Estimating Compressive Strength of Concrete Using Neural Electromagnetic Field Optimization.

Concrete compressive strength (CCS) is among the most important mechanical characteristics of this widely used material. This study develops a novel integrative method for efficient prediction of CCS. The suggested method is an artificial neural network (ANN) favorably tuned by electromagnetic field optimization (EFO). The EFO simulates a physics-based strategy, which in this work is employed to find the best contribution of the concrete parameters (i.e., cement (C), blast furnace slag (SBF), fly ash (FA1), water (W), superplasticizer (SP), coarse aggregate (AC), fine aggregate (FA2), and the age of testing (AT)) to the CCS. The same effort is carried out by three benchmark optimizers, namely the water cycle algorithm (WCA), sine cosine algorithm (SCA), and cuttlefish optimization algorithm (CFOA) to be compared with the EFO. The results show that hybridizing the ANN using the mentioned algorithms led to reliable approaches for predicting the CCS. However, comparative analysis indicates that there are appreciable distinctions between the prediction capacity of the ANNs created by the EFO and WCA vs. the SCA and CFOA. For example, the mean absolute error calculated for the testing phase of the ANN-WCA, ANN-SCA, ANN-CFOA, and ANN-EFO was 5.8363, 7.8248, 7.6538, and 5.6236, respectively. Moreover, the EFO was considerably faster than the other strategies. In short, the ANN-EFO is a highly efficient hybrid model, and can be recommended for the early prediction of the CCS. A user-friendly explainable and explicit predictive formula is also derived for the convenient estimation of the CCS.

Optimization of Fly Ash-Slag One-Part Geopolymers with Improved Properties.

One-part geopolymer concrete/mortar is a pre-mixed material made from industrial by-products and solid alkaline activators that only requires the addition of water for activation. Apart from being environmentally friendly, it also reduces complexity and improves consistency in the mixing process, leading to more efficient production and consistent material properties. However, developing one-part geopolymer concrete with desirable compressive strength is challenging because of the complexity of the chemical reaction involved, the variability of the raw materials used, and the need for precise control of curing conditions. Therefore, 80 different one-part geopolymer mixtures were compiled from the open literature in this study, and the effects of the constituent materials, the dosage of alkaline activators, curing condition, and water/binder ratio on the 28-day compressive strength of one-part geopolymer paste were examined in detail. An ANN model with the Levenberg-Marquardt algorithm was developed to estimate one-part geopolymer's compressive strength and its sensitivity to binder constituents and alkaline dosage. The ANN model's weights and biases were also used to develop a CPLEX-based optimization method for achieving maximum compressive strength. The results confirm that the compressive strength of one-part geopolymer pastes increased by increasing the Na2O content of the alkaline source and the slag dosage; however, increasing the Na2O content in alkaline sources beyond 6% by fly ash weight led to decreasing the compressive strength; therefore, the optimum alkaline activator dosage by weight of fly ash was to be 12% (i.e., 6% Na2O). The proposed ANN model developed in this study can aid in the production and performance tuning of sustainable one-part geopolymer concrete and mortar for broader full-scale applications.

Valorizing hazardous lead glass sludge and alumina flakes filling waste for the synthesis of geopolymer building bricks.

Geopolymer bricks from lead glass sludge (LGS) and alumina flakes filling (AFF) waste were synthesized in the present work. AFF waste was chemically treated to prepare sodium aluminate (NaAlO2) powder. Silicate source (untreated LGS and thermally treated one at 600 °C (LGS600)) and sodium oxide (Na2O) concentration (as NaAlO2) were the compositional parameters, which affected the physical and mechanical properties (compressive strength, water absorption, and bulk density) of the prepared bricks. High organic matter content inside LGS caused a retardation effect on the geopolymerization process, resulting in the formation of hardened bricks with modest 90-day compressive strengths (2.13 to 4.4 MPa). Using LGS600 enhanced the mechanical properties of the fabricated bricks, achieving a maximum 90-day compressive strength of 22.35 MPa at 3 wt.% Na2O. Sodium aluminosilicate hydrate was the main activation product inside all samples, as confirmed by X-ray diffraction and thermal analyses. Acetic acid leaching test also proved that all LGS600-NaAlO2 mixtures represented Pb concentrations in leachates lower than the permissible level of characteristic leaching procedures, indicating the mitigation of environmental problems caused by these wastes.

Investigation of Alkali-Activated Slag-Based Composite Incorporating Dehydrated Cement Powder and Red Mud.

Recycled construction cementitious materials (RCCM) and red mud (RM) could be considered a type of discarded material with potential cementitious properties. Generally, landfilling and stacking are utilized to dispose of this type of solid waste, which can be detrimental to the environment and sustainability of the construction sector. Accordingly, a productive process for making eco-efficient alkali-activated slag-based samples with the inclusion of RCCM and red mud is studied in this paper. Dehydrated cement powder (DCP) is attained through the high-temperature treatment of RCCM, and red mud can be obtained from the alumina industry. Subsequently, DCP and RM are utilized as a partial substitute for granulated blast furnace slag (GBFS) in alkali-activated mixtures. Two different batches were designed; the first batch had only DCP at a dosage of 15%, 30%, 45%, and 60% as a partial substitute for GBFS, and the second batch had both DCP and RM at 15%, 30%, 45%, and 60% as a partial substitute for GBFS. Different strength and durability characteristics were assessed. The findings show that when both dehydrated cement powder and red mud are utilized in high quantities, the strength and durability of the specimens were enhanced, with compressive strength improving by 42.2% at 28 days. Such improvement was obtained when 7.5% each of DCP and RM were added. The results revealed that DCP and RM have a negative effect on workability, whilst they had a positive impact on the drying shrinkage as well as the mechanical strength. X-ray diffraction and micro-structural analysis showed that when the amount of DCP and RM is increased, a smaller number of reactive products forms, and the microstructure was denser than in the case of the samples made with DCP alone. It was also confirmed that when DCP and RM are used at optimized dosages, they can be a potential sustainable binder substitute; thus, valorizing wastes and inhibiting their negative environmental footprint.

Systematic Experimental Assessment of POFA Concrete Incorporating Waste Tire Rubber Aggregate.

Several researchers devoted considerable efforts to partially replace natural aggregates in concrete with recycled materials such as recycled tire rubber. However, this often led to a significant reduction in the compressive strength of rubberized concrete due to the weaker interfacial transition zone between the cementitious matrix and rubber particles and the softness of rubber granules. Thereafter, significant research has explored the effects of supplementary cementitious materials such as zeolite, fly ash, silica fume, and slag used as partial replacement for cement on rubberized concrete properties. In this study, systematic experimental work was carried out to assess the mechanical properties of palm oil fuel ash (POFA)-based concrete incorporating tire rubber aggregates (TRAs) using the response surface methodology (RSM). Based on the findings, reasonable compressive, flexure, and tensile strengths were recorded or up to 10% replacement of sand with recycled tire fibre and fine TRAs. In particular, the reduction in compressive, tensile, and flexural strengths of POFA concrete incorporating fibre rubber decreased by 16.3%, 9.8%, and 10.1% at 365 days compared to normal concrete without POFA and rubber. It can be concluded that utilization of a combination of POFA and fine or fibre rubber could act as a beneficial strategy to solve the weakness of current rubberized concrete's strength as well as to tackle the environmental issues of the enormous stockpiles of waste tires worldwide.

Effect of Polymers on Behavior of Ultra-High-Strength Concrete.

The development of ultra-high-performance concrete (UHPC) is still practically limited due to the scarcity of robust mixture designs and sustainable sources of local constituent materials. This study investigates the engineering characteristics of Styrene Butadiene Rubber (SBR) polymeric fiber-reinforced UHPC with partial substitution of cement at 0, 5 and 20 wt.% with latex polymer under steam and air curing techniques. The compressive and tensile strengths along with capillary water absorption and sulfate resistance were measured to evaluate the mechanical and durability properties. Scanning Electron Microscopy (SEM) was carried out to explore the microstructure development and hydration products in the designed mixtures under different curing regimes. The results indicated that the mixtures incorporating 20 wt.% SBR polymer achieved superior compressive strength at later ages. Additionally, the tensile strength of the polymeric UHPC without steel fibers and with 20% polymers was enhanced by 50%, which promotes the development of novel UHPC mixtures in which steel fibers could be partially replaced by polymer, while enhancing the tensile properties.

Predicting Compressive and Splitting Tensile Strengths of Silica Fume Concrete Using M5P Model Tree Algorithm.

Compressive strength (CS) and splitting tensile strength (STS) are paramount parameters in the design of reinforced concrete structures and are required by pertinent standard provisions. Robust prediction models for these properties can save time and cost by reducing the number of laboratory trial batches and experiments needed to generate suitable design data. Silica fume (SF) is often used in concrete owing to its substantial enhancements of the engineering properties of concrete and its environmental benefits. In the present study, the M5P model tree algorithm was used to develop models for the prediction of the CS and STS of concrete incorporating SF. Accordingly, large databases comprising 796 data points for CS and 156 data records for STS were compiled from peer-reviewed published literature. The predictions of the M5P models were compared with linear regression analysis and gene expression programming. Different statistical metrics, including the coefficient of determination, correlation coefficient, root mean squared error, mean absolute error, relative squared error, and discrepancy ratio, were deployed to appraise the performance of the developed models. Moreover, parametric analysis was carried out to investigate the influence of different input parameters, such as the SF content, water-to-binder ratio, and age of the specimen, on the CS and STS. The trained models offer a rapid and accurate tool that can assist the designer in the effective proportioning of silica fume concrete.

Mechanical Behavior of Ultrahigh-Performance Concrete Tunnel Lining Segments.

Ultrahigh-performance concrete (UHPC) is a novel material demonstrating superior mechanical, durability and sustainability performance. However, its implementation in massive structures is hampered by its high initial cost and the lack of stakeholders' confidence, especially in developing countries. Therefore, the present study explores, for the first time, a novel application of UHPC, incorporating hybrid steel fibers in precast tunnel lining segments. Reduced scale curved tunnel lining segments were cast using UHPC incorporating hybrid 8 mm and 16 mm steel fibers at dosages of 1%, 2% and 3% by mixture volume. Flexural and thrust load tests were conducted to investigate the mechanical behavior of UHPC tunnel lining segments thus produced. It was observed that the flow of UHPC mixtures decreased due to steel fibers addition, yet steel fibers increased the mechanical and durability properties. Flexural tests on lining segments showed that both the strain hardening (multiple cracking) and strain softening (post-peak behavior) phases were enhanced due to hybrid addition of steel fibers in comparison with the control segments without fibers. Specimens incorporating 3% of hybrid steel fibers achieved 57% increase in ultimate load carrying capacity and exhibited multiple cracking patterns compared to that of identical UHPC segments with 1% fibers. Moreover, segments without fibers incurred excessive cracking and spalling of concrete at the base under the thrust load test. However, more stable behavior was observed for segments incorporating steel fibers under the thrust load, indicating its capability to resist typical thrust loads during tunnel lining field installation. This study highlights the potential use of UHPC with hybrid steel fibers for improved structural behavior. Moreover, the use of UHPC allows producing structural members with reduced cross-sectional dimensions, leading to reduced overall structural weight and increased clear space.

Estimating CO2 Emission Savings from Ultrahigh Performance Concrete: A System Dynamics Approach.

Ordinary Portland cement concrete (OPC) is the world's most consumed commodity after water. However, the production of cement is a major contributor to global anthropogenic CO2 emissions. In recent years, ultrahigh performance concrete (UHPC) has emerged as a strong contender to replace OPC in diverse applications. UHPC has much higher mechanical strength, and thus less material is used in a structural member to resist the same load. Moreover, it has a much longer service life, reducing the long-term need for repair and replacement of aging civil infrastructure. Thus, UHPC can enhance the sustainability of cement and concrete. However, there is currently no robust tool to estimate the sustainability benefits of UHPC. This task is challenging considering that such benefits can only be captured over the long-term since variables, such as population growth and cement demand per capita, become more uncertain. In addition, the problem of CO2 emissions from cement and concrete is a complex system affected by time-dependent feedback. The System Dynamics (SD) method has specifically been developed for modeling such complex systems. Accordingly, a SD model was developed in this study to test various pertinent policy scenarios. It is shown that UHPC can reduce cumulative CO2 emissions of cement and concrete-over the studied simulation period-by more than 17%. If supplementary cementitious materials are further deployed in UHPC and new technologies permit reducing the carbon footprint per unit mass of cement, emission savings can become more substantial. The model offers a flexible framework where the user controls various inputs and can extend the model to account for new data, without the need for reconstruction of the entire model.

Life-Cycle Assessment of Alkali-Activated Materials Incorporating Industrial Byproducts.

Eco-friendly and sustainable materials that are cost-effective, while having a reduced carbon footprint and energy consumption, are in great demand by the construction industry worldwide. Accordingly, alkali-activated materials (AAM) composed primarily of industrial byproducts have emerged as more desirable alternatives to ordinary Portland cement (OPC)-based concrete. Hence, this study investigates the cradle-to-gate life-cycle assessment (LCA) of ternary blended alkali-activated mortars made with industrial byproducts. Moreover, the embodied energy (EE), which represents an important parameter in cradle-to-gate life-cycle analysis, was investigated for 42 AAM mixtures. The boundary of the cradle-to-gate system was extended to include the mechanical and durability properties of AAMs on the basis of performance criteria. Using the experimental test database thus developed, an optimized artificial neural network (ANN) combined with the cuckoo optimization algorithm (COA) was developed to estimate the CO2 emissions and EE of AAMs. Considering the lack of systematic research on the cradle-to-gate LCA of AAMs in the literature, the results of this research provide new insights into the assessment of the environmental impact of AAM made with industrial byproducts. The final weight and bias values of the AAN model can be used to design AAM mixtures with targeted mechanical properties and CO2 emission considering desired amounts of industrial byproduct utilization in the mixture.

Mitigating Portland Cement CO2 Emissions Using Alkali-Activated Materials: System Dynamics Model.

While alkali-activated materials (AAMs) have been hailed as a very promising solution to mitigate colossal CO2 emissions from world portland cement production, there is lack of robust models that can demonstrate this claim. This paper pioneers a novel system dynamics model that captures the system complexity of this problem and addresses it in a holistic manner. This paper reports on this object-oriented modeling paradigm to develop a cogent prognostic model for predicting CO2 emissions from cement production. The model accounts for the type of AAM precursor and activator, the service life of concrete structures, carbonation of concrete, AAM market share, and policy implementation period. Using the new model developed in this study, strategies for reducing CO2 emissions from cement production have been identified, and future challenges facing wider AAM implementation have been outlined. The novelty of the model consists in its ability to consider the CO2 emission problem as a system of systems, treating it in a holistic manner, and allowing the user to test diverse policy scenarios, with inherent flexibility and modular architecture. The practical relevance of the model is that it facilitates the decision-making process and policy making regarding the use of AAMs to mitigate CO2 emissions from cement production at low computational cost.

Mixture Optimization of Recycled Aggregate Concrete Using Hybrid Machine Learning Model.

Recycled aggregate concrete (RAC) contributes to mitigating the depletion of natural aggregates, alleviating the carbon footprint of concrete construction, and averting the landfilling of colossal amounts of construction and demolition waste. However, complexities in the mixture optimization of RAC due to the variability of recycled aggregates and lack of accuracy in estimating its compressive strength require novel and sophisticated techniques. This paper aims at developing state-of-the-art machine learning models to predict the RAC compressive strength and optimize its mixture design. Results show that the developed models including Gaussian processes, deep learning, and gradient boosting regression achieved robust predictive performance, with the gradient boosting regression trees yielding highest prediction accuracy. Furthermore, a particle swarm optimization coupled with gradient boosting regression trees model was developed to optimize the mixture design of RAC for various compressive strength classes. The hybrid model achieved cost-saving RAC mixture designs with lower environmental footprint for different target compressive strength classes. The model could be further harvested to achieve sustainable concrete with optimal recycled aggregate content, least cost, and least environmental footprint.

Predicting Ultra-High-Performance Concrete Compressive Strength Using Tabular Generative Adversarial Networks.

There have been abundant experimental studies exploring ultra-high-performance concrete (UHPC) in recent years. However, the relationships between the engineering properties of UHPC and its mixture composition are highly nonlinear and difficult to delineate using traditional statistical methods. There is a need for robust and advanced methods that can streamline the diverse pertinent experimental data available to create predictive tools with superior accuracy and provide insight into its nonlinear materials science aspects. Machine learning is a powerful tool that can unravel underlying patterns in complex data. Accordingly, this study endeavors to employ state-of-the-art machine learning techniques to predict the compressive strength of UHPC using a comprehensive experimental database retrieved from the open literature consisting of 810 test observations and 15 input features. A novel approach based on tabular generative adversarial networks was used to generate 6513 plausible synthetic data for training robust machine learning models, including random forest, extra trees, and gradient boosting regression. While the models were trained using the synthetic data, their ability to generalize their predictions was tested on the 810 experimental data thus far unknown and never presented to the models. The results indicate that the developed models achieved outstanding predictive performance. Parametric studies using the models were able to provide insight into the strength development mechanisms of UHPC and the significance of the various influential parameters.

Modeling Self-Healing of Concrete Using Hybrid Genetic Algorithm-Artificial Neural Network.

This paper presents an approach to predicting the intrinsic self-healing in concrete using a hybrid genetic algorithm-artificial neural network (GA-ANN). A genetic algorithm was implemented in the network as a stochastic optimizing tool for the initial optimal weights and biases. This approach can assist the network in achieving a global optimum and avoid the possibility of the network getting trapped at local optima. The proposed model was trained and validated using an especially built database using various experimental studies retrieved from the open literature. The model inputs include the cement content, water-to-cement ratio (w/c), type and dosage of supplementary cementitious materials, bio-healing materials, and both expansive and crystalline additives. Self-healing indicated by means of crack width is the model output. The results showed that the proposed GA-ANN model is capable of capturing the complex effects of various self-healing agents (e.g., biochemical material, silica-based additive, expansive and crystalline components) on the self-healing performance in cement-based materials.