the condition of pre-cast existing pipes which will address the sustainable development goals (SDG 6, 9, 11). Consequently, it can be said that condition assessment of pre-cast concrete pipes will lead to sustainable societies and infrastructure.

Prediction of Autogenous Shrinkage of Concrete Incorporating Super Absorbent Polymer and Waste Materials through Individual and Ensemble Machine Learning Approaches.

The use of superabsorbent polymers, sometimes known as SAP, is a tremendously efficacious method for reducing the amount of autogenous shrinkage (AS) that occurs in high-performance concrete. This study utilizes support vector regression (SVR) as a standalone machine-learning algorithm (MLA) which is then ensemble with boosting and bagging approaches to reduce the bias and overfitting issues. In addition, these ensemble methods are optimized with twenty sub-models with varying the nth estimators to achieve a robust R2. Moreover, modified bagging as random forest regression (RFR) is also employed to predict the AS of concrete containing supplementary cementitious materials (SCMs) and SAP. The data for modeling of AS includes water to cement ratio (W/C), water to binder ratio (W/B), cement, silica fume, fly ash, slag, the filer, metakaolin, super absorbent polymer, superplasticizer, super absorbent polymer size, curing time, and super absorbent polymer water intake. Statistical and k-fold validation is used to verify the validation of the data using MAE and RMSE. Furthermore, SHAPLEY analysis is performed on the variables to show the influential parameters. The SVM with AdaBoost and modified bagging (RF) illustrates strong models by delivering R2 of approximately 0.95 and 0.98, respectively, as compared to individual SVR models. An enhancement of 67% and 63% in the RF model, while in the case of SVR with AdaBoost, it was 47% and 36%, in RMSE and MAE of both models, respectively, when compared with the standalone SVR model. Thus, the impact of a strong learner can upsurge the efficiency of the model.

Potential of Alkali-Silica Reactivity of Unexplored Local Aggregates as per ASTM C1260.

Alkali-silica reaction (ASR) is one of the major durability issues that affect the material degradation and structural performance, compromising the service life of concrete structures. Therefore, this study was planned to investigate the potential of ASR for locally available unexplored and vastly used aggregates, as per ASTM C1260. Aggregates from five different sources (Shalozan, Abbotabad, Orakzai, Swabi and Sada) were procured from their respective crusher sites. Mineralogical components of these aggregates were studied using the petrographic analysis. Cube, prism and mortar bar specimens were cast using mixture design in accordance with ASTM C1260 and placed in sodium hydroxide solution at 80 °C for 90 days. Identical specimens were also cured in water for the purpose of comparison. It was observed that mortar bar expansion of Orakzai aggregate was higher among the other tested aggregates and greater than 0.20% at 28 days, indicating the reactive nature according to ASTM C1260. Petrographic analysis also revealed the presence of reactive silica (quartzite) in the tested Orakzai source. It was observed that the compressive and flexural strengths of specimens exposed to ASR conducive environment was lower than the identical specimens placed in water. For instance, an approximately 9% decrease in compressive strength was observed for Orakzai aggregates exposed to ASR environment at 90 days compared to similar specimens placed in water curing. Moreover, microstructural analysis showed the development of micro-cracks for specimens incorporating Orakzai source aggregates. This study assists the construction stakeholders for the potential of unexplored local aggregates with regard to ASR before its utilization in mega construction projects.

Investigation of CFRP Reinforcement Ratio on the Flexural Capacity and Failure Mode of Plain Concrete Prisms.

The utilization of carbon-fiber-reinforced polymer (CFRP) composites as strengthening materials for structural components has become quite famous over the last couple of decades. The present experimental study was carried out to examine the effect of varied widths of externally bonded CFRP on the debonding strain of CFRP and the failure mode of plain concrete beams. Twelve plain concrete prims measuring 100 mm × 100 mm × 500 mm were cast and tested under identical loading conditions. The twelve specimens include two control prisms, i.e., without CFRP strips, and the remaining ten prisms were reinforced with CFRP strips with widths of 10 mm, 20 mm, 30 mm, 40 mm, and 50 mm, respectively, i.e., two prisms in each group. Four-point loading flexural testing was carried out, and the resulting data are presented in the form of peak load vs. midpoint displacement, load vs. concrete strain, and load vs. CFRP strain. The peak load was directly recorded from the testing machine, while the midpoint deflection was recorded through the linear variable differential transducer (LVDT) installed at the midpoint. To measure the strain, two separate strain gauges were installed at the bottom of each concrete prism, i.e., one on the concrete surface and the other on the surface of the CFRP strip. The results of this study indicate that the debonding strain is a function of CFRP strip width and that the failure patterns of beams are significantly affected by the CFRP reinforcement ratio.

Two-Way Shear Resistance of FRP Reinforced-Concrete Slabs: Data and a Comparative Study.

This study aims to investigate the two-way shear strength of concrete slabs with FRP reinforcements. Twenty-one strength models were briefly outlined and compared. In addition, information on a total of 248 concrete slabs with FRP reinforcements were collected from 50 different research studies. Moreover, behavior trends and correlations between their strength and various parameters were identified and discussed. Strength models were compared to each other with respect to the experimentally measured strength, which were conducted by comparing overall performance versus selected basic variables. Areas of future research were identified. Concluding remarks were outlined and discussed, which could help further the development of future design codes. The ACI is the least consistent model because it does not include the effects of size, dowel action, and depth-to-control perimeter ratio. While the EE-b is the most consistent model with respect to the size effect, concrete compressive strength, depth to control perimeter ratio, and the shear span-to-depth ratio. This is because of it using experimentally observed behavior as well as being based on mechanical bases.

Manufacturing of Sustainable Untreated Coal Ash Masonry Units for Structural Applications.

Burnt clay bricks are one of the most important building units worldwide, are easy and cheap to make, and are readily available. However, the utilization of fertile clay in the production of burnt clay bricks is also one of the causes of environmental pollution because of the emission of greenhouse gases from industrial kilns during the large-scale burning process. Therefore, there is a need to develop a new class of building units (bricks) incorporating recycled industrial waste, leading toward sustainable construction by a reduction in the environmental overburden. This research aimed to explore the potential of untreated coal ash for the manufacturing of building units (coal ash unburnt bricks). Coal ash unburnt bricks were manufactured at an industrial brick plant by applying a pre-form pressure of 3 MPa and later curing them via water sprinkling in a control shed. Various proportions of coal ash (i.e., 30, 35, 40, 45, 50, and 55%) were employed to investigate the mechanical and durability-related properties of the resulting bricks, then they were compared with conventional burnt clay bricks. Compressive strength, flexural strength, an initial rate of water absorption, efflorescence, microstructural analysis via scanning electron microscopy, and cost analysis were conducted. The results of the compressive strength tests revealed that the compressive strength of coal ash unburnt brick decreased with an increase in the content of coal ash; however, up to a 45% proportion of coal ash, the minimum required compressive strength specified by ASTM C62 and local building codes was satisfied. Furthermore, bricks incorporating up to 45% of coal ash also satisfied the ASTM C62 requirements for water absorption. Coal ash unburnt bricks are lighter in weight owing to their porous developed microstructure. The cost analysis showed that the utilization of untreated, locally available coal ash in brick production leads us on the path toward more economical and sustainable building units.

Comparison of Prediction Models Based on Machine Learning for the Compressive Strength Estimation of Recycled Aggregate Concrete.

Numerous tests are used to determine the performance of concrete, but compressive strength (CS) is usually regarded as the most important. The recycled aggregate concrete (RAC) exhibits lower CS compared to natural aggregate concrete. Several variables, such as the water-cement ratio, the strength of the parent concrete, recycled aggregate replacement ratio, density, and water absorption of recycled aggregate, all impact the RAC's CS. Many studies have been carried out to ascertain the influence of each of these elements separately. However, it is difficult to investigate their combined effect on the CS of RAC experimentally. Experimental investigations entail casting, curing, and testing samples, which require considerable work, expense, and time. It is vital to adopt novel methods to the stated aim in order to conduct research quickly and efficiently. The CS of RAC was predicted in this research utilizing machine learning techniques like decision tree, gradient boosting, and bagging regressor. The data set included eight input variables, and their effect on the CS of RAC was evaluated. Coefficient correlation (R2), the variance between predicted and experimental outcomes, statistical checks, and k-fold evaluations, were carried out to validate and compare the models. With an R2 of 0.92, the bagging regressor technique surpassed the decision tree and gradient boosting in predicting the strength of RAC. The statistical assessments also validated the superior accuracy of the bagging regressor model, yielding lower error values like mean absolute error (MAE) and root mean square error (RMSE). MAE and RMSE values for the bagging model were 4.258 and 5.693, respectively, which were lower than the other techniques employed, i.e., gradient boosting (MAE = 4.956 and RMSE = 7.046) and decision tree (MAE = 6.389 and RMSE = 8.952). Hence, the bagging regressor is the best suitable technique to predict the CS of RAC.

Prediction of Mechanical Properties of Fly-Ash/Slag-Based Geopolymer Concrete Using Ensemble and Non-Ensemble Machine-Learning Techniques.

The emission of greenhouse gases and natural-resource depletion caused by the production of ordinary Portland cement (OPC) have a detrimental effect on the environment. Thus, an alternative means is required to produce eco-friendly concrete such as geopolymer concrete (GPC). However, GPC has a complex cementitious matrix and an ambiguous mix design. Aside from that, the composition and proportions of materials utilized may have an impact on the compressive strength. Similarly, the use of robust and efficient machine-learning (ML) approaches is now required to forecast the strength of such a composite cementitious matrix. As a result, this study anticipated the compressive strength of GPC with waste resources using ensemble and non-ensemble ML algorithms. This was accomplished through the use of Anaconda (Python). To build a strong ensemble learner by integrating weak learners, adaptive boosting, random forest (RF), and ensemble learner bagging were employed. Furthermore, ensemble learners were utilized on non-ensemble or weak learners, such as decision trees (DT) and support vector machines (SVM) via regression. The data encompassed 156 statistical samples in which nine variables, namely superplasticizer (kg/m3), fly ash (kg/m3), ground granulated blast-furnace slag (GGBS), temperature (°C), coarse and fine aggregate (kg/m3), sodium silicate (Na2SiO3), and sodium hydroxide (NaOH), were chosen to anticipate the results. Exploring it in depth, twenty sub-models with ensemble boosting and bagging approaches were trained, and tuning was performed to achieve the highest possible coefficient of determination (R2). Moreover, cross K-Fold validation analysis and statistical checks were performed via indicators for the evaluation of the models. The result revealed that ensemble approaches yielded robust performance compared to non-ensemble algorithms. Generally, an ensemble learner with the RF and bagging approach on a DT yielded robust performance by achieving a better R2 as 0.93, and with the lowest statistical errors. The communal model in artificial-intelligence analysis, on average, improved the accuracy of the model.

Eco-Friendly Incorporation of Crumb Rubber and Waste Bagasse Ash in Bituminous Concrete Mix.

The consumption of waste materials in the construction sector is a sustainable approach that helps in reducing the environmental pollution and decreases the construction cost. The present research work emphasizes the mechanical properties of bituminous concrete mix prepared with crumb rubber (CR) and waste sugarcane bagasse ash (SCBA). For the preparation of bituminous concrete mix specimens with CR and SCBA, the effective bitumen content was determined using the Marshall Mix design method. A total of 15 bituminous concrete mix specimens with 4%, 4.5%, 5%, 5.5% and 6% of bitumen content were prepared, and the effective bitumen content turned out to be 4.7%. The effect of five different CR samples of 2%, 4%, 6%, 8% and 10% by weight of total mix and SCBA samples of 25%, 50%, 75% and 100% by weight of filler were investigated on the performance of bituminous concrete. A total of 180 samples with different percentages of CR and SCBA were tested for indirect tensile strength (ITS) and Marshall Stability, and the results were compared with conventional bituminous concrete mix. It was observed that the stability values rose with an increase in CR percentage up to 6%, while the flow values rose as the percentage of SCBA increased in the mix. Maximum ITS results were observed at 4% CR and 25% SCBA replacement levels. However, a decrease in stability and ITS result was observed as the percentages of CR and SCBA increased beyond 4% and 25%, respectively. We concluded that the optimum CR and SCBA content of 4% and 25%, respectively, can be effectively used as a sustainable alternative in bituminous concrete mix.

Application of Soft Computing Techniques to Predict the Strength of Geopolymer Composites.

Geopolymers may be the best alternative to ordinary Portland cement because they are manufactured using waste materials enriched in aluminosilicate. Research on geopolymer composites is accelerating. However, considerable work, expense, and time are needed to cast, cure, and test specimens. The application of computational methods to the stated objective is critical for speedy and cost-effective research. In this study, supervised machine learning approaches were employed to predict the compressive strength of geopolymer composites. One individual machine learning approach, decision tree, and two ensembled machine learning approaches, AdaBoost and random forest, were used. The coefficient correlation (R2), statistical tests, and k-fold analysis were used to determine the validity and comparison of all models. It was discovered that ensembled machine learning techniques outperformed individual machine learning techniques in forecasting the compressive strength of geopolymer composites. However, the outcomes of the individual machine learning model were also within the acceptable limit. R2 values of 0.90, 0.90, and 0.83 were obtained for AdaBoost, random forest, and decision models, respectively. The models' decreased error values, such as mean absolute error, mean absolute percentage error, and root-mean-square errors, further confirmed the ensembled machine learning techniques' increased precision. Machine learning approaches will aid the building industry by providing quick and cost-effective methods for evaluating material properties.

Concrete by Preplaced Aggregate Method Using Silica Fume and Polypropylene Fibres.

Preplaced aggregate concrete (PAC) is prepared in two steps, with the coarse aggregate being initially laid down in the formwork, after which a specialised grout is injected into it. To enhance the properties of concrete and to reduce the emission of CO2 produced during the production of cement, supplementary cementitious materials (SCMs) are used to partially substitute ordinary Portland cement (OPC). In this study, 100 mm × 200 mm (diameter x height) PAC cylinders were cast with 10 per cent of cement being substituted with silica fume; along with that, 1.5% dosage of Macro polypropylene fibres were also introduced into the coarse aggregate matrix. Compressive strength test, splitting tensile strength test, mass loss at 250 °C, and compressive strength at 250 °C were performed on the samples. PAC samples with 10% of cement replaced with Silica Fume (SPAC) were used as control samples. The primary objective of this study was to observe the effect of the addition of Polypropylene fibres to PAC having Silica fume as SCM (FRPAC). The aforementioned tests showed that FRPAC had a lower compressive strength than that of the control mix (SPAC). FRPAC had greater tensile strength than that of NPAC and SPAC. Mass loss at 250 °C was greater in SPAC compared to FRPAC. The compressive strength loss at 250 °C was significantly greater in FRPAC compared to SPAC. FRPAC exhibited a greater strain for the applied stress, and their stress-strain curve showed that FRPAC was more ductile than SPAC.

Impact Resistance of Styrene-Butadiene Rubber (SBR) Latex-Modified Fiber-Reinforced Concrete: The Role of Aggregate Size.

Improvements in tensile strength and impact resistance of concrete are among the most researched issues in the construction industry. The present study aims to improve the properties of concrete against impact loadings. For this purpose, energy-absorbing materials are used along with fibers that help in controlling the crack opening. A polymer-based energy-absorbing admixture, SBR latex, along with polypropylene fibers are used in this study to improve the impact resistance. Along with fibers and polymers, the effect of the size of aggregates was also investigated. In total, 12 mixes were prepared and tested against the drop weight test and the Charpy impact test. Other than this, mechanical characterization was also carried out for all the 12 concrete mixes. Three dosages of SBR latex, i.e., 0%, 4%, and 8% by weight of cement, were used along with three aggregates sizes, 19 mm down, 10 mm down, and 4.75 mm down. The quantity of polypropylene fibers was kept equal to 0.5% in all mixes. In addition to these, three control samples were also prepared for comparison. The mix design was performed to achieve a normal-strength concrete. For this purpose, a concrete mix of 1:1.5:3 was used with a water to a cement ratio of 0.4 to achieve a normal-strength concrete. The experimental study concluded that the addition of SBR latex improves the impact resistance of concrete. Furthermore, an increase in impact resistance was also observed for a larger aggregate size. The use of fibers and SBR latex is encouraged due to their positive results and the fact that they provide an economical solution for catering to impact strains. The study concludes that 4% SBR latex and 0.5% fibers with a larger aggregate size improve the resistance against impact loads.

Predicting the Mechanical Properties of RCA-Based Concrete Using Supervised Machine Learning Algorithms.

Environment-friendly concrete is gaining popularity these days because it consumes less energy and causes less damage to the environment. Rapid increases in the population and demand for construction throughout the world lead to a significant deterioration or reduction in natural resources. Meanwhile, construction waste continues to grow at a high rate as older buildings are destroyed and demolished. As a result, the use of recycled materials may contribute to improving the quality of life and preventing environmental damage. Additionally, the application of recycled coarse aggregate (RCA) in concrete is essential for minimizing environmental issues. The compressive strength (CS) and splitting tensile strength (STS) of concrete containing RCA are predicted in this article using decision tree (DT) and AdaBoost machine learning (ML) techniques. A total of 344 data points with nine input variables (water, cement, fine aggregate, natural coarse aggregate, RCA, superplasticizers, water absorption of RCA and maximum size of RCA, density of RCA) were used to run the models. The data was validated using k-fold cross-validation and the coefficient correlation coefficient (R2), mean square error (MSE), mean absolute error (MAE), and root mean square error values (RMSE). However, the model's performance was assessed using statistical checks. Additionally, sensitivity analysis was used to determine the impact of each variable on the forecasting of mechanical properties.

Performance of sustainable self-compacting fiber reinforced concrete with substitution of marble waste (MW) and coconut fibers (CFs).

Self compacting concrete (SCC) is special type of concrete which is highly flowable and non-segregated and by its own mass, spreads into the formwork without any external vibrators, even in the presence of thick reinforcement. But SSC is also brittle nature like conventional concrete, which results in abrupt failure without giving any deformation (warning), which is undesirable for any structural member. Thus, self-compacting concrete (SCC) needs some of tensile reinforcement to enhance tensile strength and prevent the unsuitable abrupt failure. But fiber increased tensile strength of concrete more effectively than compressive strength. Hence, it is essential to add pozzolanic materials into fiber reinforced concrete to achieve high strength, durable and ductile concrete. This study is conducted to assess the performance of SCC with substitutions of marble waste (MW) and coconut fiber (CFs) into SCC. MW utilized as cementitious (pozzolanic) materials in percentage of 5.0 to 30% in increment of 5.0% by weight of binder and concrete is reinforced with CFs in proportion of 0.5 to 3.0% in increment of 0.5% by weight of binder. Rheological characteristics were measured through its filling and passing ability by using Slump flow, Slump T50, L-Box, and V-funnel tests while mechanical characteristics were measured through compressive strength, split tensile strength, flexure strength and bond strength (pull out) tests. Experimental investigation show that MW and CFs decrease the passing ability and filling ability of SCC. Additionally, Experimental investigation show that MW up to 20% and CFs addition 2.0% by weight of binder tend to increase the mechanical performance of SCC. Furthermore, statistical analysis (RSM) was used to optimize the combined dose of MW and CFs into SCC to obtain high strength self-compacting concrete.

Predictive Modeling of Mechanical Properties of Silica Fume-Based Green Concrete Using Artificial Intelligence Approaches: MLPNN, ANFIS, and GEP.

Silica fume (SF) is a mineral additive that is widely used in the construction industry when producing sustainable concrete. The integration of SF in concrete as a partial replacement for cement has several evident benefits, including reduced CO2 emissions, cost-effective concrete, increased durability, and mechanical qualities. As environmental issues continue to grow, the development of predictive machine learning models is critical. Thus, this study aims to create modelling tools for estimating the compressive and cracking tensile strengths of silica fume concrete. Multilayer perceptron neural networks (MLPNN), adaptive neural fuzzy detection systems (ANFIS), and genetic programming are all used (GEP). From accessible literature data, a broad and accurate database of 283 compressive strengths and 149 split tensile strengths was created. The six most significant input parameters were cement, fine aggregate, coarse aggregate, water, superplasticizer, and silica fume. Different statistical measures were used to evaluate models, including mean absolute error, root mean square error, root mean squared log error and the coefficient of determination. Both machine learning models, MLPNN and ANFIS, produced acceptable results with high prediction accuracy. Statistical analysis revealed that the ANFIS model outperformed the MLPNN model in terms of compressive and tensile strength prediction. The GEP models outperformed all other models. The predicted values for compressive strength and splitting tensile strength for GEP models were consistent with experimental values, with an R2 value of 0.97 for compressive strength and 0.93 for splitting tensile strength. Furthermore, sensitivity tests revealed that cement and water are the determining parameters in the growth of compressive strength but have the least effect on splitting tensile strength. Cross-validation was used to avoid overfitting and to confirm the output of the generalized modelling technique. GEP develops an empirical expression for each outcome to forecast future databases' features to promote the usage of green concrete.