Prediction of Geopolymer Concrete Compressive Strength Using Convolutional Neural Networks

Geopolymer concrete emerges as a promising avenue for sustainable development and offers an effective solution to environmental problems.Its attributes as a non-toxic,low-carbon,and economical substitute for conventional cement concrete,coupled with its elevated compressive strength and reduced shrinkage properties,position it as a pivotal material for diverse applications spanning from architectural structures to transportation infrastructure.In this context,this study sets out the task of using machine learning(ML)algorithms to increase the accuracy and interpretability of predicting the compressive strength of geopolymer concrete in the civil engineering field.To achieve this goal,a new approach using convolutional neural networks(CNNs)has been adopted.This study focuses on creating a comprehensive dataset consisting of compositional and strength parameters of 162 geopolymer concrete mixes,all containing Class F fly ash.The selection of optimal input parameters is guided by two distinct criteria.The first criterion leverages insights garnered from previous research on the influence of individual features on compressive strength.The second criterion scrutinizes the impact of these features within the model’s predictive framework.Key to enhancing the CNN model’s performance is the meticulous determination of the optimal hyperparameters.Through a systematic trial-and-error process,the study ascertains the ideal number of epochs for data division and the optimal value of k for k-fold cross-validation—a technique vital to the model’s robustness.The model’s predictive prowess is rigorously assessed via a suite of performance metrics and comprehensive score analyses.Furthermore,the model’s adaptability is gauged by integrating a secondary dataset into its predictive framework,facilitating a comparative evaluation against conventional prediction methods.To unravel the intricacies of the CNN model’s learning trajectory,a loss plot is deployed to elucidate its learning rate.The study culminates in compelling findings that underscore the CNN model’s accurate prediction of geopolymer concrete compressive strength.To maximize the dataset’s potential,the application of bivariate plots unveils nuanced trends and interactions among variables,fortifying the consistency with earlier research.Evidenced by promising prediction accuracy,the study’s outcomes hold significant promise in guiding the development of innovative geopolymer concrete formulations,thereby reinforcing its role as an eco-conscious and robust construction material.The findings prove that the CNN model accurately estimated geopolymer concrete’s compressive strength.The results show that the prediction accuracy is promising and can be used for the development of new geopolymer concrete mixes.The outcomes not only underscore the significance of leveraging technology for sustainable construction practices but also pave the way for innovation and efficiency in the field of civil engineering.

Effect of silica fume on the fresh and hardened properties of fly ash-based self-compacting geopolymer concrete

The effect of silica fume on the fresh and hardened properties of fly ash-based self-compacting geopolymer concrete （SCGC） was investigated in this paper. The work focused on the concrete mixes with a fixed water-to-geopolymer solid （W/Gs） ratio of 0.33 by mass and a constant total binder content of 400 kg/m3. The mass fractions of silica fume that replaced fly ash in this research were 0wt%, 5wt%, 10wt%, and 15wt%. The workability-related fresh properties of SCGC were assessed through slump flow, V-funnel, and L-box test methods. Hardened concrete tests were limited to compressive, splitting tensile and flexural strengths, all of which were measured at the age of 1, 7, and 28 d after 48-h oven curing. The results indicate that the addition of silica fume as a partial replacement of fly ash results in the loss of workability; nevertheless, the mechanical properties of hardened SCGC are significantly improved by incorporating silica fume, especially up to 10wt%. Applying this percentage of silica fume results in 4.3% reduction in the slump flow; however, it increases the compressive strength by 6.9%, tensile strength by 12.8% and flexural strength by 11.5%.

Water Permeability in Fly Ash-Based Geopolymer Concrete

This research investigated the water permeability coefficient of fly ash-based geopolymer concrete. The effect of sodium hydroxide （Na（OH）） concentrations and Si/AI ratios on water permeability and compressive strength of geopolymer concretes were studied. The geopolymer concrete were prepared from Mae Moh fly ash with sodium silicate （Na2SiO3） and sodium hydroxide （Na（OH）） solutions. In the first group, concentration of Na（OH） was varied at 8, 10, 12, and 14 molar and the Si/AI ratio was kept constant at 1.98. In the second group, a concentration of Na（OH） was kept constant at 14 molar and the Si/AI ratio was varied at 2.2, 2.4, 2.6, and 2.8. The hardened concretes were air-cured in laboratory. The compressive strength and water permeability were tested at the age of 28 and 60 days. The results showed that compressive strengths of geopolymer concrete significantly increased with the increase of a concentration of Na（OH） and Si/AI ratio. The water permeability coefficients increase with the decrease of compressive strength. In addition, the high reduction of water permeability coefficients with time was found in geopolymer concrete with lower Na（OH） concentration than that higher Na（OH） concentration.

Machine learning based models for predicting compressive strength of geopolymer concrete

Recently,great attention has been paid to geopolymer concrete due to its advantageous mechanical and environmentally friendly properties.Much effort has been made in experimental studies to advance the understanding of geopolymer concrete,in which compressive strength is one of the most important properties.To facilitate engineering work on the material,an efficient predicting model is needed.In this study,three machine learning(ML)-based models,namely deep neural network(DNN),K-nearest neighbors(KNN),and support vector machines(SVM),are developed for forecasting the compressive strength of the geopolymer concrete.A total of 375 experimental samples are collected from the literature to build a database for the development of the predicting models.A careful procedure for data preprocessing is implemented,by which outliers are examined and removed from the database and input variables are standardized before feeding to the fitting process.The standard K-fold cross-validation approach is applied for evaluating the performance of the models so that overfitting status is well managed,thus the generalizability of the models is ensured.The effectiveness of the models is assessed via statistical metrics including root mean squared error(RMSE),mean absolute error(MAE),correlation coefficient(R),and the recently proposed performance index(PI).The basic mean square error(MSE)is used as the loss function to be minimized during the model fitting process.The three ML-based models are successfully developed for estimating the compressive strength,for which good correlations between the predicted and the true values are obtained for DNN,KNN,and SVM.The numerical results suggest that the DNN model generally outperforms the other two models.

Influence of surface cracking,anchor head profile,and anchor head size on cast-in headed anchors in geopolymer concrete

In this study,the concrete cone capacity,concrete cone angle,and load–displacement response of cast-in headed anchors in geopolymer concrete are explored using numerical analyses.The concrete damaged plasticity(CDP)model in ABAQUS is used to simulate the behavior of concrete substrates.The tensile behavior of anchors in geopolymer concrete is compared with that in normal concrete as well as that predicted by the linear fracture mechanics(LFM)and concrete capacity design(CCD)models.The results show that the capacity of the anchors in geopolymer concrete is 30%–40%lower than that in normal concrete.The results also indicate that the CCD model overestimates the capacity of the anchors in geopolymer concrete,whereas the LFM model provides a much more conservative prediction.The extent of the difference between the predictions by the numerical analysis and those of the above prediction models depends on the effective embedment depth of the anchor and the anchor head size.The influence of concrete surface cracking on the capacity of the anchor is shown to depend on the location of the crack and the effective embedment depth.The influence of the anchor head profile on the tensile capacity of the anchors is found to be insignificant.

State of the art review on the production and bond behaviour of reinforced geopolymer concrete

Geopolymer is produced through the polymerization of active aluminosilicate material with an alkaline activator,leading to the formation of a green,inorganic polymer binder.Geopolymer concrete(GPC)has become a promising low-carbon alternative to traditional Portland cement-based concrete(OPC).GPC-bonded reinforcing bars offer a promising alternative for concrete structures,boasting excellent geopolymer binder/reinforcement bonding and superior corrosion and high-temperature resistance compared to Portland cement.However,due to differences in the production process of GPC,there are distinct engineering property variations,including bonding characteristics.This literature review provides an examination of the manufacturing procedures of GPC,encompassing source materials,mix design,curing regimes,and other factors directly influencing concrete properties.Additionally,it delves into the bond mechanism,bond tests,and corresponding results that represent the bond characteristics.The main conclusions are that GPC generally has superior mechanical properties and bond performance compared to ordinary Portland cement concrete(OPC).However,proper standardization is needed for its production and performance tests to limit the contradictory results in the lab and on site.

Development of mix design method based on statistical analysis of different factors for geopolymer concrete

The present study proposes the mix design method of Fly Ash(FA)based geopolymer concrete using Response Surface Methodology(RSM).In this method,different factors,including binder content,alkali/binder ratio,NS/NH ratio(sodium silicate/sodium hydroxide),NH molarity,and water/solids ratio were considered for the mix design of geopolymer concrete.The 2D contour plots were used to setup the mix design method to achieve the target compressive strength.The proposed mix design method of geopolymer concrete is divided into three categories based on curing regime,specifically one ambient curing(25°C)and two heat curing(60 and 90°C).The proposed mix design method of geopolymer concrete was validated through experimentation of M30,M50,and M70 concrete mixes at all curing regimes.The observed experimental compressive strength results validate the mix design method by more than 90%of their target strength.Furthermore,the current study concluded that the required compressive strength can be achieved by varying any factor in the mix design.In addition,the factor analysis revealed that the NS/NH ratio significantly affects the compressive strength of geopolymer concrete.

Assessment and prediction of the mechanical properties of ternary geopolymer concrete

This paper utilized granulated blast furnace slag(GBFS),fly ash(FA),and zeolite powder(ZP)as the binders of ternary geopolymer concrete(TGC)activated with sodium silicate solution.The effects of alkali content(AC)and alkaline activator modulus(AAM)on the compressive strength,flexural tensile strength and elastic modulus of TGC were tested and the SEM micrographs were investigated.The experimental results were then compared with the predictions based on models of mechanical properties,and the amended models of TGC were proposed taking account of the effects of AC and AAM.The results indicated that increasing AC and reducing AAM which were in the specific ranges(5%to 7%and 1.1 to 1.5,respectively)had positive effects on the mechanical properties of TGC.In addition,the flexural tensile strength of TGC was 27.7%higher than that of OPC at the same compressive strength,while the elastic modulus of TGC was 25.8%lower than that of OPC.Appropriate prediction models with the R2 of 0.945 and 0.987 for predicting flexural tensile strength and elastic modulus using compressive strength,respectively,were proposed.Fitting models,considering the effects of AC and AAM,were also proposed to predict the mechanical properties of TGC.

Performances of a new sustainable and durable dry beam-column joints under cyclic and impact loads

This study investigated the performances of a new type of precast beam-column joint subjected to earthquake and impact loads.For sustainability and durability considerations,new materials such as corrosion-resistant fibre reinforced polymer(FRP)bolts and reinforcements,fibre reinforced concrete(FRC),and geopolymer concrete(GPC)were used to construct the joint.To examine the resilience,durability,sustainability,and multi-hazard resistance capacities,both cyclic and pendulum impact tests were carried out.The experimental results demonstrated that the proposed precast joints had the comparable or even better performances as compared with the traditional monolithic joints under cyclic and impact loads.Numerical simulations using ABAQUS were also adopted to determine the optimal values of the concrete-end-plate(CEP)thickness for the proposed dry joints and to further quantify other response parameters which could not be obtained during the test,e.g.,stress distribution,energy absorption,and stress contours.Discussion on the influences of various parameters on joint performances under different loading conditions was also presented in this study.