Hybrid BO-XGBoost and BO-RF Models for the Strength Prediction of Self-Compacting Mortars with Parametric Analysis

Self-compacting mortar (SCM) has superior workability and long-term durable performance compared to traditional mortar. The strength of SCM, including both its compressive and flexural strengths, is a crucial property that is determined by appropriate curing conditions and mix design parameters. In the context of materials science, predicting the strength of SCM is challenging because of multiple influencing factors. This study employed machine learning techniques to establish SCM strength prediction models. Based on ten different input parameters, the strength of SCM specimens were predicted using two different types of hybrid machine learning (HML) models, namely Extreme Gradient Boosting (XGBoost) and the Random Forest (RF) algorithm. HML models were trained and tested by experimental data from 320 test specimens. In addition, the Bayesian optimization method was utilized to fine tune the hyperparameters of the employed algorithms, and cross-validation was employed to partition the database into multiple folds for a more thorough exploration of the hyperparameter space while providing a more accurate assessment of the model's predictive power. The results show that both HML models can successfully predict the SCM strength values with high accuracy, and the Bo-XGB model demonstrated higher accuracy (R² = 0.96 for training and R² = 0.91 for testing phases) for predicting flexural strength with low error. In terms of compressive strength prediction, the employed BO-RF model performed very well, with R² = 0.96 for train and R² = 0.88 testing stages with minor errors. Moreover, the SHAP algorithm, permutation importance and leave-one-out importance score were used for sensitivity analysis to explain the prediction process and interpret the governing input variable parameters of the proposed HML models. Finally, the outcomes of this study might be applied to guide the future mix design of SCM specimens.

Strength Investigation and Prediction of Superfine Tailings Cemented Paste Backfill Based on Experiments and Intelligent Methods

The utilization of solid waste for filling mining presents substantial economic and environmental advantages, making it the primary focus of current filling mining technology development. To enhance the mechanical properties of superfine tailings cemented paste backfill (SCPB), this study conducted response surface methodology experiments to investigate the impact of various factors on the strength of SCPB, including the composite cementitious material, consisting of cement and slag powder, and the tailings' grain size. Additionally, various microanalysis techniques were used to investigate the microstructure of SCPB and the development mechanisms of its hydration products. Furthermore, machine learning was utilized to predict the strength of SCPB under multi-factor effects. The findings reveal that the combined effect of slag powder dosage and slurry mass fraction has the most significant influence on strength, while the coupling effect of slurry mass fraction and underflow productivity has the lowest impact on strength. Moreover, SCPB with 20% slag powder has the highest amount of hydration products and the most complete structure. When compared to other commonly used prediction models, the long-short term memory neural network (LSTM) constructed in this study had the highest prediction accuracy for SCPB strength under multi-factor conditions, with root mean square error (RMSE), correlation coefficient (R), and variance account for (VAF) reaching 0.1396, 0.9131, and 81.8747, respectively. By optimizing the LSTM using the sparrow search algorithm (SSA), the RMSE, R, and VAF improved by 88.6%, 9.4%, and 21.9%, respectively. The research results can provide guidance for the efficient filling of superfine tailings.

Probability Density Function Models for Float Glass under Mechanical Loading with Varying Parameters

Glass as a construction material has become indispensable and is still on the rise in the building industry. However, there is still a need for numerical models that can predict the strength of structural glass in different configurations. The complexity lies in the failure of glass elements largely driven by pre-existing microscopic surface flaws. These flaws are present over the entire glass surface, and the properties of each flaw vary. Therefore, the fracture strength of glass is described by a probability function and will depend on the size of the panels, the loading conditions and the flaw size distribution. This paper extends the strength prediction model of Osnes et al. with the model selection by the Akaike information criterion. This allows us to determine the most appropriate probability density function describing the glass panel strength. The analyses indicate that the most appropriate model is mainly affected by the number of flaws subjected to the maximum tensile stresses. When many flaws are loaded, the strength is better described by a normal or Weibull distribution. When few flaws are loaded, the distribution tends more towards a Gumbel distribution. A parameter study is performed to examine the most important and influencing parameters in the strength prediction model.

Strength Prediction of Ball-Milling-Modified Phosphorus Building Gypsum Based on NSGM (1,4) Model

Phosphogypsum is an industrial byproduct from the wet preparation of phosphoric acid. Phosphorus building gypsum can be obtained from phosphogypsum after high-thermal dehydration. This study aimed to analyze the influence of ball milling with different parameters on the strength of phosphorus building gypsum. In this paper, the absolute dry flexural strength and the absolute dry compressive strength of phosphorus building gypsum were compared under different mass ratios of material to ball, ball-milling speed, and ball-milling time, and the NSGM (1,4) model was applied to model and predict the strength of phosphorus building gypsum modified by ball milling. According to the research results, under the same mass ratio of material to ball and ball-milling speed, the absolute dry flexural strength and absolute dry compressive strength of phosphorus building gypsum firstly increased and then decreased with the increase in milling time. The NSGM (1,4) model established in this paper could effectively simulate and predict the absolute dry flexural strength and the absolute dry compressive strength of the ball-milling-modified phosphorus building gypsum; the average relative simulation errors were 12.38% and 13.77%, and the average relative prediction errors were 6.30% and 12.47%.

Study on the Expansion and Compression Resistance of 3D-Textile-Reinforced Self-Stressing Concrete

Textile-reinforced concrete (TRC), as a kind of high-crack-resistance and high-corrosion-resistance material, has been widely studied. The current research has begun the exploration of the change of textile form, such as 3D-textile-reinforced concrete (3D TRC), and its superior bending performance has been verified. In order to pursue better mechanical properties, combined with the characteristics of self-stressing concrete and 3D textiles, three-dimensional-textile-reinforced self-stressing concrete (3D-TRSSC) specimens were designed in this research. The expansive and compressive properties of specimens with two types of textiles were tested by self-stress and compressibility tests, and the results showed the compressive property and failure mode of 3D-TRSSC were improved compared with 2D-TRSSC and SSC: the increase in compressive strength was 16.3% and 35.1%, respectively. In order to explain the improvement of the compressive strength of the 3D-TRSSC specimens, the triaxial self-stress state analysis of the compressive specimen was carried out, and then a set of calculation methods based on deformation analysis was designed to explain the upward displacement of the necking position of the TRSSC compressive specimen. The theoretical results and experimental data were 27.2 mm and 28–30 mm, respectively. In addition, the improvement of the compressive strength of the 3D-TRSSC specimens relative to that of the 2D-TRSSC specimen was predicted. The calculation results were highly consistent with the predicted values.

Correlation Analysis of Ultrasonic Pulse Velocity and Mechanical Properties of Normal Aggregate and Lightweight Aggregate Concretes in 30-60 MPa Range

This study classified the strength of normal aggregate concrete (NC) and lightweight aggregate concrete (LC) into three levels (30, 45, and 60 MPa). In particular, the compressive strength, ultrasonic pulse velocity, and elastic modulus were measured and analyzed at the ages of 1, 3, 7, and 28 days to establish the correlation between the compressive strength and the ultrasonic pulse velocity and between the elastic modulus and the ultrasonic pulse velocity. In addition, this study proposed strength and elastic modulus prediction equations as functions of the ultrasonic pulse velocity. The developed equations were compared with previously proposed strength prediction equations. The results showed that the measured mechanical properties of NC tended to be higher at all ages than in LC. However, LC45 exhibited relatively high compressive strength compared to NC45. The relative mechanical properties of LC compared to NC were the highest at 45 MPa and the lowest at 60 MPa. The relative ultrasonic pulse velocity converged at all levels as the age increased. Moreover, the correlation between the compressive strength and the ultrasonic pulse velocity in LC exceeded that of NC, and in LC, the correlation coefficient decreased as the strength increased. The correlation coefficients between the elastic modulus and the ultrasonic pulse velocity were high at all levels except for LC45. Finally, this study proposed compressive strength and elastic modulus prediction equations as an exponential function of LC. The proposed equations outperformed the previously proposed strength prediction equations.

Introducing Fractal Dimension for Interlaminar Shear and Tensile Strength Assessment of Mechanically Interlocked Polymer-Metal Interfaces

The interlaminar strength of mechanically interlocked polymer–metal interfaces is strongly dependent on the surface structure of the metal component. Therefore, this contribution assesses the suitability of the fractal dimension for quantification of the surface structure, as well as interlaminar strength prediction of aluminum/polyamide 6 polymer–metal hybrids. Seven different surface structures, manufactured by mechanical blasting, combined mechanical blasting and etching, thermal spraying, and laser ablation, are investigated. The experiments are carried out on a butt-bonded hollow cylinder testing method that allows shear and tensile strength determination with one specific specimen geometry. The fractal dimension of the metal surfaces is derived from cross-sectional images. For comparison, the surface roughness slope is determined and related to the interlaminar strength. Finally, a fracture analysis is conducted. For the investigated material combination, the experimental results indicate that the fractal dimension is an appropriate measure for predicting the interlaminar strength.

Influence of Reinforcement Bars on Concrete Pore Structure and Compressive Strength

In this research, the influence of reinforcement bars on concrete pore structure and compressive strength was experimentally investigated. Concrete samples with two mixture ratios and nine reinforcement ratios were provided. Tests were conducted on concrete pore structure and compressive strength at three ages (3 d, 7 d, and 28 d). It was found that reinforcement bars changed the concrete pore structure. In terms of size, the pore structure of concrete increased with the increase of reinforcement ratio. At the same age, concrete compressive strength in reinforced concrete specimens saw a gradual reduction when reinforcement ratio increased. A formula was proposed to calculate the compressive strength of concrete in reinforced specimens according to the strength of unreinforced concrete.

Microwave Non-Destructive Inspection and Prediction of Modulus of Rupture and Modulus of Elasticity of Engineered Cementitious Composites (ECCs) Using Dual-Frequency Correlation

This research article presents dual-frequency correlation models for predicting the growth of elasticity and flexural strength of engineered cementitious composites (ECCs) using microwave nondestructive inspection technique. Parallel measurements of microwave properties and mechanical properties of ECC specimens were firstly undertaken in the sense of cross-disciplinary experiments. Regression models were developed via means of nonlinear regression to the measured data. The purpose of the study is: (i) to monitor the flexural strength and elasticity growth; and (ii) to predict their mature values under the influence of different initial water contents, via microwave effective conductance at early ages. It has been demonstrated that both the modulus of rupture (MOR) and modulus of elasticity (MOE) can be accurately modeled and correlated by microwave conductance using exponential functions. The moduli developed as a function of conductance whereas the regression coefficient exhibited a linear relation with water-to-binder ratio. These findings have highlighted the effectiveness of the microwave non-destructive technique in inspecting the variation of liquid phase morphology of ECCs. The dual-frequency correlation can be used for structural health monitoring, which is not only for prediction but also provides a means of verification.

Inter-Investigator Reliability of Anthropometric Prediction of 1RM Bench Press in College Football Players

The purpose of this study was to determine the effect of inter-investigator differences in anthropometric assessments on the prediction of one-repetition maximum (1RM) bench press in college football players. Division-II players (n = 34, age = 20.4 ± 1.2 y, 182.3 ± 6.6 cm, 99.1 ± 18.4 kg) were measured for selected anthropometric variables and 1RM bench press at the conclusion of a heavy resistance training program. Triceps, subscapular, and abdominal skinfolds were measured in triplicate by three investigators and used to estimate %fat. Arm circumference was measured around a flexed biceps muscle and was corrected for triceps skinfold to estimate muscle cross-sectional area (CSA). Chest circumference was measured at mid-expiration. Significant differences among the testers were evident in six of the nine anthropometric variables, with the least experienced tester being significantly different from the other testers on seven variables, although average differences among investigators ranged from 1-2% for circumferences to 4-9% for skinfolds. The two more experienced testers were significantly different on only one variable. Overall agreement among testers was high (ICC>0.895) for each variable, with low coefficients of variation (CV<10.7%). Predicted 1RMs for testers (126.9 ± 20.6, 123.4 ± 22.0, and 132.1 ± 28.4 kg, respectively) were not significantly different from actual 1RM (129.2 ± 20.6 kg). Individuals with varying levels of experience appear to have an acceptable level of ability to estimate 1RM bench press using a non-performance anthropometric equation. Minimal experience in anthropometry may not impede strength and conditioning specialists from accurately estimating 1RM bench press.