Assessment of compressive strength of jet grouting by machine learning

Jet grouting is one of the most popular soil improvement techniques,but its design usually involves great uncertainties that can lead to economic cost overruns in construction projects.The high dispersion in the properties of the improved material leads to designers assuming a conservative,arbitrary and unjustified strength,which is even sometimes subjected to the results of the test fields.The present paper presents an approach for prediction of the uniaxial compressive strength(UCS)of jet grouting columns based on the analysis of several machine learning algorithms on a database of 854 results mainly collected from different research papers.The selected machine learning model(extremely randomized trees)relates the soil type and various parameters of the technique to the value of the compressive strength.Despite the complex mechanism that surrounds the jet grouting process,evidenced by the high dispersion and low correlation of the variables studied,the trained model allows to optimally predict the values of compressive strength with a significant improvement with respect to the existing works.Consequently,this work proposes for the first time a reliable and easily applicable approach for estimation of the compressive strength of jet grouting columns.

Predicting uniaxial compressive strength of tuff after accelerated freeze-thaw testing: Comparative analysis of regression models and artificial neural networks

Ignimbrites have been widely used as building materials in many historical and touristic structures in the Kayseri region of Türkiye. Their diverse colours and textures make them a popular choice for modern construction as well. However, ignimbrites are particularly vulnerable to atmospheric conditions, such as freeze-thaw cycles, due to their high porosity, which is a result of their formation process. When water enters the pores of the ignimbrites, it can freeze during cold weather. As the water freezes and expands, it generates internal stress within the stone, causing micro-cracks to develop. Over time, repeated freeze-thaw (F-T) cycles lead to the growth of these micro-cracks into larger cracks, compromising the structural integrity of the ignimbrites and eventually making them unsuitable for use as building materials. The determination of the long-term F-T performance of ignimbrites can be established after long F-T experimental processes. Determining the long-term F-T performance of ignimbrites typically requires extensive experimental testing over prolonged freeze-thaw cycles. To streamline this process, developing accurate predictive equations becomes crucial. In this study, such equations were formulated using classical regression analyses and artificial neural networks (ANN) based on data obtained from these experiments, allowing for the prediction of the F-T performance of ignimbrites and other similar building stones without the need for lengthy testing. In this study, uniaxial compressive strength, ultrasonic propagation velocity, apparent porosity and mass loss of ignimbrites after long-term F-T were determined. Following the F-T cycles, the disintegration rate was evaluated using decay function approaches, while uniaxial compressive strength (UCS) values were predicted with minimal input parameters through both regression and ANN analyses. The ANN and regression models created for this purpose were first started with a single input value and then developed with two and three combinations. The predictive performance of the models was assessed by comparing them to regression models using the coefficient of determination (R2) as the evaluation criterion. As a result of the study, higher R2 values (0.87) were obtained in models built with artificial neural network. The results of the study indicate that ANN usage can produce results close to experimental outcomes in predicting the long-term F-T performance of ignimbrite samples.

Predicting dynamic compressive strength of frozen-thawed rocks by characteristic impedance and data-driven methods

In cold regions,the dynamic compressive strength(DCS)of rock damaged by freeze-thaw weathering significantly influences the stability of rock engineering.Nevertheless,testing the dynamic strength under freeze-thaw weathering conditions is often both time-consuming and expensive.Therefore,this study considers the effect of characteristic impedance on DCS and aims to quickly determine the DCS of frozen-thawed rocks through the application of machine-learning techniques.Initially,a database of DCS for frozen-thawed rocks,comprising 216 rock specimens,was compiled.Three external load parameters(freeze-thaw cycle number,confining pressure,and impact pressure)and two rock parameters(characteristic impedance and porosity)were selected as input variables,with DCS as the predicted target.This research optimized the kernel scale,penalty factor,and insensitive loss coefficient of the support vector regression(SVR)model using five swarm intelligent optimization algorithms,leading to the development of five hybrid models.In addition,a statistical DCS prediction equation using multiple linear regression techniques was developed.The performance of the prediction models was comprehensively evaluated using two error indexes and two trend indexes.A sensitivity analysis based on the cosine amplitude method has also been conducted.The results demonstrate that the proposed hybrid SVR-based models consistently provided accurate DCS predictions.Among these models,the SVR model optimized with the chameleon swarm algorithm exhibited the best performance,with metrics indicating its effectiveness,including root mean square error(RMSE)﹦3.9675,mean absolute error(MAE)﹦2.9673,coefficient of determination(R^(2))﹦0.98631,and variance accounted for(VAF)﹦98.634.This suggests that the chameleon swarm algorithm yielded the most optimal results for enhancing SVR models.Notably,impact pressure and characteristic impedance emerged as the two most influential parameters in DCS prediction.This research is anticipated to serve as a reliable reference for estimating the DCS of rocks subjected to freeze-thaw weathering.

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.

Fluid-Related Performances and Compressive Strength of Clinker-Free Cementitious Backfill Material Based on Phosphate Tailings

Phosphate tailings are usually used as backfill material in order to recycle tailings resources.This study considers the effect of the mix proportions of clinker-free binders on the fluidity,compressive strength and other key performances of cementitious backfill materials based on phosphate tailings.In particular,three solid wastes,phosphogypsum(PG),semi-aqueous phosphogypsum(HPG)and calcium carbide slag(CS),were selected to activate wet ground granulated blast furnace slag(WGGBS)and three different phosphate tailings backfill materials were prepared.Fluidity,rheology,settling ratio,compressive strength,water resistance and ion leaching behavior of backfill materials were determined.According to the results,when either PG or HPG is used as the sole activator,the fluidity properties of the materials are enhanced.Phosphate tailings backfill material activated with PG present the largest fluidity and the lowest yield stress.Furthermore,the backfill material’s compressive strength is considerably increased to 2.9 MPa at 28 days after WGGBS activation using a mix of HPG and CS,all with a settling ratio of only 1.15 percent.Additionally,all the three ratios of binder have obvious solidification effects on heavy metal ions Cu and Zn,and P in phosphate tailings.

An Investigation into the Compressive Strength,Permeability and Microstructure of Quartzite-Rock-Sand Mortar

River sand is an essential component used as a fine aggregate in mortar and concrete.Due to unrestrained exploitation,river sand resources are gradually being exhausted.This requires alternative solutions.This study deals with the properties of cement mortar containing different levels of manufactured sand(MS)based on quartzite,used to replace river sand.The river sand was replaced at 20%,40%,60%and 80%with MS(by weight or volume).The mechanical properties,transfer properties,and microstructure were examined and compared to a control group to study the impact of the replacement level.The results indicate that the compressive strength can be improved by increasing such a level.The strength was improved by 35.1%and 45.5%over that of the control mortar at replacement levels of 60%and 80%,respectively.Although there was a weak link between porosity and gas permeability in the mortars with manufactured sand,the gas permeability decreased with growing the replacement level.The microstructure of the MS mortar was denser,and the cement paste had fewer microcracks with increasing the replacement level.

Uniaxial Compressive Strength Prediction for Rock Material in Deep Mine Using Boosting-Based Machine Learning Methods and Optimization Algorithms

Traditional laboratory tests for measuring rock uniaxial compressive strength(UCS)are tedious and timeconsuming.There is a pressing need for more effective methods to determine rock UCS,especially in deep mining environments under high in-situ stress.Thus,this study aims to develop an advanced model for predicting the UCS of rockmaterial in deepmining environments by combining three boosting-basedmachine learning methods with four optimization algorithms.For this purpose,the Lead-Zinc mine in Southwest China is considered as the case study.Rock density,P-wave velocity,and point load strength index are used as input variables,and UCS is regarded as the output.Subsequently,twelve hybrid predictive models are obtained.Root mean square error(RMSE),mean absolute error(MAE),coefficient of determination(R2),and the proportion of the mean absolute percentage error less than 20%(A-20)are selected as the evaluation metrics.Experimental results showed that the hybridmodel consisting of the extreme gradient boostingmethod and the artificial bee colony algorithm(XGBoost-ABC)achieved satisfactory results on the training dataset and exhibited the best generalization performance on the testing dataset.The values of R2,A-20,RMSE,and MAE on the training dataset are 0.98,1.0,3.11 MPa,and 2.23MPa,respectively.The highest values of R2 and A-20(0.93 and 0.96),and the smallest RMSE and MAE values of 4.78 MPa and 3.76MPa,are observed on the testing dataset.The proposed hybrid model can be considered a reliable and effective method for predicting rock UCS in deep mines.

An Effective Hybrid Model of ELM and Enhanced GWO for Estimating Compressive Strength of Metakaolin-Contained Cemented Materials

This research proposes a highly effective soft computing paradigm for estimating the compressive strength(CS)of metakaolin-contained cemented materials.The proposed approach is a combination of an enhanced grey wolf optimizer(EGWO)and an extreme learning machine(ELM).EGWO is an augmented form of the classic grey wolf optimizer(GWO).Compared to standard GWO,EGWO has a better hunting mechanism and produces an optimal performance.The EGWO was used to optimize the ELM structure and a hybrid model,ELM-EGWO,was built.To train and validate the proposed ELM-EGWO model,a sum of 361 experimental results featuring five influencing factors was collected.Based on sensitivity analysis,three distinct cases of influencing parameters were considered to investigate the effect of influencing factors on predictive precision.Experimental consequences show that the constructed ELM-EGWO achieved the most accurate precision in both training(RMSE=0.0959)and testing(RMSE=0.0912)phases.The outcomes of the ELM-EGWO are significantly superior to those of deep neural networks(DNN),k-nearest neighbors(KNN),long short-term memory(LSTM),and other hybrid ELMs constructed with GWO,particle swarm optimization(PSO),harris hawks optimization(HHO),salp swarm algorithm(SSA),marine predators algorithm(MPA),and colony predation algorithm(CPA).The overall results demonstrate that the newly suggested ELM-EGWO has the potential to estimate the CS of metakaolin-contained cemented materials with a high degree of precision and robustness.

Unconfined compressive strength and failure behaviour of completely weathered granite from a fault zone

Understanding the strength characteristics and deformation behaviour of the tunnel surrounding rock in a fault zone is significant for tunnel stability evaluation.In this study,a series of unconfined compression tests were conducted to investigate the mechanical characteristics and failure behaviour of completely weathered granite(CWG)from a fault zone,considering with height-diameter(h/d)ratio,dry densities(ρd)and moisture contents(ω).Based on the experimental results,a regression mathematical model of unconfined compressive strength(UCS)for CWG was developed using the Multiple Nonlinear Regression method(MNLR).The research results indicated that the UCS of the specimen with a h/d ratio of 0.6 decreased with the increase ofω.When the h/d ratio increased to 1.0,the UCS increasedωwith up to 10.5%and then decreased.Increasingρd is conducive to the improvement of the UCS at anyω.The deformation and rupture process as well as final failure modes of the specimen are controlled by h/d ratio,ρd andω,and the h/d ratio is the dominant factor affecting the final failure mode,followed byωandρd.The specimens with different h/d ratio exhibited completely different fracture mode,i.e.,typical splitting failure(h/d=0.6)and shear failure(h/d=1.0).By comparing the experimental results,this regression model for predicting UCS is accurate and reliable,and the h/d ratio is the dominant factor affecting the UCS of CWG,followed byρd and thenω.These findings provide important references for maintenance of the tunnel crossing other fault fractured zones,especially at low confining pressure or unconfined condition.

Effect of chloride salt concentration on unconfined compression strength of cement-treated Lianyungang soft marine clay

This study aims to quantify the influence of the amount of cement and chloride salt on the unconfined compression strength （UCS） of Lianyungang marine clay. The clays with various sodium chloride salt concentrations were prepared artificially and stabilized by ordinary Portland cement with various contents. A series of UCS tests of cement stabilized clay specimen after 28 d curing were carried out. The results indicate that the increase of salt concentration results in the decrease in the UCS of cement-treated soil. The negative effect of salt concentration on the strength of cement stabilized clay directly relates to the cement content and salt concentration. The porosity-salt concentration/cement content ratio is a fundamental parameter for assessing the UCS of cement-treated salt-rich clay. An empirical prediction model of UCS is also proposed to take into account the effect of salt concentration. The findings of this study can be referenced for the stabilization improvement of chloride slat- rich soft clay.

Prediction of compressive strength of cement mortars with fly ash and activated coal gangue

The pozzolanic activity of coal gangue, which is calcining at 500 to 1 000 ℃, differs distinctly. The simplex-centroid design with upper and lower bounds of component proportion is adopted to study the compressive strength of mortars made with ternary blends of cement, activated coal gangue and fly ash. Based on the results of a minimum of seven design points, three special cubic polynomial models are used to establish the strength predicating equations at different ages for mortars. Five experimental checkpoints were also designed to verify the precision of the equations. The most frequent errors of the predicted values are within 3%. A simple and practical way is provided for determining the optimal proportion of two admixtures when they are used in concrete.

Calculation on uniaxial compressive strength of high strength concrete after wrapped by FRP

A theoretical calculation method of the axial compressive strength of a high strength concrete with fibre reinforced plastics (FRP) constraint is proposed. It is shown by test verification that the FRP strength devotion factor used for this method is in accordance with actual conditions. FRP is not up to the ultimate strength when the concrete reaches the ultimate strength, whose strength devotion factor is in the range of 0.28 to 0.59, which is related to an elastic modulus. The method can be used to estimate axial compressive strength of the concrete strengthened with FRP. The theoretical strength is 10% to 30% higher than the measured one. The deviation comes mainly from a non-ideal bonding condition of FRP-concrete interfaces and discrete property of the testing data of compressive strength.

Strength regularity and failure criterion of plain HSHPC under biaxial compression after exposure to high temperatures

Biaxial compression tests are performed on 100 mm × 100 mm × 100 mm cubic specimens of plain high-strength highperformance concrete （HSHPC） at seven kinds of stress ratios, σ2：σ3 =0 ： - 1, -0.20 ： - 1, -0.30 ： - 1, -0.40 ： - 1, -0.50 ： -1, -0. 75 ： - 1, and - 1.00 ： - 1 after exposure to normal and high temperatures of 20, 200, 300, 400, 500 and 600 ℃, using a large static-dynamic true triaxial machine. Frictionreducing pads are three layers of plastic membranes with glycerine in-between for the compressive loading plane. Failure modes of the specimens are described. The two principally static compressive strengths are measured. The influences of the temperatures and stress ratios on the biaxial strengths of HSHPC after exposure to high temperatures are also analyzed. The experimental results show that the uniaxial compressive strength of plain HSHPC after exposure to high temperatures does not decrease completely with the increase in temperature; the ratios of the biaxial to its uniaxial compressive strengths depend on the stress ratios and brittleness-stiffness of HSHPC after exposure to different high temperatures. The formula of the Kupfer-Gerstle failure criterion modified with the temperature and stress ratio parameters for plain HSHPC is proposed.

Effects of binder strength and aggregate size on the compressive strength and void ratio of porous concrete

To test the influence of binder strength, porous concretes with 4 binder strengths between 30.0-135.0 MPa and 5 void ratios between 15%-35% were tested. The results indicated that for the same aggregate, the rates of strength reduction due to the increases in void ratio were the same for binders with different strengths. To study the influence of aggregate size, 3 single size aggregates with nominal sizes of 5.0, 13.0 and 20.0 mm （Nos. 7, 6 and 5 according to JIS A 5001） were used to make porous concrete. The strengths of porous concrete are found to be dependent on aggregate size. The rate of strength reduction of porous concrete with small aggregate size is found to be higher than that with larger aggregate size. At the same void ratio, the strength of porous concrete with large aggregate is larger than that with small aggregate. The general equations for porous concrete are related to compressive strength and void ratio for different binder strengths and aggregate sizes.

Surface Modification of Fly Ashes with Carbide Slag and Its Effect on Compressive Strength and Autogenous Shrinkage of Blended Cement Pastes

Surfaces of grade III fly ashes were modified through mixing with carbide slag and calcining at 850 ℃ for 1 h. Mineralogical compositions and surface morphology of fly ashes before and after modification were characterized by X-ray diffraction （XRD） and scanning electron microscopy （SEM）, respectively. Effect of surface-modified fly ashes on compressive strength and autogenous shrinkage of blended cement pastes was investigated. Microstructures of cement pastes were examined by backscattered electron （BSE） imaging and mercury intrusion porosimetry （MIP）. The experimental results showed that β-C2S was formed on the surfaces of fly ashes after modification. Hydration ofβ-C2S on the surface-modified fly ashes densified interface zone and enhanced bond strength between particles of fly ashes and hydrated clinkers. In addition, surface modification of fly ashes tended to decrease total porosity and 10-50 nm pores of cement pastes. Surface modification of fly ashes increased compressive strength and reduced autogenous shrinkage of cement pastes.

Effect of Coal Gangue with Different Kaolin Contents on Compressive Strength and Pore Size of Blended Cement Paste

The effects of activated coal gangue on compressive strength, porosity and pore size distribution of hardened cement pastes were investigated. Activated coal gangue with two different kaolin contents, one higher and one lower, were used to partially replace Portland cement at 0%, 10%, and 30% by weight. The water to binder ratio（w/b） of 0.5 was used for all the blended cement paste mixes. Experimental results indicate that the blended cement of activated coal gangue mortar with higher kaolin mineral content has a higher compressive strength than that with lower kaolin mineral content. The porosity and pore size of blended cement mortar were significantly affected by the replacement of activated coal gangue.

The uniaxial compressive strength of the Arctic summer sea ice

The results on the uniaxial compressive strength of Arctic summer sea ice are presented based on the sam- ples collected during the fifth Chinese National Arctic Research Expedition in 2012 （CHINARE-2012）. Exper- imental studies were carried out at different testing temperatures （-3, -6 and -9℃）, and vertical samples were loaded at stress rates ranging from 0.001 to 1 MPa/s. The temperature, density, and salinity of the ice were measured to calculate the total porosity of the ice. In order to study the effects of the total porosity and the density on the uniaxial compressive strength, the measured strengths for a narrow range of stress rates from 0.01 to 0.03 MPa/s were analyzed. The results show that the uniaxial compressive strength decreases linearly with increasing total porosity, and when the density was lower than 0.86 g/cm3, the uniaxial com- pressive strength increases in a power-law manner with density. The uniaxial compressive behavior of the Arctic summer sea ice is sensitive to the loading rate, and the peak uniaxial compressive strength is reached in the brittle-ductile transition range. The dependence of the strength on the temperature shows that the calculated average strength in the brittle-ductile transition range, which was considered as the peak uniaxial compressive strength, increases steadily in the temperature range from -3 to -9℃.

Effect of Sample Disturbance on Unconfined Compression Strength of Natural Marine Clays

Quantitatively correcting the unconfined compressive strength for sample disturbance is an important research project in the practice of ocean engineering and geotechnical engineering. In this study, the specimens of undisturbed natural marine clay obtained from the same depth at the same site were deliberately disturbed to different levels. Then, the specimens with different extents of sample disturbance were trimmed for both oedometer tests and unconfined compression tests. The degree of sample disturbance SD is obtained from the oedometer test data. The relationship between the unconfined compressive strength q u and SD is studied for investigating the effect of sample disturbance on q u. It is found that the value of q u decreases linearly with the increase in SD. Then, a simple method of correcting q u for sample disturbance is proposed. Its validity is also verified through analysis of the existing published data.

Compressive Strength of Polymer Grouting Material at Different Temperatures

In order to study the influence of temperature on compressive strength of polymer grouting material,the compression specimen injection mold is self-made,and the uniaxial compressive test was carried out in the temperature control box under different temperatures.The change regularity of compressive strength of polymer grouting material under different temperatures and the law of volume changes of polymer samples were obtained.The experimental results show that：the compressive strength of polymer material increases with the increase of density;the temperature change has a certain influence on the compressive strength of polymer grouting material;the compressive strength decreases with temperature increases under the same density,but the compressive strength is not significantly affected by temperature when the density is less than 0.4 g/cm3;the volume change of the samples accords with the law of thermal expansion and contraction when temperature changes,and the increase of the volume is obvious when it is under high temperature.The achievements will provide an important basis to the application of the polymer grouting material.

Prediction of uniaxial compressive strength and modulus of elasticity for Travertine samples using regression and artificial neural networks

Uniaxial Compressive Strength (UCS) and modulus of elasticity (E) are the most important rock parameters required and determined for rock mechanical studies in most civil and mining projects. In this study, two mathematical methods, regression analysis and Artificial Neural Networks (ANNs), were used to predict the uniaxial compressive strength and modulus of elasticity. The P-wave velocity, the point load index, the Schmidt hammer rebound number and porosity were used as inputs for both meth-ods. The regression equations show that the relationship between P-wave velocity, point load index, Schmidt hammer rebound number and the porosity input sets with uniaxial compressive strength and modulus of elasticity under conditions of linear rela-tions obtained coefficients of determination of (R2) of 0.64 and 0.56, respectively. ANNs were used to improve the regression re-sults. The generalized regression and feed forward neural networks with two outputs (UCS and E) improved the coefficients of determination to more acceptable levels of 0.86 and 0.92 for UCS and to 0.77 and 0.82 for E. The results show that the proposed ANN methods could be applied as a new acceptable method for the prediction of uniaxial compressive strength and modulus of elasticity of intact rocks.