Related references
Note: Only part of the references are listed.
Article
Green & Sustainable Science & Technology
Qingfu Li et al.
Summary: By replacing cement with rice husk ash (RHA) in concrete production, this study aimed to reduce the amount of cement used and its environmental impact. A stacking ensemble learning model was developed to accurately determine the compressive strength of RHA concrete. The model successfully fused the prediction outputs of base learners and increased the predictive accuracy. The performance evaluation indices of the model were RMSE = 2.344, MAE = 1.764, and R2 = 0.987. Cement and age were identified as the two most important parameters impacting the compressive strength of RHA concrete.
JOURNAL OF CLEANER PRODUCTION
(2023)
Review
Engineering, Environmental
Kai Ouyang et al.
Summary: This study compares the effects of different pretreatment methods on recycled aggregate concrete (RAC) and finds that pretreatment methods play a significant role in improving the mechanical properties, durability, and reducing drying shrinkage of RAC.
RESOURCES CONSERVATION AND RECYCLING
(2023)
Article
Engineering, Environmental
Junyu Tao et al.
Summary: This study proposes a method using hyperspectral imaging and machine learning models to rapidly determine the components and properties of municipal solid waste. The results demonstrate high accuracy in the identification and prediction of inorganic and organic components in MSW, respectively.
RESOURCES CONSERVATION AND RECYCLING
(2023)
Article
Engineering, Environmental
Soroush Mahjoubi et al.
Summary: This paper presents an AI-guided approach to automatically discover low-carbon cost-effective ultra-high performance concrete (UHPC). The approach integrates advanced techniques of generative modeling, automated machine learning, and many-objective optimization to automate data augmentation, machine learning model generation, and mixture selection. The proposed approach synthesizes new data for training machine learning models using generative modeling and semi-supervised learning, and predicts the properties of UHPC such as compressive strength, flexural strength, mini-slump spread, and porosity. The approach was applied in two design scenarios, resulting in significant reductions in life-cycle carbon footprint, embodied energy, and material cost compared to traditional UHPC mixtures.
RESOURCES CONSERVATION AND RECYCLING
(2023)
Article
Engineering, Civil
Xin-Yu Zhao et al.
Summary: This paper presents an alternative approach to evaluating the performance of recycled aggregate concrete columns using FRP jacketing. The XGBoost method and beetle antennae search metaheuristic algorithm are used to optimize the model, and a synthetic data generator is introduced to supplement the training data. The developed model outperforms existing models and improves the understanding of the axial stress-strain behavior of FRP-confined concrete.
THIN-WALLED STRUCTURES
(2023)
Article
Construction & Building Technology
Ligang Peng et al.
Summary: By using waste glass powder (GP), the corrosion resistance of recycled aggregate concrete (RAC) was enhanced due to the alkali-rich and pozzolanic characteristics of GP. The results showed that partially replacing cement with GP improved the steel corrosion resistance of RAC, surpassing that of conventional concrete prepared with natural aggregates. Additionally, the presence of 20% GP significantly enhanced the chloride penetration resistance without sacrificing compressive strength. The use of GP in low-carbon cement can compensate for the inferior durability of RAC, making it a promising option in the construction sector.
CEMENT & CONCRETE COMPOSITES
(2023)
Article
Construction & Building Technology
Kelli A. Knight et al.
Summary: In order to reduce the environmental impact of concrete production, supplementary cementitious materials (SCMs) can be used to replace some cement and reduce greenhouse gas emissions. However, overuse of SCMs can have negative effects on material performance and other environmental impacts. This study provides quantitative methods to determine the optimal SCM to OPC ratio for different SCMs, with the goal of minimizing environmental impacts while maintaining compressive strength.
CEMENT & CONCRETE COMPOSITES
(2023)
Review
Construction & Building Technology
Tong Zhang et al.
Summary: CO2 mineralisation by recycled concrete is an innovative method to improve the sustainability of concrete products. This review provides a comprehensive overview of the carbonation mechanisms, microstructure, and mechanical properties of concrete containing carbonated recycled concrete fines and aggregates. It highlights the chemistry-microstructure-property relationships and emphasizes the benefits of using carbonated recycled aggregates in enhancing the mechanical properties of concrete. Future research opportunities for developing low-carbon concrete with recycled concrete as a carbon sink are also discussed.
CEMENT & CONCRETE COMPOSITES
(2023)
Article
Construction & Building Technology
Yihan Ma et al.
Summary: In this paper, the polycarboxylate ether superplasticizer with cross-linked structure (TPCE) was synthesized and characterized. The adsorption isotherms and kinetics of TPCE on cement and montmorillonite (MMT) were measured, and the effects of TPCE on cement dispersion and hydration were examined. Results showed that TPCE exhibited stronger adsorption, dispersion, and dispersion-retention capabilities on cement containing MMT compared to conventional PCE (CPCE). It was also found that TPCE and CPCE exhibited different intercalation modes on MMT.
CEMENT AND CONCRETE RESEARCH
(2023)
Article
Construction & Building Technology
Bingcheng Chen et al.
Summary: This study investigates the effects of the combined utilization of mussel shell aggregate (MSA) and recycled concrete aggregate (RCA) on the mechanical, durability, and microstructural properties of mussel shell-recycled aggregate concrete (MS-RAC). The results show that increasing the MSA replacement rate has a more negative impact on the compressive and splitting tensile strength of MS-RAC compared to increasing the RCA replacement rate. The combined utilization of MSA and RCA leads to lower steel corrosion resistance during chloride attacks, which can be attributed to the higher debonding rate of the MSA-mortar interface and more complicated interfacial transition zones (ITZs) due to the incorporation of MSA and RCA. Furthermore, the incorporation of MSA results in more macropores and increased porosity in MS-RAC, significantly weakening its mechanical and durability properties.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Construction & Building Technology
Hai-Van Thi Mai et al.
Summary: This study proposes an effective approach to determine the compressive strength of recycled brick aggregate concrete using ensemble machine learning models. The findings can assist material engineers in designing the composition of recycled brick aggregate concrete.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Construction & Building Technology
Hongyu Chen et al.
Summary: By optimizing the mix proportion, the durability of concrete in severely cold regions can be improved. The research shows that after optimization, the chloride ion permeability coefficient of concrete is reduced by 47.9%, the relative dynamic elastic modulus is increased by 4.07%, and the cost is reduced by 2.4%.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Construction & Building Technology
Samer Al Martini et al.
Summary: This study investigates the mechanical properties of concrete mixes containing recycled concrete aggregate (RCA) from demolished buildings in Abu Dhabi, aiming to promote sustainable construction practices. The results showed that concrete with 20% RCA can be utilized in structural applications, as its strength exceeded 45 MPa. Accurate machine learning-based models were developed for predicting the compressive and flexural strengths of eco-friendly concrete containing RCA. The findings encourage wider adoption of RCA in structural applications, contributing to more sustainable concrete practices in the construction industry.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Review
Construction & Building Technology
Jingli Wei et al.
Summary: Reasonable use of coral as concrete aggregate can solve raw material shortage in island engineering construction and reduce costs and energy consumption caused by marine transportation. However, the low compressive strength and high porosity of coral aggregates limit their application in island engineering construction.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Construction & Building Technology
Qinghe Wang et al.
Summary: This study investigated the long-term performance of steel-spontaneous combustion coal gangue aggregate concrete (S-SCGAC) composite slabs. The effects of the replacement ratio (rc) of spontaneous-combustion coal gangue aggregate (SCGA) and humidity boundary conditions on the shrinkage of SCGAC specimens were quantified through shrinkage tests. A non-uniform shrinkage model for S-SCGAC composite slabs was proposed and a long-term performance design method was put forward. The results showed that the shrinkage deformation of SCGAC specimens increased significantly with increasing rc, and humidity boundary conditions had a significant effect on the shrinkage performance.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Automation & Control Systems
Bin Chen et al.
Summary: A hybrid intelligent framework based on random forest (RF) and non-dominated sorting genetic algorithm version II (NSGA-II) is developed to predict the durability and optimize the mix ratio of high-durability concrete. The proposed RF-NSGA-II framework effectively predicts concrete durability and achieves a high standard of frost resistance and chloride ion permeability coefficient at a low cost. The developed RF model has excellent regression learning ability, with high goodness of fit and low error values. This framework can provide guidance for optimizing concrete mix design and similar projects.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Engineering, Civil
Jin-Xin Chen et al.
Summary: Machine learning in civil engineering still faces challenges such as small and incomplete training datasets, questionable generalization ability, and lack of physical interpretability. To address these issues, we propose a general integrated ML pipeline that utilizes transfer learning and synthetic data augmentation to handle limited data and enable transparent and interpretable analysis.
ENGINEERING STRUCTURES
(2023)
Article
Engineering, Civil
Alireza Entezami et al.
Summary: Long-term monitoring is crucial for health monitoring of civil structures as it covers all possible unpredictable variations in vibration data and provides adequate training samples for unsupervised learning. However, it may encounter large data with missing values and erroneous results due to environmental changes. To address these challenges, this article proposes a novel unsupervised meta-learning method involving four steps of data analysis, segmentation, subspace searching, and anomaly detection.
ENGINEERING STRUCTURES
(2023)
Article
Green & Sustainable Science & Technology
Elyas Asadi Shamsabadi et al.
Summary: A multicollinearity-aware multi-objective optimisation (MA-MOO) framework was developed to minimize environmental issues and production cost of green concrete, while maintaining compressive strength. This was achieved using machine learning and a novel set of constraints to eliminate multicollinearity. Testing the framework with a dataset of 2644 concrete mixes, the extreme gradient boosting machine (XGBM) achieved the best performance (RMSE 4.3 MPa). The framework allowed for the design of mixes with significantly reduced production cost and environmental impact.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Green & Sustainable Science & Technology
Emadaldin Mohammadi Golafshani et al.
Summary: The use of supplementary cementitious materials in concrete can reduce the negative environmental impacts, however, the durability and resistance of recycled aggregate concrete (RAC) must be studied. The combination of machine learning techniques and RCMT can save time, cost, materials, and the need for skilled technicians.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Construction & Building Technology
Zemei Wu et al.
Summary: This study investigates the influence of deicing salt type, concentration, and exposed environment on the moisture susceptibility of an asphalt mixture. Various tests were conducted to evaluate the effects, and statistical analysis and microstructure analysis were performed to establish relationships and understand the underlying mechanisms.
JOURNAL OF MATERIALS IN CIVIL ENGINEERING
(2023)
Article
Construction & Building Technology
Xian Rong et al.
Summary: The study investigates a predictive model for recycled aggregate concrete (RAC) creep and compares its accuracy with existing models using back-propagation neural network (BPNN) and support vector machine (SVM). A creep database of RAC with 106 groups of 1309 experimental data points is established, considering 15 influencing parameters. The results show that the BPNN and SVM models are more accurate in predicting RAC creep compared to existing models. Furthermore, the effects of recycled coarse aggregate (RCA) replacement ratio, RCA residual mortar content, and RAC strength on the creep properties of RAC are clarified using the extended parameters analyzed by the BPNN model.
STRUCTURAL CONCRETE
(2023)
Review
Engineering, Environmental
Hannah Szu-Han Wang et al.
Summary: This paper reviews 53 papers published since 2008 to understand the capabilities, limitations, and potentials of machine learning (ML) in supporting sustainable development and applications of biomass-derived materials (BDM). Previous ML applications in BDM systems focus on material and process design, end-use performance prediction, and sustainability assessment. However, there are limitations in the interpretability of models and the lack of studies considering geo-temporal dynamics in sustainability assessment.
RESOURCES CONSERVATION AND RECYCLING
(2023)
Article
Engineering, Environmental
Chuangchuang Zhou et al.
Summary: Recent developments in robotic demanufacturing have the potential to enhance the efficiency of recycling and resource recovery from WEEE. To achieve industrial adoption, a generic retrieval system called YODO was developed, using content-based image retrieval (CBIR) to identify product models and retrieve model-specific demanufacturing instructions. The system compares visual features of WEEE images with a database to find matches and demonstrates high performance in a laptop model identification case study. YODO showed a top-1 retrieval mean average precision (mAP) of 93.75%, learned 1079 unique product models, and achieved an 85% chance of the next laptop being registered in the database.
RESOURCES CONSERVATION AND RECYCLING
(2023)
Article
Engineering, Environmental
Weiqi Xing et al.
Summary: Massive emissions and energy consumption in concrete production pose threats to sustainable development and human health. Studies on sustainable concrete mainly focus on technical properties, while limited research has integrated life cycle assessment (LCA) to measure environmental impacts. This research examines 570 concrete mix designs incorporating recycled aggregate (RA) and supplementary cementitious materials (SCMs) to analyze their environmental behavior and develop a model to predict carbon emissions and energy consumption. The results show that the environmental impact of sustainable concrete is related to compressive strength, water-to-binder ratio, and RA/SCMs ratios, and the allocation coefficient and alternative fuel utilization significantly affect the impact.
RESOURCES CONSERVATION AND RECYCLING
(2023)
Article
Engineering, Environmental
Soroush Mahjoubi et al.
Summary: This study presents an approach to discover the intrinsic relationships between the physicochemical properties of concrete ingredients and its mechanical properties. The proposed approach has been implemented to predict the compressive strength of complex concrete mixtures, assess the importance of variables, and discover chemical reactions, showing high accuracy and high generalizability. This research advances the understanding of complex concrete mixtures and the design of low-carbon cost-effective concrete.
RESOURCES CONSERVATION AND RECYCLING
(2023)
Article
Engineering, Environmental
Yiming Peng et al.
Summary: By building a comprehensive database with 607 records, the complex functional relationship between key parameters of recycled aggregate concrete (RAC), such as recycled aggregate properties, mix proportion, and compressive strength, was explored. Two standard algorithms (artificial neural network and support vector regression) and two optimized hybrid models (Particle Swarm Optimization based support vector regression and grey Wolf optimizer based support vector regression) were used. Additionally, two interpretable algorithms (Partial Dependence Plot and SHapley Additive exPlanations) were applied to assess the global and local approaches independent of machine learning models. Results showed that the hybrid models outperformed the conventional models, with the coefficient of determination (R2) of the optimized hybrid models reaching above 0.89.
RESOURCES CONSERVATION AND RECYCLING
(2023)
Article
Energy & Fuels
Zongxiang Li et al.
Summary: In this paper, a multi-fault online diagnosis approach combining a non-redundant measurement topology and weighted Pearson correlation coefficient (WPCC) is proposed to detect various circuit faults. The approach uses weighted measured data with different forgetting factors and can accurately distinguish and locate battery abuse faults, connection faults, sensor faults, adjacent homogeneous faults, and adjacent hybrid faults.
JOURNAL OF ENERGY STORAGE
(2023)
Article
Engineering, Civil
Songsong Lian et al.
Summary: The diffusion behavior of chloride in recycled concrete was found to be different from that in normal concrete due to the high porosity of recycled aggregates. The maximum chloride concentration in the drying-wetting environment increased rapidly, but the decrease in the chloride diffusion coefficient was slower. The relationship between several parameters related to chloride diffusion was established, and a more sophisticated model considering key indexes was proposed.
Article
Construction & Building Technology
Jin Xia et al.
Summary: This study determined the microstructural characteristics of concrete-to-concrete interfaces with various preparation methods. The results showed the formation of microcracks and CaCO3 precipitations in the interface, resulting in higher porosity compared to the matrix and interface transition zone. This higher tortuosity of water transport channel and increased solution absorption rate led to deeper diffusion of chloride ions and ingress into the concrete on both sides, causing a diffusion peak formation.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Construction & Building Technology
Mo Zhang et al.
Summary: The random forest model optimized by genetic algorithm achieved the highest prediction accuracy for uniaxial compressive strength (UCS) and final setting time (FST) of alkali-activated materials (AAMs). The curing time and water content significantly influenced the UCS, while Na/Al and water contents were more important to FST. The microstructure development of AAMs was affected by Ca/Si, Na/Al, and Si/Al ratios.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Construction & Building Technology
Chong Chen et al.
Summary: In this study, the synergistic effects of fly ash (FA) and ground-granulated blast slag (GGBS) on the compressive behavior and durability of recycled aggregate concrete (RAC) were comprehensively investigated. The results showed that partially replacing cement with 15% FA and 15% GGBS can enhance the 90-day compressive strength, chloride penetration resistance, and frost resistance of RAC.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Multidisciplinary Sciences
Lingjie Wu et al.
Summary: This research focuses on predicting and analyzing chloride profiles in concrete using deep learning methods. The study finds that Bi-LSTM and CNN models converge rapidly during training but lack accuracy in predicting chloride profiles. The GRU model is more efficient than the LSTM model but falls short in prediction accuracy. By optimizing the LSTM model, significant improvements are achieved, and desirable chloride profiles of concrete specimens at 720 days are successfully predicted.
Article
Construction & Building Technology
Fuyuan Gong et al.
Summary: This paper investigates the impact of thermo-drying (TD) on the freeze-thaw cycles (FTC) processing of recycled coarse aggregate (RCA). Experimental data and a theoretical model reveal that TD has a positive impact on FTC processing. However, an integrated analysis is needed to balance processing efficiency and energy consumption.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Construction & Building Technology
Mohammad Iqbal Khan et al.
Summary: The use of supplementary cementitious materials in ultra-high-performance concrete has grown in recent years, with a focus on recycled glass powder. This research applied machine learning techniques to develop and validate a predictive model for the compressive strength of UHPC containing recycled GP. The model showed high accuracy and identified important features such as silica fume, water-binder ratio, water-powder ratio, and virtual packing density.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Construction & Building Technology
Mei-Yu Xuan et al.
Summary: This study reveals the positive effects of adding dry ice on the properties of ultra-high-performance concrete. Adding dry ice generates microscopic CO2 bubbles that enhance later-stage strength and electrical resistivity. It also reduces heat of hydration and promotes ettringite formation. Moreover, the addition of dry ice decreases CO2 emissions and is crucial for achieving carbon neutrality in the concrete industry.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Construction & Building Technology
Xueqing Zhang et al.
Summary: Previous studies mainly used laboratory data to explore machine learning (ML) models for predicting the 28-day compressive strength (f28) of concrete, while this study utilizes industrial data. Predicting industrial concrete performance using laboratory models may be questionable due to the increased uncertainties in an industrial environment. This study applies ML models to analyze 12,107 observations of industrially produced concrete, covering various concrete applications with different strength and slump requirements. By employing a systematic approach, including data visualization, model selection and assessment, model finalization, and variable importance analysis, seven ML models are developed to predict f28. Significant improvements are achieved compared to previous studies using field concrete data. It is also observed that industrial data poses a multimodal problem and is noisier than laboratory data. The findings of this study can serve as a valuable reference for predicting f28 and designing concrete mixes in an industrial environment.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Construction & Building Technology
Yunze Liu et al.
Summary: This paper used machine learning models to predict creep and analyze characteristic factors for concrete with supplementary cementitious materials (SCM). A creep database was developed with thirteen input parameters and one output parameter, and different models were used to establish creep compliance models. The study also conducted sensitivity analysis on each input parameter to investigate their influence on creep prediction. The results showed that the extreme gradient boosting (XGB) model performed well in predicting creep compliance for SCM concrete. The stress-to-strength ratio was identified as the most important factor affecting creep prediction.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Construction & Building Technology
Wujian Long et al.
Summary: The purpose of this study is to establish highly nonlinear relationships between SCC mix proportions and properties using machine learning techniques and providing interpretable models to guide SCC design. The proposed models exhibit high accuracy in predicting the key properties of SCC through careful feature engineering, model training, and hyper-parameter optimization. Experimental verification shows that the proposed models can accurately predict the properties of C45, C50, and C55 SCC.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Construction & Building Technology
Kunting Miao et al.
Summary: This study introduces a machine learning-based model for predicting the ultimate strength of circular concrete-filled fiber-reinforced polymer (FRP)-steel composite tube (CFSCT) columns. The ML-based models were evaluated and proved to have superior prediction accuracy and applicability compared to existing empirical models. The SVR model demonstrated the best performance with an R2 of 0.992, followed by the BPNN and RF models with R2 of 0.984 and 0.982, respectively. Concrete compressive strength, steel tube thickness, and FRP thickness were identified as influential factors on the ultimate strength of CFSCT columns.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Construction & Building Technology
Thushara Jayasinghe et al.
Summary: Recycled aggregate concrete (RAC) has gained attention for sustainable development, but its use in structural elements is limited due to the lack of design guidelines. This study proposes a data-driven framework using machine learning to predict the shear capacity of RAC beams. Analysis of 401 RAC beam samples and the implementation of eight machine learning algorithms identified XGBoost as the best ML-based framework with high prediction accuracy.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Engineering, Multidisciplinary
Chao Xiang et al.
Summary: In this study, a novel semi-supervised deep learning framework, called SemiCrack, is proposed for crack segmentation. The framework combines contrastive learning and cross pseudo supervision (CPS) and utilizes pixel contrastive loss to improve segmentation accuracy. Experimental results demonstrate that SemiCrack outperforms many existing fully-supervised and semi-supervised segmentation algorithms on various publicly available datasets. The segmentation accuracy of TC-Net is higher than that of most fully-supervised segmentation networks, with an improvement of about 2% in Intersection of Union (IoU). Besides, SemiCrack achieves comparable accuracy to other fully-supervised algorithms with only 20% labeled data.
Review
Computer Science, Interdisciplinary Applications
Jie Li et al.
Summary: This study developed an ANFIS-GA-PSO hybrid model to predict the shear strength of concrete beams. Predicting the shear strength before construction is crucial for assessing the structure's ability to withstand external forces. The hybrid model showed higher accuracy in assessing shear behavior compared to the ELM model, and the ELM model exhibited fast training performance. The results identified key factors determining shear strength in reinforced concrete beams.
ADVANCES IN ENGINEERING SOFTWARE
(2023)
Article
Engineering, Environmental
Ben Moins et al.
Summary: Lean asphalt is a hot mixture with lower binder content, allowing for high RAP content and increased pavement structural capacity. However, concerns arise regarding its performance due to low binder content and high air void content. The study suggests that 40% RAP content is necessary to meet moisture susceptibility requirements. Fatigue testing shows satisfactory resistance, but semicircular bending and IDEAL-CT testing reveal low cracking tolerance. Life cycle assessment shows that lean asphalt with 40% RAP has lower environmental impact, and life cycle cost analysis confirms its lower economic impact compared to other base materials.
RESOURCES CONSERVATION AND RECYCLING
(2023)
Article
Construction & Building Technology
Lifu Yang et al.
Summary: This paper introduces a hybrid machine learning method for predicting concrete expansion caused by alkali-silica reaction (ASR) and presents a comprehensive and reliable experimental database with around 1900 sets of ASR expansion data. The method uses a beta differential evolution-improve particle swarm optimization algorithm (BDE-IPSO) to tune weights and biases of an artificial neural network model. The model considers 11 variables as input and accurately predicts ASR expansion. The results demonstrate that the prediction model captures various aspects of ASR expansion, including reactivity, aggregate content, water-to-cement ratio, temperature, humidity, specimen geometry, and time-dependent behavior.
CEMENT & CONCRETE COMPOSITES
(2023)
Article
Construction & Building Technology
Celal Cakiroglu et al.
Summary: Colossal amounts of construction and demolition waste (C & D) and waste tires have become a considerable global environmental concern. To alleviate this issue, it is proposed to use crumb rubber (CR) derived from waste tires and recycled coarse aggregate (RCA) from C & D as a replacement for natural aggregates in new construction materials. However, the wide variability in the mechanical properties of recycled concrete and the lack of reliable predictive tools in the literature make the wide-scale adoption of these new materials a challenging task.
JOURNAL OF BUILDING ENGINEERING
(2023)
Article
Construction & Building Technology
I. G. Endzhievskaya et al.
Summary: The study investigates the relationship between various parameters of concrete production process and its properties, such as strength, density, and bending strength, using 48 experimental data points. The results show significant correlations among the compressive strength at different ages, suggesting that predicting only one characteristic is sufficient. Linear regression analysis is not accurate due to the lack of multiple correlations, hence Machine Learning, specifically the Random Forest method, is recommended. The study identifies key parameters for achieving high compressive and bending strengths, including air-entraining additives and specific types of crushed stone fractions.
JOURNAL OF BUILDING ENGINEERING
(2023)
Article
Engineering, Civil
Congcong Fan et al.
Summary: A prediction model based on Sparrow Search Algorithm (SSA) Optimized Extreme Learning Machine (SSA-ELM) is proposed to evaluate the failure forms of reinforced concrete (RC) structures. The model utilizes a database of pull-out test samples and various characteristic parameters to screen out the significant features influencing the failure pattern and develops a classification prediction model using standard machine learning algorithms.
Article
Engineering, Civil
Ji-gang Zhang et al.
Summary: In this study, a fusion model (stacking-CRRL) combining Catboost, RFR, RR, and LASSO was proposed and demonstrated to accurately predict the load capacity of SRCCs clad in CFRP in axial compression. Sparse initial data were extended using synthetic minority oversampling, and redundant features were eliminated using Spearman correlation coefficients. The prediction performance of various algorithmic models was compared, and the stacking-CRRL fusion model outperformed other models, a published prediction equation, and an Abaqus simulation after SMOTE processing.
Article
Computer Science, Artificial Intelligence
Nick Harder et al.
Summary: This study presents a novel approach to simulate electricity markets using multi-agent deep reinforcement learning. The method is highly adaptive and scalable, able to diagnose market manipulation and reflect market liquidity. It contributes to the analysis of market design and supports the establishment of future-proof electricity markets for energy transition.
Article
Environmental Sciences
Yi Han et al.
Summary: Ultra-high-performance concrete (UHPC) with indirect CO2 addition showed improved performance in terms of early strength, ultrasonic velocity, and resistivity compared to the control group. The method of adding solid calcium carbonate (CaCO3) converted from gaseous CO2 did not negatively affect the microstructure of UHPC. Microscopic experiments demonstrated that the hydration rate of the UHPC paste was accelerated by the addition of captured CO2.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Computer Science, Interdisciplinary Applications
Junfei Zhang et al.
Summary: This study proposes a machine learning approach for shear design of RC beams. A random forest model is constructed and the hyperparameters are tuned using an improved search algorithm and inertia weight. The developed model accurately predicts the shear strength of RC beams with and without stirrups. This method shows powerful and efficient capabilities in shear design, leading to intelligent construction.
ENGINEERING WITH COMPUTERS
(2022)
Article
Construction & Building Technology
Hongyu Chen et al.
Summary: This paper presents an efficient optimization method for concrete mixture based on a hybrid intelligent algorithm, which generates a series of optimized solutions through multi-objective optimization. The verification in an engineering case demonstrates that this method can improve the performance and reduce the cost of concrete.
CEMENT & CONCRETE COMPOSITES
(2022)
Article
Construction & Building Technology
Keyu Chen et al.
Summary: Optimizing critical factors for geopolymer production is important for engineering applications, and a three-level Box-Behnken design was used in this study to optimize the geopolymer paste. The optimized paste was later used as a sustainable stabilizer for improving the mechanical performance of soft soil in Hangzhou, China. The study evaluated the effects of stabilizer content, curing age, and moisture content on the compressive strength of the stabilized soil, and introduced a quasiwater-cement ratio to predict the strength development. The results showed that the geopolymer gel structure improved the soil microstructure, leading to a more compact and strong final stabilized soil.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
Yiming Peng et al.
Summary: This study demonstrated the feasibility of predicting the 28-day strength of geopolymer concrete through mix proportions and pre-curing conditions using three machine learning algorithms. Results showed good prediction performance for the overall database, with BPNN having the largest number of instances within +/- 20% error. SiO2 content in FA was found to have the highest influence on strength among the variables investigated.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
Kaihua Liu et al.
Summary: This study predicts the sulfate resistance of recycled aggregate concrete through machine learning approaches, with extreme gradient boosting model demonstrating the best performance among the four methods utilized. The sulfate resistance of RAC is influenced by environmental conditions, and the partial dependence analysis of critical parameters confirms the robustness of the model.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Green & Sustainable Science & Technology
Taehoon Kim et al.
Summary: This study proposes a PC production scheduling model based on a reinforcement learning approach, which has the advantages of a general capacity, fast computation time, and good performance in real-time. The experimental study shows that the proposed model outperformed other methods in total tardiness.
JOURNAL OF CLEANER PRODUCTION
(2022)
Article
Computer Science, Interdisciplinary Applications
Jiandong Huang et al.
Summary: This research introduces a new model based on artificial intelligence for optimizing compressive strength in concrete samples. By using a human learning optimization algorithm and support vector regression models, the study successfully identified the polynomial model as the most accurate for predicting and optimizing concrete strength under different conditions.
ENGINEERING WITH COMPUTERS
(2022)
Article
Engineering, Chemical
Yanfeng Nie et al.
Summary: This study investigates the use of metakaolin as a modifier for high-volume fly ash (HVFA) concrete. It is found that incorporating an appropriate amount of metakaolin improves the mechanical properties and microstructure of HVFA concrete, reducing drying shrinkage and porosity. Furthermore, the inclusion of metakaolin helps reduce the carbon footprint and cost of HVFA concrete.
Article
Construction & Building Technology
Qian Zhang et al.
Summary: The study proposed two new algorithms, the gray wolf multi-layer perceptron neural networks (GWMLP) and gray wolf support vector regression (GWSVR), to predict the elastic modulus of RAG concrete. Results showed that GWSVR performed better in the testing phase compared to GWMLP models.
STRUCTURAL CONCRETE
(2022)
Article
Construction & Building Technology
Kaiyun Wu et al.
Summary: The carbonation treatment improved the properties of weak multiple interface transition zones (ITZs) in recycled aggregate concrete (RAC), enhancing the performance of the concrete. Different carbonation conditions had consistent effects on the microproperties and macroproperties of RAC, with compressive strength and chloride ion penetration resistance showing a linear correlation with the modulus of the ITZ.
CEMENT & CONCRETE COMPOSITES
(2022)
Article
Construction & Building Technology
Yanqi Wu et al.
Summary: A hybrid machine learning model called GS-SVR, combining the SVR model and grid search optimization algorithm, was proposed to predict the compressive strength of sustainable concrete. The results showed that the GS-SVR model outperformed the original SVR model and can be recommended as a reliable and accurate compressive strength prediction tool. Additionally, the SHAP method was used to explain the importance and contribution of the input variables that influence the compressive strength.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
Qinghe Wang et al.
Summary: This study investigated the effects of silica fume type and content on the abrasion resistance and mechanical properties of low-heat Portland cement concrete. The results showed that adding silica fume significantly improved the abrasion resistance of the concrete. The silica fume content had a significant impact on the abrasion resistance, and the type of silica fume also had some influence. Additionally, the addition of silica fume enhanced the strength and elastic modulus of the concrete.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
Huan Zhang et al.
Summary: This paper investigates the influence of coarse recycled aggregate on the non-uniform shrinkage of concrete. The study found that the use of recycled aggregate significantly increased the shrinkage gradient, and its influence on shrinkage distribution increased with a decrease in surface depth. The developed prediction model accurately predicts the non-uniform shrinkage of exposed recycled aggregate concrete.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
Kai-Hua Liu et al.
Summary: This study investigates the feasibility of using machine learning algorithms to predict the resistance of recycled aggregate concrete (RAC) to chloride penetration. Multiple models were integrated and optimized to improve prediction performance, with water content identified as the most critical factor affecting chloride ion permeability. Through partial dependence analysis, the interpretability of the model was enhanced. Based on the machine learning models, a performance-based mixture design method and a service life prediction approach for RAC were developed.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
Wei Dong et al.
Summary: This study proposes a comprehensive data-driven method for the multi-objective design optimization of GN-reinforced cementitious composites (GNRCC) using machine learning techniques and a non-dominated sorting genetic algorithm. It establishes prediction models for the properties of GNRCC and quantifies the influence of critical features. The proposed method successfully achieves a set of Pareto solutions for the optimization of GNRCC properties.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
Xianguo Wu et al.
Summary: An intelligent framework based on the random forest algorithm is proposed to predict the frost resistance of concrete in extremely cold areas. The framework effectively eliminates coupling factors and noise, determines the optimal factor index system for concrete mix proportions, and establishes a regression prediction function between mix proportions and frost resistance. The feasibility of the proposed method is verified through a case study.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
Seyed Arman Taghizadeh Motlagh et al.
Summary: The paper presents a combined multi-model framework using regression methods based on artificial neural network, random forest regression, and polynomial regression for more accurate concrete compressive strength prediction. The results of the individual regression models are combined using a linear weighting strategy and optimized through quadratic convex optimization.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Review
Construction & Building Technology
Deepak Prasad et al.
Summary: This paper discusses the utilization of recycled concrete aggregates (RCA) in bituminous mixes, including different stages and treatment methods. The paper also explores the characteristics of RCA and their impact on the performance of bituminous mixes, as well as approaches for enhancing the physical properties of RCA and the performance of bituminous mixes incorporating RCA.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
Van Quan Tran
Summary: This study uses machine learning algorithms to predict the chloride diffusion coefficient of concrete containing SCMs. The performance of eight machine learning models is evaluated, and the Gradient Boosting model is found to have the highest accuracy. SHAP, ICE, and PDP 2D techniques are used to identify the most influential input variables and quantify their impact on chloride diffusion in concrete.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
Van Quan Tran et al.
Summary: This study focused on evaluating the compressive strength of concrete made from recycled concrete aggregate (RCA) using different single and hybrid machine learning models. The results showed that the hybrid models outperformed single models in terms of prediction accuracy. This research provides valuable insights for the systematic evaluation of compressive strength prediction of recycled concrete.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Green & Sustainable Science & Technology
Qiang Zeng et al.
Summary: This work presents a proof-of-concept study on the development of sustainable cement-free pervious concrete using recycled low-quality urban-fringe construction and demolition waste. The study explores the engineering performances and multi-scale structures of the concrete. The findings suggest that replacing cement with alkali-activated brick powder can bring substantial economic and environmental benefits.
JOURNAL OF CLEANER PRODUCTION
(2022)
Article
Green & Sustainable Science & Technology
Bawar Iftikhar et al.
Summary: This study aims to develop an empirical formula for the compressive strength of rice husk ash (RHA) concrete using machine learning algorithms. The gene expression programming (GEP) model outperforms the Random Forest Regression (RFR) ensemble model in terms of robustness. The use of agricultural waste as a substitute for cement in sustainable concrete production shows promise in mitigating greenhouse gas emissions.
JOURNAL OF CLEANER PRODUCTION
(2022)
Article
Engineering, Multidisciplinary
Yinghao Zhao et al.
Summary: This study uses artificial neural network models to estimate the compressive strength of manufactured sand concrete. Two improved ANN models are developed using conventional algorithms and metaheuristic algorithms, respectively, and it is found that the improved models have higher accuracy. Additionally, the analysis reveals the significant impact of curing age and water to binder ratio on the compressive behavior of concrete.
Article
Construction & Building Technology
Yi-Sheng Wang et al.
Summary: This study systematically investigated the effects of silicate-modified calcium oxide-based expansive agents (SCEAs) on the engineering performance and self-healing of ultra-high-strength concrete (UHSC). Experimental results showed that the addition of SCEA decreased the compressive strength, ultrasonic pulse velocity, and surface resistivity of UHSC, but increased the penetration of calcium ions. Moreover, UHSC doped with SCEA exhibited higher crack width healing and greater reduction in permeability.
JOURNAL OF BUILDING ENGINEERING
(2022)
Article
Engineering, Civil
Uma Shankar Biswal et al.
Summary: This study demonstrates that machine learning techniques can be used to predict the compressive strength of recycled aggregate concrete. By testing specimens from numerous mixes, a machine learning model with an accuracy of 0.95 was established. XG Boost is identified as the most suitable machine learning algorithm for this prediction.
INNOVATIVE INFRASTRUCTURE SOLUTIONS
(2022)
Article
Engineering, Multidisciplinary
Shuaicheng Guo et al.
Summary: This study experimentally investigated the influence of surface treatments on the elevated temperature resistance and durability performance of carbon textile-reinforced concrete (CTRC) and basalt textile-reinforced concrete (BTRC). The results showed that nano-silica treatment improved the high-temperature resistance and aging resistance of both CTRC and BTRC specimens in the simulated marine environment. The use of a silane coupling agent further enhanced the improvement effect.
COMPOSITES PART B-ENGINEERING
(2022)
Article
Construction & Building Technology
Anas Abdulalim Alabdullah et al.
Summary: This study investigates the non-linear capabilities of two machine learning prediction models, Light GBM and XGBoost, for predicting RCPT values. The study found that LightGBM surpasses XGBoost in prediction accuracy and that the W/B ratio and MK replacement are of significant importance in resisting chloride penetration.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
Selim Cemalgil et al.
Summary: This paper investigates the durability properties of concrete subjected to harsh climatic conditions, such as abrasion and freezing/thawing cycles. By modifying the concrete with silica fume and steel fiber, the authors predict the performance of the concrete using mix design and additional properties. Experimental tests were conducted and a prediction model using metaheuristic algorithms was proposed. The results show that the ternary prediction model provided accurate results and improved performance compared to other models.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Review
Construction & Building Technology
Hongwei Lin et al.
Summary: This paper presents a literature review on the mechanical properties of concrete subjected to low temperatures and cryogenic freeze-thaw cycles. It discusses the effects of low temperatures on concrete properties and summarizes existing mathematical models. The paper also explores the mechanism of concrete damage induced by cryogenic freeze-thaw cycles. The conclusions drawn from this review can facilitate and safeguard the application of concrete structures in very low temperature environments.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
Guowei Ma et al.
Summary: This study developed an ensemble machine learning modeling method to predict the strength of fly ash-based geopolymer, showing that the XGBoost model outperformed others and accurately predicted the strength. The impact of curing conditions, alkali-activator solution variables, and the mole of sodium hydroxide on the model output was analyzed using the SHapley Additive exPlanations theory.
JOURNAL OF MATERIALS IN CIVIL ENGINEERING
(2022)
Article
Chemistry, Physical
Jesus de-Prado-Gil et al.
Summary: This study compares the performance of four machine learning models in predicting the splitting tensile strength of self-compacting concrete made from recycled aggregates. XG Boost model shows the best performance in terms of R-2 value, RMSE, and MAE.
Review
Chemistry, Physical
Zhanzhao Li et al.
Summary: Concrete science has made progress, but concrete formulation remains challenging. Machine learning has transformative potential and has been widely used in concrete research. It is necessary to understand methodological limitations and formulate best practices to fully exploit the capabilities of machine learning models.
NPJ COMPUTATIONAL MATERIALS
(2022)
Article
Construction & Building Technology
Ligang Peng et al.
Summary: The accelerated carbonation treatment can improve the physical properties of recycled aggregate and enhance the performance of recycled aggregate concrete. However, the corrosion and cracking induced by carbonated recycled aggregate in concrete have not been adequately addressed in previous studies. This study experimentally investigated the effects of accelerated carbonation treatment on the physical properties of recycled aggregate and the performance of recycled aggregate concrete. The results show that carbonated recycled aggregate exhibits improved water absorption and slightly higher density. Carbonated recycled aggregate concrete demonstrates higher compressive strength, better resistance to steel corrosion, and reduced corrosion-induced cracking, which can be attributed to the enhanced micro-hardness of the interfacial transition zones between new and old mortar.
CEMENT & CONCRETE COMPOSITES
(2022)
Article
Construction & Building Technology
Babatunde Abiodun Salami et al.
Summary: This study proposed AI-based models to predict the compressive strength of foamed concrete and experimented with three different AI approaches. After training the models with experimental data, verification and analysis revealed that the GBT model had relatively better performance.
CEMENT & CONCRETE COMPOSITES
(2022)
Article
Construction & Building Technology
Shengying Zhao et al.
Summary: This paper presents a model to calculate the long-term compressive strength of SAP-modified concrete compared to concrete without SAP. The model takes into account the influence of paste strength and SAP void content. Results show that the addition of internal curing water can enhance the strength of concrete, but there exists a critical water-to-binder ratio above which the addition of water reduces strength. The model is validated by experimental results and is applicable to various types of concrete.
CEMENT & CONCRETE COMPOSITES
(2022)
Review
Construction & Building Technology
Hanxi Jia et al.
Summary: This review analyzes recent machine learning methods for corrosion assessment of reinforced concrete structures and discusses some challenges in corrosion evaluation. These methods have significant impact on the estimation of corrosion process, mechanical properties, and durability of structures, providing valuable insights for researchers and engineers in the field.
CEMENT & CONCRETE COMPOSITES
(2022)
Article
Construction & Building Technology
Rahul Biswas et al.
Summary: Carbonation is a serious issue affecting the durability of reinforced concrete. Traditional prediction models struggle to capture the complex interaction between parameters. This study develops a machine learning model that combines metaheuristic algorithms with Support Vector Regression to improve prediction accuracy. The model is validated using experimental data and successfully applied to study the carbonation depth in fly-ash concrete.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
Woubishet Zewdu Taffese et al.
Summary: This study utilizes the machine learning algorithm XGBoost to predict the chloride migration coefficient of concrete. The verification results confirm the high accuracy of the model, suggesting its potential to replace laboratory testing.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
Victor Revilla-Cuesta et al.
Summary: The hammer rebound index, traditionally used to estimate the compressive strength of vibrated concrete, can now be applied to predict the compressive strength of Self-Compacting Concrete (SCC) and concrete with Recycled Concrete Aggregate (RCA). This paper further develops the use of the hammer rebound test by demonstrating its ability to estimate the overall mechanical behavior of SCC containing RCA. By expressing the hammer rebound index as a combination of four mechanical properties, adjusted through multiple regression, it serves as a quality performance indicator and can predict various mechanical properties of SCC containing RCA.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
Jinjun Xu et al.
Summary: This paper presents a series of data-driven analysis on the compressive behavior of unconfined and confined recycled aggregate concretes (RACs). Reliable experimental databases were assembled, and models were developed to estimate the failure envelope and compressive properties of RACs. The proposed models exhibit acceptable predictions and provide a design-oriented procedure for material and structural assessments.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
Yang Liu et al.
Summary: A hybrid intelligent prediction model using random forest and least squares support vector machine algorithms is proposed in this study to quickly and accurately predict the resistance of high-performance concrete to chloride penetration. The model effectively screens important indicators and achieves high-precision predictions, demonstrating good prediction performance.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
Hisham Hafez et al.
Summary: Partially replacing ordinary Portland cement with low-carbon supplementary cementitious materials in blended cement concrete is a promising route for sustainable concrete production. However, the performance of blended cement concrete may be inferior to that of ordinary Portland cement. To reduce the cost and time of experimental testing, a machine learning regression model was created to predict the performance of blended cement concrete using prominent supplementary cementitious materials.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Green & Sustainable Science & Technology
Ke-yu Chen et al.
Summary: This paper provides a comprehensive overview of the importance of finding a clean technology option for the cement manufacturing industry in order to reduce greenhouse gas emissions. It discusses the potential of CO2 curing for large-scale carbon sequestration and improvement of cement-based composites, as well as the challenges and future research directions in this field.
JOURNAL OF CLEANER PRODUCTION
(2022)
Review
Green & Sustainable Science & Technology
Yi-Chen Lan et al.
Summary: There is a lack of research on the environmental impacts of cut flowers from growing facilities to end consumers, and no review has been conducted on this topic. Current studies on life cycle assessment (LCA) of cut flowers show inconsistencies in the choice of functional unit and a focus on carbon footprint and energy consumption. The various flower species and cultivation methods make it challenging to compare environmental performance. To enhance environmental sustainability, suggestions include improving greenhouse technology, implementing integrated nutrient and pest management, introducing certification and labeling for cut flowers, developing sea transport with refrigerated containers, and increasing consumer awareness of environmental impact. There is still room for improvement in LCA of cut flowers, particularly in terms of allocation, waste treatment, and uncertainty analysis.
JOURNAL OF CLEANER PRODUCTION
(2022)
Article
Construction & Building Technology
Mei-Yu Xuan et al.
Summary: This study proposes a method to reduce autogenous shrinkage and increase strength in ultra-high-strength concrete by controlling the hydration reaction of the binder. The addition of belite-rich Portland cement (BPC) reduces autogenous shrinkage, increases long-term strength, and decreases CO2 emissions.
JOURNAL OF BUILDING ENGINEERING
(2022)
Article
Construction & Building Technology
Jinpeng Feng et al.
Summary: This paper comprehensively investigates the surrogate model of recycled aggregate concrete (RAC) creep behavior prediction using machine learning algorithms. The study evaluates the impact of input variables on the prediction results and identifies loading age as the most influential factor. The XGBoost model demonstrates higher efficiency and accuracy in predicting RAC creep under various conditions. The findings can assist designers in understanding RAC structures and promote the application of RAC in buildings, as well as the study of reducing carbon emissions.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
Vahab Toufigh et al.
Summary: This study proposes a novel machine learning algorithm, SVR-DE, to predict the post-fire compressive strength ratio of slag-based concrete. Among the four different models based on different kernel functions, the model with polynomial kernel function showed the highest accuracy. The sensitivity analysis revealed the importance of six parameters in the post-fire strength ratio of slag-based concrete.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
Victor Revilla-Cuesta et al.
Summary: This paper presents models for predicting the modulus of elasticity in concrete using non-destructive tests, and improving the estimation accuracy with a density correction factor. The results show that the multiple-regression model has a high estimation precision.
DEVELOPMENTS IN THE BUILT ENVIRONMENT
(2022)
Article
Computer Science, Artificial Intelligence
Hongyan Yan et al.
Summary: This paper proposes an investment estimation model of prefabricated concrete buildings based on the XGBoost machine learning algorithm, which extracts construction characteristic indices and quantifies uncertainty. Compared with traditional machine learning methods, this model has better generalization and interpretability.
ADVANCED ENGINEERING INFORMATICS
(2022)
Article
Construction & Building Technology
Hamza Imran et al.
Summary: Testing the compressive strength of concrete using machine learning approaches is crucial for civil engineering. This study presents two ensemble models for accurately predicting the compressive strength of new concrete containing recycled concrete aggregate (RCA) and ground granulated blast furnace slag (GGBFS).
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Computer Science, Interdisciplinary Applications
Jin Duan et al.
Summary: Recycled aggregate concrete is being researched using artificial intelligence techniques to assess its compressive strength, with the ICA-XGBoost model proving to be the most effective among the developed models. This model can be utilized in construction engineering to ensure adequate mechanical performance and safe usage of recycled aggregate concrete for building purposes.
ENGINEERING WITH COMPUTERS
(2021)
Article
Construction & Building Technology
Qinghe Wang et al.
Summary: This study proposed a new model for estimating the autogenous shrinkage of recycled aggregate concrete with recycled coarse aggregate. Results showed that the autogenous shrinkage of RAC was influenced by internal curing effects induced by absorbed water of RCA and by the RCA stiffness loss caused by adhered residual mortar. The model developed in this study is capable of predicting well the autogenous shrinkage of RAC.
CONSTRUCTION AND BUILDING MATERIALS
(2021)
Article
Construction & Building Technology
Xiaochen Wang et al.
Summary: The bleeding characteristic of Portland cement influences its density and rheological behavior, with higher water-cement ratios leading to faster density growth speed and degree during bleeding. The apparent viscosity of the slurry shows two stages of change with bleeding time, indicating a transition from weak to stronger interactions within the cement slurry particles. The Herschel-Bulkley model performs better in describing the rheological characteristics of slurry bleeding compared to other empirical models.
CONSTRUCTION AND BUILDING MATERIALS
(2021)
Article
Green & Sustainable Science & Technology
Hsing-Jung Ho et al.
Summary: Effective recycling and use of chemicals in concrete waste are crucial for developing a sustainable cement and concrete industry, as well as addressing various environmental issues. Concrete waste shows great potential for CO2 sequestration and carbonation processes.
JOURNAL OF CLEANER PRODUCTION
(2021)
Article
Materials Science, Multidisciplinary
Osama Mohamed et al.
Summary: Self-consolidating concrete has advantages over traditional concrete, but corrosion of steel reinforcement remains a major issue. The study successfully developed Artificial Neural Networks for predicting chloride penetration levels and compressive strength of SCC mixes. The trained ANNs showed promise in accurately predicting chloride penetration levels and compressive strength based on selected input parameters.
Article
Mining & Mineral Processing
Yuantian Sun et al.
Summary: This study introduced the jet grouting technique to improve the self-supporting ability of coal mass and analyzed the strength of JG composite by studying the UCS evolution patterns. The results showed that chemical grout composite has higher short-term strength, while cement grout composite achieves more stable long-term strength. Models with adjusted parameters can achieve high prediction accuracy, highlighting the importance of grout type and curing time consideration.
INTERNATIONAL JOURNAL OF MINING SCIENCE AND TECHNOLOGY
(2021)
Article
Construction & Building Technology
Eslam Gomaa et al.
Summary: This study introduces a random forest model to predict two important properties of fly ash-based AACs, providing high fidelity predictions of new AACs and quantitatively assessing the influence of physiochemical attributes and process parameters on AAC properties, offering a new pathway for optimization of AAC properties.
CEMENT & CONCRETE COMPOSITES
(2021)
Article
Construction & Building Technology
Emerson F. Felix et al.
Summary: The control and prediction of carbonation depth in reinforced concrete structures is crucial for the construction industry, as it directly affects the service life and durability of the structures. An Artificial Neural Network with backpropagation algorithm was used to predict carbonation depth in concretes containing fly ash addition, with 90 different network topologies implemented. The parametric study revealed that cement consumption, fly ash content, CO2 rate, and relative humidity were the parameters most influencing carbonation depth in fly ash-concretes. The optimized model can estimate the lifespan of concrete structures and serve as a simulation tool for engineering projects focusing on durability.
CONSTRUCTION AND BUILDING MATERIALS
(2021)
Article
Construction & Building Technology
Harun Tanyildizi
Summary: This study found that the deep LSTM model can estimate the geopolymerization process of fly ash-based geopolymer with higher accuracy than the SVR and kNN models.
CEMENT & CONCRETE COMPOSITES
(2021)
Article
Construction & Building Technology
Yuxi Zhao et al.
Summary: The study tested the physical properties of recycled coarse aggregate (RCA) before and after microbial induced carbonate precipitation (MICP) modification, and investigated the effects of MICP modification on the mechanical and durability properties of concrete specimens. SEM observation and ITZs microhardness test were conducted to reveal the micro mechanism of improvement due to the MICP modification, showing that the modified RCA exhibited improved properties and the concrete specimens with modified RCA exhibited higher compressive strength and steel corrosion resistance.
CEMENT & CONCRETE COMPOSITES
(2021)
Article
Construction & Building Technology
Hongwei Song et al.
Summary: This study focused on predicting the compressive strength of concrete containing fly ash using machine learning approaches. Different supervised learning algorithms were utilized, with the bagging algorithm showing the highest accuracy in prediction. Experimental data was used to validate the models, demonstrating high precision in forecasting the compressive strength.
CONSTRUCTION AND BUILDING MATERIALS
(2021)
Article
Construction & Building Technology
Xueqing Zhang et al.
Summary: This study explored nine machine learning methods and found that nonlinear models generally perform better than linear models, with the random forest model of ensemble learning performing the best. The study also confirmed the usefulness of data visualization in learning, summarizing data, understanding variable relationships, and making premodeling assumptions, as well as identified the top three most significant concrete constituents affecting the seven-day compressive strength.
CONSTRUCTION AND BUILDING MATERIALS
(2021)
Article
Green & Sustainable Science & Technology
Furqan Farooq et al.
Summary: This study uses machine intelligence algorithms to predict the strength of high-performance concrete (HPC) prepared with waste materials, employing ensemble learners and weak learners to construct a robust model. Eight parameters were chosen to predict the output, and bagging and boosting learners were used to enhance the response of individual models.
JOURNAL OF CLEANER PRODUCTION
(2021)
Article
Green & Sustainable Science & Technology
Emadaldin Mohammadi Golafshani et al.
Summary: This study proposes a machine learning model to predict the compressive strength of rubbercrete for practical use in construction projects. The green mix design model can achieve environmentally friendly and cost-effective concrete mix design. The optimal ratio of WR to natural aggregate for rubbercrete mix designs is found to be around 2%-6%.
JOURNAL OF CLEANER PRODUCTION
(2021)
Article
Green & Sustainable Science & Technology
Wafaa Mohamed Shaban et al.
Summary: A method for accurately predicting the compressive strength of strengthened recycled aggregate concrete was developed, integrating the SSA and DE algorithms to achieve better prediction performance. Sensitivity analysis showed that certain material contents and properties played vital roles in the model prediction.
JOURNAL OF CLEANER PRODUCTION
(2021)
Article
Green & Sustainable Science & Technology
F. Dabbaghi et al.
Summary: The experimental study on 30 LWC mixtures revealed the effects of variables such as LECA percentage, water-to-cement ratio, cement content, and silica fume dosage on compressive and tensile strengths. Utilizing data analysis and optimization methods allows accurate prediction of LWC mechanical properties and optimization of sustainable mixture proportions.
JOURNAL OF CLEANER PRODUCTION
(2021)
Article
Construction & Building Technology
Junfei Zhang et al.
Summary: Lightweight concrete (LWC) is widely used in the construction industry due to its advantages. However, optimizing multiple properties of LWC, such as UCS, density and cost, requires considering more influencing variables and may be difficult using traditional methods. This study proposes a multi-objective optimization method using machine learning and metaheuristic approaches to design LWC mixtures effectively, achieving high prediction accuracy and successfully optimizing the mixtures to meet conflicting objectives.
CEMENT & CONCRETE COMPOSITES
(2021)
Article
Construction & Building Technology
Xiao-Yong Wang
Summary: This paper proposes a method for the optimal design of concrete by incorporating fly ash. The study shows that carbonation or strength may dominate the mixtures in different strength concretes. Furthermore, stress types and levels also impact the optimal mixtures.
JOURNAL OF SUSTAINABLE CEMENT-BASED MATERIALS
(2021)
Article
Engineering, Environmental
Sophie Renard et al.
Summary: Lifecycle assessment (LCA) studies are commonly used to evaluate environmental impacts of pavement facilities. This study introduces a novel approach to LCA modeling using a type of reinforcement learning algorithm known as Q-learning, which has shown to reduce global warming impacts of pavement infrastructure by 13% to 18% in three representative case studies. This approach can help decision-makers optimize construction and maintenance plans while considering uncertainties and improve management strategies to mitigate environmental impacts.
RESOURCES CONSERVATION AND RECYCLING
(2021)
Article
Engineering, Environmental
Junfei Zhang et al.
Summary: A multi-objective optimization model for optimizing the mixture proportions of silica fume concrete using machine learning techniques and a meta-heuristic algorithm is developed in this study. The proposed MOBAS algorithm shows superior computational efficiency and accuracy in predicting concrete strength, achieving a high correlation coefficient. The model successfully obtains the Pareto front of optimal silica fume concrete mixture proportions, improving efficiency in mixture optimization and facilitating appropriate decision making before construction.
RESOURCES CONSERVATION AND RECYCLING
(2021)
Article
Construction & Building Technology
Panagiotis G. Asteris et al.
Summary: This study implemented a hybrid ensemble surrogate machine learning technique to predict the compressive strength of concrete. The newly constructed Hybrid Ensemble Model showed higher predictive accuracy compared to conventional machine learning models, making it a potential solution for overfitting issues and predicting concrete compressive strength in a more environmentally friendly and sustainable way.
CEMENT AND CONCRETE RESEARCH
(2021)
Article
Mechanics
Wenguang Chen et al.
Summary: This study presents machine learning prediction models based on a large database and Bayesian techniques, which can accurately predict the ultimate axial strain of FRP-confined concrete cylinders. Empirical results demonstrate that the proposed models have outstanding predictive performance, which can assist various stakeholders in better utilizing FRP-confined concrete columns in construction applications.
COMPOSITE STRUCTURES
(2021)
Article
Construction & Building Technology
Itzel Nunez et al.
Summary: A GBRT model is proposed to determine the carbonation depth of recycled aggregate concrete with different mineral additions, showing that machine learning outperformed mathematical models and can provide insight into concrete resistance to carbonation and predict other features of concrete with diverse recycled materials.
CONSTRUCTION AND BUILDING MATERIALS
(2021)
Article
Construction & Building Technology
Hailong Wang et al.
Summary: This paper introduces a numerical method based on Fick's law and reaction kinetics for predicting the erosion process of concrete in sodium sulphate solution. The model considers the effects of ITZ, pore-filling, and chemo-mechanical damage on diffusivity, as well as uneven precipitation of gypsum and ettringite in concrete. Simulation results show that the ITZ has a significant impact on diffusion and expansion of concrete specimens.
CONSTRUCTION AND BUILDING MATERIALS
(2021)
Article
Construction & Building Technology
Kaihua Liu et al.
Summary: This paper investigates the prediction of carbonation depth for recycled aggregate concrete (RAC) with machine learning models, where the Random Forest model demonstrated superior performance. ANN models hybridized with swarm intelligence algorithms outperform the standalone ANN model, and all machine learning models show higher accuracy than existing models.
CONSTRUCTION AND BUILDING MATERIALS
(2021)
Article
Construction & Building Technology
J. J. Xu et al.
Summary: This paper presents a Bayesian model updating approach for evaluating and updating existing deterministic models for the mechanical properties of recycled aggregate concrete (RAC), improving the accuracy and applicability of prediction performances. Using Bayesian parameter estimation technique, the important parameters in the updating process are assessed and the selected deterministic models for RAC mechanical performances are accordingly updated.
CONSTRUCTION AND BUILDING MATERIALS
(2021)
Article
Engineering, Environmental
Weisheng Lu et al.
Summary: This study utilized a data-driven approach to analyze a large dataset of construction waste loads in Hong Kong from 2017 to 2019, obtaining bulk density information for inert and non-inert construction waste. The findings validated heuristic rules regarding the bulk densities of the three generic types of construction waste and suggested adjustments to governmental waste management policies. Future research is recommended to further refine bulk density ranges for more accurate references in construction waste management.
RESOURCES CONSERVATION AND RECYCLING
(2021)
Article
Construction & Building Technology
Huan Zhang et al.
CEMENT & CONCRETE COMPOSITES
(2020)
Article
Construction & Building Technology
Nan Zhao et al.
CONSTRUCTION AND BUILDING MATERIALS
(2020)
Article
Construction & Building Technology
Emadaldin Mohammadi Golafshani et al.
CONSTRUCTION AND BUILDING MATERIALS
(2020)
Article
Engineering, Environmental
Muhammad Farjad Iqbal et al.
JOURNAL OF HAZARDOUS MATERIALS
(2020)
Article
Construction & Building Technology
Jiepeng Liu et al.
AUTOMATION IN CONSTRUCTION
(2020)
Article
Construction & Building Technology
Taihao Han et al.
CONSTRUCTION AND BUILDING MATERIALS
(2020)
Article
Green & Sustainable Science & Technology
Tianyu Xie et al.
JOURNAL OF CLEANER PRODUCTION
(2020)
Article
Construction & Building Technology
Khoa Tan Nguyen et al.
CONSTRUCTION AND BUILDING MATERIALS
(2020)
Article
Construction & Building Technology
Junfei Zhang et al.
CONSTRUCTION AND BUILDING MATERIALS
(2020)
Article
Construction & Building Technology
Huan Zhang et al.
CEMENT & CONCRETE COMPOSITES
(2020)
Article
Construction & Building Technology
Shanshan Qin et al.
CEMENT AND CONCRETE RESEARCH
(2020)
Article
Green & Sustainable Science & Technology
Hamed Naseri et al.
JOURNAL OF CLEANER PRODUCTION
(2020)
Article
Green & Sustainable Science & Technology
P. S. M. Thilakarathna et al.
JOURNAL OF CLEANER PRODUCTION
(2020)
Article
Construction & Building Technology
Rong Cai et al.
CEMENT AND CONCRETE RESEARCH
(2020)
Review
Construction & Building Technology
Wassim Ben Chaabene et al.
CONSTRUCTION AND BUILDING MATERIALS
(2020)
Article
Construction & Building Technology
Yimiao Huang et al.
CONSTRUCTION AND BUILDING MATERIALS
(2020)
Article
Construction & Building Technology
Benjamin A. Young et al.
CEMENT AND CONCRETE RESEARCH
(2019)
Article
Construction & Building Technology
Emadaldin Mohammadi Golafshani et al.
CEMENT & CONCRETE COMPOSITES
(2019)
Article
Green & Sustainable Science & Technology
Subhasis Pradhan et al.
JOURNAL OF CLEANER PRODUCTION
(2019)
Article
Engineering, Civil
J. J. Xu et al.
THIN-WALLED STRUCTURES
(2019)
Article
Construction & Building Technology
M. A. DeRousseau et al.
CONSTRUCTION AND BUILDING MATERIALS
(2019)
Article
Construction & Building Technology
Meysam Najimi et al.
JOURNAL OF BUILDING ENGINEERING
(2019)
Article
Construction & Building Technology
Kaijian Zhang et al.
CEMENT & CONCRETE COMPOSITES
(2018)
Review
Construction & Building Technology
Hui Guo et al.
CEMENT & CONCRETE COMPOSITES
(2018)
Article
Construction & Building Technology
Fangming Deng et al.
CONSTRUCTION AND BUILDING MATERIALS
(2018)
Review
Engineering, Civil
Hadi Salehi et al.
ENGINEERING STRUCTURES
(2018)
Article
Construction & Building Technology
Bo Dai et al.
STRUCTURAL CONTROL & HEALTH MONITORING
(2018)
Article
Engineering, Environmental
Rawaz Kurda et al.
RESOURCES CONSERVATION AND RECYCLING
(2018)
Article
Engineering, Mechanical
Fuyuan Gong et al.
JOURNAL OF ENGINEERING MECHANICS
(2017)
Article
Construction & Building Technology
Ning Li et al.
MATERIALS AND STRUCTURES
(2017)
Article
Engineering, Multidisciplinary
Nhat-Duc Hoang et al.
Article
Engineering, Mechanical
Fuyuan Gong et al.
JOURNAL OF ENGINEERING MECHANICS
(2017)
Article
Construction & Building Technology
Vesna Bulatovic et al.
CONSTRUCTION AND BUILDING MATERIALS
(2017)
Article
Construction & Building Technology
Emadaldin Mohammadi Golafshani et al.
AUTOMATION IN CONSTRUCTION
(2016)
Article
Construction & Building Technology
C. J. Zega et al.
CONSTRUCTION AND BUILDING MATERIALS
(2016)
Article
Construction & Building Technology
S. Boudali et al.
CONSTRUCTION AND BUILDING MATERIALS
(2016)
Article
Construction & Building Technology
Kemal Celik et al.
CEMENT & CONCRETE COMPOSITES
(2015)
Article
Construction & Building Technology
R. V. Silva et al.
CEMENT & CONCRETE COMPOSITES
(2015)
Article
Engineering, Environmental
Lei Jiang et al.
COLD REGIONS SCIENCE AND TECHNOLOGY
(2015)
Article
Mechanics
Rui Sun et al.
COMPOSITE STRUCTURES
(2015)
Article
Construction & Building Technology
Hyeong-Kyu Cho et al.
MATERIALS AND STRUCTURES
(2015)
Article
Construction & Building Technology
Shi-Cong Kou et al.
CEMENT & CONCRETE COMPOSITES
(2013)
Article
Construction & Building Technology
Z. H. Duan et al.
CONSTRUCTION AND BUILDING MATERIALS
(2013)
Article
Construction & Building Technology
Z. H. Duan et al.
CONSTRUCTION AND BUILDING MATERIALS
(2013)
Review
Engineering, Multidisciplinary
Osama Hodhod et al.
AIN SHAMS ENGINEERING JOURNAL
(2013)
Article
Construction & Building Technology
Mohammad Iqbal Khan
AUTOMATION IN CONSTRUCTION
(2012)
Article
Construction & Building Technology
Siamak Safarzadegan Gilan et al.
CONSTRUCTION AND BUILDING MATERIALS
(2012)
Article
Engineering, Civil
Joo-Ha Lee et al.
KSCE JOURNAL OF CIVIL ENGINEERING
(2012)
Article
Engineering, Multidisciplinary
Xiao-Yong Wang et al.
COMPOSITES PART B-ENGINEERING
(2011)
Article
Construction & Building Technology
Ha-Won Song et al.
CEMENT AND CONCRETE RESEARCH
(2009)
Article
Construction & Building Technology
R. Parichatprecha et al.
CONSTRUCTION AND BUILDING MATERIALS
(2009)
Article
Engineering, Environmental
Chi-Sun Poon et al.
RESOURCES CONSERVATION AND RECYCLING
(2007)
Article
Engineering, Environmental
Akash Rao et al.
RESOURCES CONSERVATION AND RECYCLING
(2007)
Article
Construction & Building Technology
Chi-Sun Poon et al.
CONSTRUCTION AND BUILDING MATERIALS
(2007)
Article
Construction & Building Technology
G Constantinides et al.
CEMENT AND CONCRETE RESEARCH
(2004)
Article
Construction & Building Technology
SM Levy et al.
CEMENT AND CONCRETE RESEARCH
(2004)
Article
Construction & Building Technology
O Bernard et al.
CEMENT AND CONCRETE RESEARCH
(2003)
Article
Construction & Building Technology
N Otsuki et al.
JOURNAL OF MATERIALS IN CIVIL ENGINEERING
(2003)
Article
Construction & Building Technology
N Gowripalan et al.
CEMENT AND CONCRETE RESEARCH
(2000)
