Strength Prediction Model Research Articles

Strength characteristics and mix design of full-depth reclamation of asphalt pavement with cement

The research presents the strength characteristics and theoretical mix design of full-depth reclamation (FDR) with cement for road maintenance and rehabilitation. The reclaimed aggregates used in the study were pulverized and blended on the investigation site by the recycler machine. The FDR mix design covered the reclaimed asphalt pavement (RAP), reclaimed base, and reclaimed subbase courses. The unconfined compressive strength (UCS) was tested on the FDR with cement under different mix proportions, cement content, moisture content, and curing time. Two factors that affect the UCS of FDR, viz., moisture-induced packing density and moisture for cement hydration, were observed. The mix proportion with 40 % RAP required at least 6 % cement to stabilize the FDR for use as a bound base course as per the standard, while the effective limit of cement content for FDR was 9 %. The strength prediction model of FDR with cement was presented theoretically based on the modified soil-moisture/cement ratio concept. The verification of the proposed strength model was performed using 7 and 28-day UCS from another investigation site. The design recommendations for FDR with cement were summarized. This discovery could offer a cost-effective and precise method for the mix design of FDR with cement.

Effect of multiple environmental conditions on the formation process and adhesion strength of ice on asphalt binder surface

Road icing caused by freezing rain significantly impacts driving safety. Since asphalt binder plays a pivotal role in pavement infrastructure, understanding the formation process and adhesion strength of ice on asphalt binder surfaces is crucial for assessing road icing risk. This work investigated the effect of different environmental conditions on asphalt-ice interface adhesion strength via a self-designed low-temperature adhesion testing system. In addition, the icing process on asphalt binder surfaces was observed to analyze the asphalt-ice adhesion strength formation mechanism. Results show that the completion time of water-ice phase transition signified the initial development of asphalt-ice adhesion strength. Moreover, as the internal structure of the ice evolved from transparent to needle-like fine lines to dense, the asphalt-ice adhesion strength gradually increased until it reached stability. At asphalt-ice adhesion began forming after 40 min and stabilized after 80 min, whereas at −8°C, adhesion strength started forming after 20 min and stabilized by 60 min. The growth rates of asphalt-ice adhesion strength for temperatures ranging from −2°C to −10°C were approximately 7.92 kPa/°C, 6.56 kPa/°C, 5.14 kPa/°C, 3.29 kPa/°C, and 1.49 kPa/°C, respectively, showing a positive correlation with temperature and a negative correlation with time. According to heterogeneous nucleation theory, the influence mechanism of temperature and water depth on the nucleation icing process and asphalt-ice adhesion strength is analyzed. lower temperatures lead to asphalt-ice adhesion strength increase originating from the larger supercooling, which reduces the critical nucleation energy and thus accelerates the ice nucleation rate. In addition, the increase in water depth promotes the formation of nucleation sites and further enhances the asphalt-ice adhesion strength. Finally, an asphalt-ice adhesion strength prediction model was developed, with PSO-SVM-G achieving over 90 % accuracy. These results provide insights for evaluating ice adhesion behavior on asphalt surfaces and designing anti-icing asphalt materials.

Concrete Compressive Strength Prediction by Ensemble Machine Learning Approach

The prediction of concrete compressive strength is a crucial aspect of ensuring the structural integrity and durability of construction projects. In recent years, machine learning approaches have improved upon the limitations of empirical formulas and laboratory testing methods for predicting concrete compressive strength. This study utilizes ensemble machine-learning techniques, such as Bagging, XGBoost, and Stacking models, to enhance the accuracy of concrete compressive strength prediction models. A five-fold cross-validation technique was applied to mitigate the problems of underfitting or overfitting in the regression model. Furthermore, various statistical indices were employed to compare the forecasting performance of these ensemble techniques. The prediction performance of this research revealed that XGBoost achieved the highest R-squared value of 93%, followed by Stacking and Bagging regression models at 92%. Consequently, this research underscores the potential of ensemble techniques as valuable tools in the domain of civil engineering, paving the way for more reliable and efficient construction practices.

Flaw characteristics of architectural glass and long-term strength prediction model

Flaw characteristics of architectural glass and long-term strength prediction model

23‐4: Research on LCD Strength Improvement Based on Neural Networks Algorithm

Aiming at the display fragmentation caused by insufficient module strength of ultra-thin and narrow design, a module strength prediction model is proposed to improve LCDs strength immunity and provide design guide, The comparison between the experiment measurement and the predicted results shows that the model can accurately predict the module strength under different design conditions and provide effective technical support and guidance.

MsBERT-Promoter: a multi-scale ensemble predictor based on BERT pre-trained model for the two-stage prediction of DNA promoters and their strengths

BackgroundA promoter is a specific sequence in DNA that has transcriptional regulatory functions, playing a role in initiating gene expression. Identifying promoters and their strengths can provide valuable information related to human diseases. In recent years, computational methods have gained prominence as an effective means for identifying promoter, offering a more efficient alternative to labor-intensive biological approaches.ResultsIn this study, a two-stage integrated predictor called “msBERT-Promoter” is proposed for identifying promoters and predicting their strengths. The model incorporates multi-scale sequence information through a tokenization strategy and fine-tunes the DNABERT model. Soft voting is then used to fuse the multi-scale information, effectively addressing the issue of insufficient DNA sequence information extraction in traditional models. To the best of our knowledge, this is the first time an integrated approach has been used in the DNABERT model for promoter identification and strength prediction. Our model achieves accuracy rates of 96.2% for promoter identification and 79.8% for promoter strength prediction, significantly outperforming existing methods. Furthermore, through attention mechanism analysis, we demonstrate that our model can effectively combine local and global sequence information, enhancing its interpretability.ConclusionsmsBERT-Promoter provides an effective tool that successfully captures sequence-related attributes of DNA promoters and can accurately identify promoters and predict their strengths. This work paves a new path for the application of artificial intelligence in traditional biology.

Proposing an inherently interpretable machine learning model for shear strength prediction of reinforced concrete beams with stirrups

Advanced machine learning (ML) models are utilized for accurate shear strength prediction of reinforced concrete beams (RCB), but their lack of interpretability makes it unclear how models make specific predictions, reducing their reliability and applicability. Mainstream model-agnostic interpretation methods require numerous additional computing procedures, limiting the interpretation efficiency, and the model prediction process remains unknown. This study proposes an inherently interpretable shear strength prediction model for RCB with stirrups based on Explainable Boosting Machine (EBM) and Bayesian optimization. The EBM algorithm decomposes the predicted shear strength into individual shape functions, thus thoroughly revealing the prediction process. Besides, the ML tasks of selecting a model with optimal hyperparameters are automatically performed by Bayesian optimization to reduce computational cost. The developed model is validated on a database including 372 specimens. Compared with shear design codes, empirical models and prominent ML models, the EBM model obtains most accurate predictions for the test set with R2, MAE, and RMSE of 0.9293, 35.42 kN, and 50.99 kN, respectively. The accuracy of EBM is robust to varying input variables through trend analysis. Its interpretability fully discloses the contribution of individual features to the shear strength, and the model rationality is verified by comparing feature contribution with existing mechanisms. The proposed EBM model achieves inherently interpretable shear strength predictions while maintaining high accuracy, which promotes the model applicability in structural assessment.

Prediction of compressive strength of cross‐shaped stub CFSTs under axial loading: Numerical and analytical study

AbstractSpecial‐shaped concrete‐filled steel tubes (CFSTs) have been used in modern structures like high‐rise commercial and residential buildings due to their superior structural performance compared to steel and reinforced concrete members. Various shapes of special‐shaped CFSTs might be necessary to meet architectural and aesthetic needs. Cross‐shaped CFSTs could be used where two orthogonal walls cross in high‐rise buildings. However, at present, the research on the compressive performance of cross‐shaped CFSTs is limited, consequently, the unavailability of design guidelines and design‐oriented strength prediction models. Therefore, in this study, a finite element (FE) model of cross‐shaped CFSTs was developed following the past experimental data, and the model's accuracy was verified by the failure modes and load–strain curves of specimens. Sensitivity analysis was performed for some parameters of the concrete damaged plasticity model besides imperfections and residual stress. The parametric analysis was conducted considering various study parameters such as the width‐to‐thickness ratio, width‐to‐depth ratio, and steel and concrete strengths. The compressive strength of cross‐shaped CFSTs was predicted by different design codes and available design formulas, which gave unsatisfactory results necessitating the development of new strength prediction models. Finally, a new design formula was developed by performing a linear regression of FE and test results. The proposed formula predicted the strength of cross‐shaped CFSTs with great accuracy and can be used for design purposes.

Machine learning guided iterative mix design of geopolymer concrete

Current mix design methods for Geopolymer concrete (GPC) require substantial efforts of trial-and-error experiments and is applicable only to those formulated by specific precursor materials. In this work, a machine learning (ML) guided mix design method for GPC is proposed, which can considerably reduce the experimental workload and be versatile with a broad range of precursor materials. First, a database for the slump and compressive strength of GPC was established, and ML prediction models were developed with these as objectives. Subsequently, the mix design for GPC was conducted using the particle swarm optimization (PSO) algorithm. The designed mixture proportions underwent experimental validation, and if targets were not met, results were then used for model iteration until desired performance targets were achieved. The results showcase the excellent performance of the established slump and compressive strength prediction models, with an accuracy and coefficient of determination of 94 % and 0.95, respectively. The developed ML guided model effectively generates concrete mix achieving compressive strengths of 20 MPa, 40 MPa, and 60 MPa, while concurrently satisfying slump requirements. The experimentally validated results for the three designated target strengths after iterations were 25.2 MPa, 43.8 MPa, and 66.6 MPa, respectively. These positive results emphasize the ability of the proposed optimized mix design method to meet both the strength and workability targets in GPC via a minimum number of trail experiments.

Experimental research and theoretical prediction on mechanical properties for recycled GFRP fiber reinforced concrete

Recycled GFRP fiber has increasingly been reused in concrete, necessitating an improvement in its recycling process and an investigation into its effects on the mechanical properties of concrete to achieve higher recycling values. To this end, this study proposed a novel GFRP recycling method that integrates mechanical recycling, water-vibratory separation, and secondary sieving to efficiently remove impurities from GFRP waste. Three different sizes of recycled GFRP fibers (SF, MF, and LF) were sorted from decommissioned GFRP wind turbine blades using the novel recycling method, and their effects of on the mechanical properties of concrete were investigated. The results show that all three types of recycled GFRP fibers increase the strength and toughness of concrete. With equivalent fiber content, the largest recycled GFRP fiber (LF) yields the most substantial reinforcement effect on the mechanical properties of concrete. Specifically, incorporating 1.0 % LF increases the compressive strength, splitting tensile strength, and flexural strength of concrete by 14.0 %, 16.8 %, and 37.0 %, respectively, while also increasing flexural toughness by 2.9 times. In addition, the mechanical properties of recycled GFRP fiber reinforced concrete were theoretically analyzed in this study, and two strength prediction models for recycled GFRP fiber reinforced concrete were established to achieve rapid prediction of concrete strength.

A model predicting mechanical properties of asphalt mixtures considering void ratio and loading conditions

The void ratio is an essential parameter in asphalt mixture design, which significantly affects asphalt mixtures' mechanical properties and road performance. The prediction model for mechanical properties will be established based on the Computed tomography (CT) scanning, strength, and fatigue test results in this research to reveal the relationship between the asphalt mixtures' mechanical properties and void ratio. Firstly, the voids' transverse and longitudinal distribution characteristics in asphalt mixtures of different gradations were investigated based on CT scanning. Then, the influences of void ratio, loading rates on the strength, and the impacts of void ratio and stress levels on the fatigue life were investigated by conducting indirect tensile tests. Finally, the mechanical properties prediction model was established for void ratio and loading conditions. Further, the feasibility of the model is verified in conjunction with existing research results. The results show that the void ratio calculated based on CT scanning is about 1.15 times the measured void ratio in the water weight method. The number of voids was uniformly distributed in the range of 15 mm∼50 mm in height and 10 mm∼40 mm in radius of the specimen. The asphalt mixtures' strength decreases with increasing void ratio and increases with increasing loading rate. The asphalt mixtures' fatigue life declines with increasing void ratio and stress level. The correlation coefficients of the established strength and fatigue prediction models were 0.963 and 0.976, respectively. The relative error between the measured strength, fatigue life, and predicted results is about 10.75% and 11.27%, respectively. This research provides a basis for designing high-performance asphalt mixtures by establishing the relationship between asphalt mixtures' microscopic and mechanical characteristics.

Cold spray processing of AA2024/Al2O3 coating on magnesium AZ31B alloy: Process parameters optimization, microstructure and adhesive strength performance of coating

The automotive and aerospace sectors are progressively employing the magnesium (Mg) alloy of the grade AZ31B because of its excellent castability, low density, and high ratio of strength to weight. Nevertheless, the limited ability of AZ31B alloy to withstand corrosion limits their use in several fields of technology. In order to solve this problem, the AZ31B alloy is coated utilizing an AA2024/Al2O3 metal matrix composite (MMC) coating that is applied by the cold spray coating (CS) method. The primary goal of this work is the parametric optimization of CS process for maximizing adhesive strength of MMC-coated Mg-alloy substrate. Response surface methodology (RSM) is implemented to find the optimum CS parameters, including feed rate of powder – FRP (g/min), standoff distance of gun – SDG (mm) and processing temperature – TEMP (°C). The regression-based parametric adhesion strength prediction (ASP) model was formulated using the RSM and statistically validated using analysis of variance (ANOVA). Employing 3D surface of responses, the influence of CS parameters on the adhesion strength of an MMC-coating was assessed. The findings revealed that when the MMC-coating was cold sprayed on the Mg-alloy using FRP of 22 g/min, SDG of 12 mm, and TEMP of 520 °C, the maximum adhesion strength of MMC-coating was 70 MPa (actual). Given less than 2% error at 95% confidence, the parametric ASP model correctly predicted the adhesion strength of the MMC-coating. The ANOVA findings showed that FRP (g/min) had significant effect on adhesive strength of MMC-coating followed by SDG (mm) and TEMP (°C). The MMC-coating applied using the RSM optimized CS parameters showed 70.73% superior adhesive strength owing to the lower porosity formation of 2 vol% which offers greater interfacial area. The ASP equation was formulated using the “best fitting line” approach and validated using ANOVA for predicting the adhesive strength (MPa) from the porosity formation (vol%) in the MMC-coating.

Evolutionary Algorithms for Strength Prediction of Geopolymer Concrete

Geopolymer concrete (GPC) serves as a sustainable substitute for conventional concrete by employing alternative cementitious materials such as fly ash (FA) instead of ordinary Portland cement (OPC), contributing to environmental and durability benefits. To increase the rate of utilization of FA in the construction industry, distinctive characteristics of two machine learning (ML) methods, namely, gene expression programming (GEP) and multi-expression programming (MEP), were utilized in this study to propose precise prediction models for the compressive strength and split tensile strength of GPC comprising FA as a binder. A comprehensive database was collated, which comprised 301 compressive strength and 96 split tensile strength results. Seven distinct input variables were employed for the modeling purpose, i.e., FA, sodium hydroxide, sodium silicate, water, superplasticizer, and fine and coarse aggregates contents. The performance of the developed models was assessed via numerous statistical metrics and absolute error plots. In addition, a parametric analysis of the finalized models was performed to validate the prediction ability and accuracy of the finalized models. The GEP-based prediction models exhibited better performance, accuracy, and generalization capability compared with the MEP-based models in this study. The GEP-based models demonstrated higher correlation coefficients (R) for predicting the compressive and split tensile strengths, with the values of 0.89 and 0.87, respectively, compared with the MEP-based models, which yielded the R values of 0.76 and 0.73, respectively. The mean absolute errors for the GEP- and MEP-based models for predicting the compressive strength were 5.09 MPa and 6.78 MPa, respectively, while those for the split tensile strengths were 0.42 MPa and 0.51 MPa, respectively. The finalized models offered simple mathematical formulations using the GEP and Python code-based formulations from MEP for predicting the compressive and tensile strengths of GPC. The developed models indicated practical application potential in optimizing geopolymer mix designs. This research work contributes to the ongoing efforts in advancing ML applications in the construction industry, highlighting the importance of sustainable materials for the future.

The strength prediction model of unidirectional fiber reinforced composites based on the renormalization group method

When unidirectional fiber reinforced composites are subjected to longitudinal tensile loading and reach a critical failure state, they experience a sudden transition from local damage to catastrophic failure, commonly termed as an avalanche event. This paper integrates the self-organized criticality theory (SOC) concepts into the prediction of longitudinal tensile strength of composites and establishes a strength prediction model of composites based on the renormalization group method (RGM). The predictions of the RGM model are successfully validated against experimental results in the literatures, and it demonstrates relatively acceptable predictive accuracy compared to classical strength criteria. Compared to other state-of-the-art prediction models considering stochastic fiber strength distribution, the RGM model effectively provides strength statistics for fiber bundles of any size and describes the occurrence of composites avalanche failure induced by local stress concentration. This present model can be very conveniently implemented as a User Material Subroutine (UMAT) for finite simulations, facilitating practical prediction of the strength of composites structures.

Bond performance of recycled coarse aggregate concrete with rebar under freeze–thaw environment: A review

Abstract In this article, a review focusing on the frost resistance of recycled coarse aggregate concrete (RAC) and the bond performance of RAC with rebar under freeze–thaw environment is carried out. The results show that there are still some controversies about the advantages and disadvantages of the frost resistance of RAC, and many influencing factors have not been considered. The mass of the RAC pullout specimens shows a trend of first increasing and then decreasing after freeze‒thaw cycles. The failure modes of the RAC pullout specimens after freeze‒thaw cycles include pullout failure, pullout-splitting failure, splitting failure, and rebar yielding failure. The bond performance of RAC with rebar shows a degradation trend after freeze‒thaw cycles, mainly in the decrease in bond strength and the increase in bond slip. The bond performance of RAC specimens is inferior to that of natural aggregate concrete specimens after freeze‒thaw cycles. The bond strength prediction models and the bond–slip constitutive relation prediction models of RAC with rebar after freeze‒thaw cycles have been summarized to ensure that engineers can better understand their applicability. The bond stress distribution between the RAC and rebar in the anchoring area is not uniform and constantly changes with the number of freeze‒thaw cycles. The degradation mechanism of the bond performance of RAC with rebar after freeze‒thaw cycles is analyzed.

Artificial intelligence-based prediction models of bio-treated sand strength for sustainable and green infrastructure applications

As a sustainable, environmentally friendly, and green solution, biomineralization/bio-treatment process has recently emerged for enhancing the strength characteristics of loose sands by inducing cementation material commonly referred to as microbially induced calcite/cementation precipitation (MICP). To date, existing research on the unconfined compression strength of MICP-treated sands (UCSmicp) relies heavily on experimental data, with predictions primarily based on linear or curvilinear models that consider calcite (CaCO3) as the main influencing factor. However, there is limited exploration into the application of artificial intelligence (AI) and machine learning (ML) methods for UCSmicp prediction involving multiple influencing factors and their validation on unseen laboratory data. Therefore, this study intends to propose new prediction models of UCSmicp using four advanced ML techniques: Gaussian Process Regression (GPR), Adaptive Neuro Fuzzy Inference System (ANFIS), Artificial Neural Network (ANN), and Gene Expression Programming (GEP). The models incorporate various factors affecting UCSmicp, including sand uniformity coefficient (Cu), initial void ratio (e), mean grain size (D50), optical density at 600 mm wavelength (OD600), urea concentration (U), calcium concentration (Ca), and calcite content (C). Performance evaluation of models involved statistical assessments, error analysis, cross validation on laboratory data, and sensitivity and monotonicity studies. Results indicate that the proposed models exhibit exceptional precision across training, testing, and validation data in predicting UCSmicp, with ANN demonstrating the highest accuracy, followed by GPR, ANFIS, and GEP. Sensitivity analysis identifies CaCO3 as the main influencing factor on UCSmicp, while monotonicity analysis confirms alignment with physical processes. This work advocates for MICP as an eco-friendly solution and highlights the efficacy of advanced ML techniques in fostering sustainable infrastructure.

An improved tensile strength and failure mode prediction model of FDM 3D printing PLA material: Theoretical and experimental investigations

3D-printed polylactic acid (PLA) is being increasingly used in practical engineering. In the past, a certain number of models were developed to describe the tensile strength of PLA specimens. However, two opposite tensile strength variation trends with raster angle varying were observed in previous experiments, which cannot be reasonably explained by the current tensile strength models. To resolve this issue, an improved tensile strength and failure mode prediction model is proposed based on the assumption of transversely isotropic material. Corresponding experiments of PLA specimens have also been performed to validate the accuracy of the proposed model. It has been demonstrated that this model could accurately predict the tensile strength and failure mode of 3D printing PLA material. In addition, the opposite strength trends mentioned above with raster variation could also be perfectly explained using the improved prediction model.

Grey modeling study on mechanical properties and pore structure of concrete with different basalt fiber contents based on NMR

This paper investigates the correlation between strength and pore characteristics of basalt fiber-reinforced concrete (BFRC) with different fiber contents and establishes a link between meso- and macro-properties. The research focuses on BFRC with differing fiber contents, analyzing compressive strength, flexural strength, and splitting tensile strength across eight admixture levels (ranging from 0 % to 0.35 %). Using the nuclear magnetic resonance (NMR) technique, T2 spectra of BFRC with varying fiber contents are obtained, deriving curves of the pore distribution. Additionally, considering the parameters of different pore size proportions, the paper delves into analyzing the impact of pore structure on BFRC's distinct mechanical properties using grey correlation. Utilizing the optimal pore structure parameters derived from GCA to forecast different strengths, this study establishes GM(1,3) prediction models for three strengths, respectively. The results showed that basalt fibers can enhance concrete strength. And, 0.25 % basalt fibers optimize concrete's the inner structure of BFRC by decreasing harmful pores. The comprehensive correlation between pore parameters and BFRC strength ranges significantly indicating a notable relationship between strength and pore alterations. The compressive strength was most related to the total porosity and the proportion of non-harmful pores, and the splitting tensile and flexural strengths were related to the fractal dimension and porosity of the harmful pores as well as to the total and non-harmful porosity, respectively. A BFRC strength prediction model formula was developed based on the most relevant pore structure parameters derived from GCA. This calculation formula showcases a high accuracy in predicting BFRC strength, establishing a mesoscopic-to-macroscopic quantitative relationship that effectively informs the production and application of BFRC.

The Difference in Shear Behavior and Strength between Loess and Paleosol and Their Prediction of Unsaturated Strength

In recent decades, loess landslide events have attracted increasing attention in the South Jingyang tableland. To elucidate the mechanical mechanism of landslide initiation in the region, this work collected undisturbed loess and paleosol samples taking from the Q2 strata in the South Jingyang tableland. A range of direct shear tests were carried out to explore the strength evolution law of shear zone soil subjected to a varying initial moisture content. In addition, soil water characteristic curves (SWCCs) were also charted and used for predicting the unsaturated shear strength. The findings show that the basic physical properties of the paleosol are different from those of loess due to their different pedogenic environments. The normal stress level and initial moisture content jointly determine whether the shear behavior is strain hardening or strain softening. The shear strength and strength parameters evidently diminish with an increasing initial moisture content, and cohesion contributes to the vast majority of strength attenuation. Paleosol samples possess higher values in shear strength and strength parameters than loess samples due to their stronger inter-particle cementation. The predictive formulas of unsaturated shear strength for undisturbed loess and paleosol are proposed, respectively, based on the Vanapalli model, and the calculated values of the strength prediction model are in perfect agreement with the experimental values.

A comparative study of ensemble machine learning models for compressive strength prediction in recycled aggregate concrete and parametric analysis

A comparative study of ensemble machine learning models for compressive strength prediction in recycled aggregate concrete and parametric analysis