Accurate Strength Predictions Research Articles

Kriging-based surrogate data-enriching artificial neural network prediction of strength and permeability of permeable cement-stabilized base

Limited test data hinder the accurate prediction of mechanical strength and permeability of permeable cement-stabilized base materials (PCBM). Here we show a kriging-based surrogate model assisted artificial neural network (KS-ANN) framework that integrates laboratory testing, mathematical modeling, and machine learning. A statistical distribution model was established from limited test data to enrich the dataset through the combination of markov chain monte carlo simulation and kriging-based surrogate modeling. Subsequently, an artificial neural network (ANN) model was trained using the enriched dataset. The results demonstrate that the well-trained KS-ANN model effectively captures the actual data distribution characteristics. The accurate prediction of the mechanical strength and permeability of PCBM under the constraint of limited data validates the effectiveness of the proposed framework. As compared to traditional ANN models, the KS-ANN model improves the prediction accuracy of PCBM’s mechanical strength by 21%. Based on the accurate prediction of PCBM’s mechanical strength and permeability by the KS-ANN model, an optimization function was developed to determine the optimal cement content and compaction force range of PCBM, enabling it to concurrently satisfy the requirements of mechanical strength and permeability. This study provides a cost-effective and rapid solution for evaluating the performance and optimizing the design of PCBM and similar materials.

Joint shear strength prediction for fiber reinforced concrete beam-to-column connections

Beam-to-column joints experience substantial shear forces and deformations, playing a pivotal role in maintaining the overall stability and integrity of moment-resisting frames under earthquake loading. If fiber reinforced concrete is used instead of reinforced concrete, beam flexural failure can be achieved, which leads to a ductile behavior and increased energy dissipation capacity, when compared to joint shear failure. To ensure a ductile failure mode, accurate prediction of the joint shear strength is essential. However, there are only a limited number of analytical studies on predicting the shear strength of fiber reinforced concrete joints, most of which are only applicable to steel fibers. In this study, a comprehensive database of prior experiments conducted on fiber reinforced concrete beam-to-column connection subassemblies is compiled. Based on Pearson Correlation Analyses, the factors influencing the seismic response are determined to be the composite tensile cracking strength, axial load on the column, aspect ratios of member dimensions, and specific fiber properties such as aspect ratio and volume fraction. A joint shear strength prediction equation is then developed utilizing statistical nonlinear regression method. Validation against experimental data confirms that the proposed equation provides conservative estimates of joint shear strength and can be utilized for composites with any fiber type, even hybrid fibers; in contrast to existing equations which often lead to overestimation of strength and restricted to a specific fiber type. Moreover, the proposed equation provides engineers a practical tool to assess the seismic behavior of such connections, which has not been addressed by current structural design codes yet. The improved accuracy of the proposed equation, demonstrated by the lowest mean absolute error and coefficient of variation and the highest coefficient of correlation, positions it as a promising candidate for integration into structural design codes.

SPATIAL PREDICTION OF RECEIVED SIGNAL STRENGTH FOR CELLULAR COMMUNICATION USING SUPPORT VECTOR MACHINE AND K-NEAREST NEIGHBOURS REGRESSION

Abstract. Signal strength maps are of great importance for cellular system providers in network planning and operation. Accurate prediction of signal strength is important for solving problems such as link quality. In this study, Received Signal Strength (RSS) prediction model is proposed for the 900 MHz band in the Van Yüzüncü Yıl University campus environment by using machine learning regression methods such as K- Nearest Neıghbours (KNN) and Support Vector Regression (SVR) together with Geographic Information Systems. For the training of this model, signal strength values taken from the RF Spectrum Analyser at different locations and distances were used. In addition, spatial data sets such as the digital elevation model, location of base stations and measurement stations, building heights and location, and land use/cover were used in the model. The effect of these data sets on RSS power is included in the model. The model aims to predict RSS accurately, visualize the estimated signal strength, and analyze the signal field strength coverage. Different kernels from the SVR model such as Polynomial, , and Sigmoid were tested. To increase the success of the model, appropriate parameter values were selected and configured according to SVR and KNN methods. For 900 MHz, the performances of SVR and KNN models were compared and the results of the models were verified using root mean squares (RMSE). Among the measured data, the lowest prediction is found in KNN Manhattan. According to the results of the simulation was observed that the SVR model created with spatial data performs better for Signal Strength. Finally, the lowest RMSE value (1.71 dB) was obtained from the Sigmoid kernel in the best signal strength estimation SVR model. The SVR model is recommended for Campus Area signal strength estimation.

Analytical Modeling of Unsaturated Soil Shear Strength during Water Infiltration for Different Initial Void Ratios

Unsaturated soil mechanics, when applied to determine the soil shear strength, are crucial for accurately evaluating the safety of geotechnical structures affected by seasonal moisture variations. Over the past decades, multiple models have been formulated to predict the behavior of unsaturated soils in terms of water flow and shear strength individually. Building upon these foundational studies, this research introduces a model that couples an analytical solution for one-dimensional water infiltration with an unsaturated shear strength model. This model further incorporates the impact of void ratio fluctuations on soil properties and state variables related to shear strength. A parametric analysis is conducted to evaluate the effects of the initial void ratio on a representative soil profile during a water infiltration event. The model presented in this paper integrates various concepts from the field of unsaturated soil mechanics and is applicable to any homogeneous soil where expansion/collapse effects are negligible. It demonstrates how shear strength might be underestimated when using a saturated soil approach. Conversely, it may also lead to an overestimation of safety conditions if the soil approaches a saturated or dry state. The proposed model offers a more accurate prediction of unsaturated soil shear strength. It is useful for determining transient safety factors in geotechnical structures. Furthermore, when combined with field-installed instrument monitoring, this model contributes significantly to the functionality, safety, cost-effectiveness, and sustainability of geotechnical structures and projects.

Data-driven shear strength prediction of steel reinforced concrete composite shear wall

Due to composition of concrete and steel materials, steel reinforced concrete composite shear wall (SRCCSW) plays a pivotal role as the primary lateral load-resisting component in buildings. Accurate prediction of shear strength is crucial, but numerous complex factors affect the shear strength, including shear-span ratio, axial load ratio, and materials properties. Therefore, it is imperative and urgent to develop precise prediction model. In this paper, machine learning (ML) models for predicting the shear strength of SRCCSW are developed. Firstly, a comprehensive database is established by collecting experimental data of 149 SRCCSW. Twelve predictive models are proposed, evaluated, and compared, including linear regression, decision tree, K-nearest neighbors, support vector regression, random forest, gradient boosting, adaptive boosting, categorical boosting, extreme gradient boosting (XGB), light gradient boosting machine, histogram-based gradient boosting, and artificial neural network. Then, six existing empirical models are further evaluated and compared. Finally, SHapley Additive exPlanations (SHAP) is employed to comprehensively explore the global explanation, individual explanation, and feature dependency of XGB model. The results show that the LR model is not as effective as that of other ML models, and the predictive performances of other ML models are generally comparable. The XGB model outperforms the best empirical model with a correlation coefficient of 0.99 (vs. 0.80) and a standard deviation of 520 kN (vs. 491 kN), while the experimental results have a standard deviation of 516 kN. Compared to other models, the XGB model possesses superior predictive accuracy and smallest dispersion. Wall height and shear-span ratio are the most two critical variables influencing the shear strength. At the individual level, the model’s prediction may depend only on certain features rather than having complex dependencies on all features. For the same feature, SHAP values may vary significantly due to the influence of other features. These results provided by SHAP reveal the detailed insights into the comprehensive impact of features on the shear strength of SRCCSW.

Strength properties prediction of RCA concrete via hybrid regression framework

High-performance concrete (HPC) is commonly utilized in the construction industry because of its strength and durability. The mechanical properties of HPC, specifically its compressive and tensile strength, are crucial indicators. Accurate prediction of concrete strength is crucial for optimizing the design as well as the performance of concrete structures. In this investigation, a novel approach for strength prediction of HPC is proposed, employing the Support Vector Regression (SVR) algorithm in conjunction with three optimizers: the Slime Mold Algorithm (SMA), Adaptive Opposition Slime Mold Algorithm (AOSM), and Equilibrium Slime Mold Algorithm (ESMA). The SVR algorithm is a robust machine-learning technique that has displayed promising results in various prediction tasks. The utilization of SVR allows for the effective modeling and prediction of the complex relationship between the strength properties of HPC and the influencing factors. To achieve this, a dataset comprising 344 samples of high-performance concrete was collected and utilized to train and assess the SVR algorithm. However, the choice of suitable optimization algorithms becomes crucial to enhance prediction accuracy and convergence speed. Through extensive experimentation and comparative analysis, the proposed framework’s performance is evaluated using real-world HPC strength data. The results demonstrate that combining SVR with AOSM, ESMA, and SMA outperforms traditional prediction accuracy and convergence speed optimization methods. The suggested framework provides an effective and reliable solution for accurately predicting the compressive strength (CS) of HPC, enabling engineers and researchers to optimize the design and construction processes of HPC structures.

Exploring the resilience of supplementary cementitious materials-based concrete to elevated temperatures via modern computing techniques

Researchers are focused on the production of sustainable materials in order to reduce the negative environmental impact of conventional concrete. Utilizing industrial by-products as alternative cementitious materials in concrete is an appropriate strategy for promoting sustainability in construction. This research employed supervised machine learning techniques, including gradient boosting (GB), random forest (RF), and extreme gradient boosting (X-GB), in order to predict the compressive strength of sustainable concrete when exposed to high temperatures. SHapley Additive exPlanation (SHAP) analysis provided input component relevance. The comparison of these methodologies indicated that X-GB performed remarkably well and had a superior R2 value of 0.94 when compared to GB and RF. The results were further supported by a Taylor diagram, which demonstrated that the X-GB model best fitted the data, surpassing both the GB and RF models. This study's findings demonstrated the potential of machine learning, and more particularly X-GB, for making accurate predictions of compressive strength in high-temperature concrete applications. The results of SHAP analysis may be useful for selecting the proportions of raw materials in the mix design to achieve the desired properties.

A shear history model for capturing the liquefaction resistance of sands at various cyclic stress ratios

Various constitutive formulations have been developed over the years to reproduce the cyclic resistance of sands. A common challenge for existing models is the accurate simulation of the cyclic strength of sands for a wide range of initial conditions and different cyclic stress levels when adopting a single calibration. Many liquefaction models tend to overpredict the resistance of the soil under large-amplitude loading, while underestimating the strength at low-amplitude cyclic shearing. This manifests itself in slopes of simulated cyclic resistance ratio curves (CRR-curves) which are steeper than experimental studies indicate. This paper provides a discussion on the effects of large-amplitude and low-amplitude cyclic shearing on a granular material based on micromechanical and experimental investigations presented in the literature. A constitutive model with a shear-history threshold is proposed, which accounts for a shift of the apparent angle of phase transformation under cyclic loading. In addition, a novel expression for a deviatoric fabric tensor is introduced to describe the evolution of shear-induced fabric anisotropy while a soil is dilating and contracting. Combining these two features in one formulation within the bounding surface plasticity framework enables an accurate prediction of cyclic strength of sands under a wide range of cyclic stress ratios.

Optimized artificial neural network model for accurate prediction of compressive strength of normal and high strength concrete

This study develops and presents an Artificial Neural Network (ANN) model employing the Levenberg-Marquardt Backpropagation (LMBP) training algorithm to predict the compressive strength of both normal and high strength concrete. The model's robustness was evaluated using an extensive dataset comprising 1637 samples. Eight input variables, including the cement content, blast furnace slag, fly ash, fine aggregate, coarse aggregate, water content, superplasticizer, and testing age, were considered. The optimal number of hidden layers and neurons in the layer were identified through analysis, and the effectiveness of the model was assessed through k-fold cross-validation and statistical measures, including correlation coefficient (R), coefficient of determination (R2), Root Mean Square Error (RMSE), and Mean Absolute Error (MEA). Comparison with other models was carried out, and the perturbation/super-position method was employed for parametric studies to investigate the effect of each input variable on the output variable. The k-fold cross-validation confirmed the generalizability of the model, and statistical measures showed good results, with unit cement content and superplasticizers having the highest impact on compressive strength. The findings demonstrate that the suggested ANN model is an extremely precise, economical, and practical predictive tool for concrete compressive strength.

Experimental analysis on the mixed-mode fracture behavior of structural adhesives

The wide use of adhesive joints supposes that accurate strength predictions methods exist for design. Cohesive zone models (CZM) consist of the most accepted method, although the fracture toughness (GC) of the adhesive in the different loading modes should be firstly characterized, and the mixed-mode behavior or fracture envelope known. This work experimentally evaluates the cracked-lap shear (CLS) test for mixed-mode GC assessment of two epoxy adhesives. Different theoretical reduction methods were evaluated. The work consisted of testing CLS specimens with the different adhesives, and carrying out the respective data processing. Results showed that the model of Brussat et al. led to offset results compared to the other methods.

Unboxing machine learning models for concrete strength prediction using XAI

Concrete is a cost-effective construction material widely used in various building infrastructure projects. High-performance concrete, characterized by strength and durability, is crucial for structures that must withstand heavy loads and extreme weather conditions. Accurate prediction of concrete strength under different mixtures and loading conditions is essential for optimizing performance, reducing costs, and enhancing safety. Recent advancements in machine learning offer solutions to challenges in structural engineering, including concrete strength prediction. This paper evaluated the performance of eight popular machine learning models, encompassing regression methods such as Linear, Ridge, and LASSO, as well as tree-based models like Decision Trees, Random Forests, XGBoost, SVM, and ANN. The assessment was conducted using a standard dataset comprising 1030 concrete samples. Our experimental results demonstrated that ensemble learning techniques, notably XGBoost, outperformed other algorithms with an R-Square (R2) of 0.91 and a Root Mean Squared Error (RMSE) of 4.37. Additionally, we employed the SHAP (SHapley Additive exPlanations) technique to analyze the XGBoost model, providing civil engineers with insights to make informed decisions regarding concrete mix design and construction practices.

Explanatory Machine Learning Accelerates the Design of Graphene-Reinforced Aluminium Matrix Composites with Superior Performance

Addressing the exceptional properties of aluminium alloy composites reinforced with graphene, this study presents an interpretable machine learning approach to aid in the rapid and efficient design of such materials. Initially, data on these composites were gathered and optimised in order to create a dataset of composition/process-property. Several machine learning algorithms were used to train various models. The SHAP method was used to interpret and select the best performing model, which happened to be the CatBoost model. The model achieved accurate predictions of hardness and tensile strength, with coefficients of determination of 0.9597 and 0.9882, respectively, and average relative errors of 6.02% and 5.01%, respectively. The results obtained from the SHAP method unveiled the correlation between the composition, process and properties of aluminium alloy composites reinforced with graphene. By comparing the predicted and experimental data in this study, all machine learning models exhibited prediction errors within 10%, confirming their ability to generalise. This study offers valuable insights and support for designing high-performance aluminium matrix composites reinforced with graphene and showcases the implementation of machine learning in materials science.

Tests, numerical simulations and design of G550 high strength cold-formed steel lipped channel section columns failing by interactive buckling

This paper presents the experimental and numerical investigations into the structural performance and strengths of G550 high strength cold-formed steel (CFS) lipped channel section columns failing by interactive buckling. A testing program was first conducted, comprising material testing, measurements of initial local, distortional and global geometric imperfections and ten pin-ended column tests. The interaction between different buckling modes was observed and discussed for all the examined specimens upon testing. A numerical modeling program was subsequently performed, where numerical models were created and verified with reference to the test results and afterwards utilized to conduct parametric analysis to produce more numerical data over an extensive spectrum of cross-section geometries and effective member lengths. The effective width method (EWM) codified in the European code and direct strength method (DSM) specified in American and Australian standards were evaluated, based on the combined set of numerical and test data, for their suitability to G550 high strength CFS lipped channel section columns susceptible to interactive buckling. The evaluation results indicated that (i) the EWM yielded scattered and conservative ultimate strengths for columns with small and intermediate slenderness ratios, but relatively accurate results for those of large slenderness ratios and (ii) the DSM led to more consistent and accurate strength predictions for G550 high strength CFS lipped channel section columns failing by interactive buckling, though a number of strength predictions were on the unsafe side.

Confinement-based direct design method for fibre reinforced polymer confined CFST short columns

The paper presents a detailed analysis of the behaviour of circular and square concrete filled steel tube (CFST) short columns strengthened externally with carbon or glass fibre reinforced polymer sheets (CFRP or GFRP, respectively). A thorough review of existing test information is presented and discussed, and the most salient parameters in terms of the overall strength are identified. There are a large number of influential and inter-related parameters which affect the load-carrying capacity, including the geometry, cross-sectional shape, type of steel, concrete strength, boundary and loading conditions, and type of FRP. It is shown that existing design approaches do not reliably predict the strength for the full range of possible parameters. Therefore, this paper proposes a new design model to calculate the axial compressive strength of FRP-confined concrete filled steel tubular (CFST) short columns with either a circular or square cross-section. The method accounts for the various complexities which affect the behaviour, yet presents a user-friendly, performance-based design expression. It is based on an evaluation of the lateral confining pressure provided by the both the FRP and the steel tube to the concrete core. This is employed in the confinement-based direct resistance calculations. The paper validates the approach by comparing its capacity predictions with a large database of experimental results and alternative design models available in the literature. The results show that the proposed model provides much accurate strength predictions with greater reliability for the full range of parameters examined, than existing methods.

Development of chemistry-informed interpretable model for predicting compressive strength of recycled aggregate concrete containing supplementary cementitious materials

Accurate prediction of compressive strength of recycled aggregate concrete (RAC) has great value for promoting the sustainable development of concrete field. The study aims to propose a chemistry-informed interpretable model for predicting compressive strength of RAC containing supplementary cementitious materials. First, this study collected the compressive strength records of RAC. Then, the unsupervised learning algorithm isolation forest was utilized to perform data cleaning, and 1600 samples were obtained to build the dataset. And the topological network constraint was introduced to represent the reactivity of cementitious systems. The five machine learning (ML) algorithms were employed to predict compressive strength of RAC, and the prediction accuracy of above models were compared. In addition, SHapley Additive exPlanations (SHAP) method was integrated with the ML model to shed more light on the outcome of ML model. Results showed that the Categorical Boosting (CatBoost) outperformed other ML models on the test set, and the coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE) were 0.961, 2.650 MPa, and 1.636 MPa. The introduction of chemical information enhanced the predictive accuracy of model, and the R2 increased from 0.935 to 0.961, the RMSE and MAE decreased by 22.7% and 15.1%, respectively. The SHAP values of curing age, natural coarse aggregate replacement ratio and water-binder ratio were higher than those other input variables, indicating that the three features were essential for predictive results of model. And the curing age played a positive role in the strength development of RAC, and the increase of natural coarse aggregate replacement ratio and water-binder ratio caused the loss of compressive strength. The influence trends of features on the outputs were in accord with the engineering experience, which proved the reliability of predictions. The contribution and importance of features on the predictions provide a theoretical guidance to aid the concrete mixture design for engineers to obtain the desired performance.

Theoretical modeling for predicting the shear strength of partially-encased composite members with multiple transverse stiffeners

Partially encased composite (PEC) members are frequently used as girders in heavily-loaded or long-span structures. In PEC members, the steel web is encased in web concrete between the top and bottom flanges. When PEC members are used in continuous beam spans, the intermediate support area is subjected to significant shear force and negative bending, which is more critical than the span center. As a result, accurate prediction of shear strength is crucial for structural safety in practical design. Unlike traditional concrete or steel beams, PEC beams have multiple shear transfer mechanisms consisting of concrete, steel flanges, axial steel web, and transverse stiffeners (if necessary), and it is essential to investigate the shear contributions of the different mechanisms and how they work together as a composite structure. To solve this problem, this paper presents a novel shear strength model, in which the global shear strength is composed of two main components: the composite truss (steel flanges, web concrete, and transverse stiffeners) and the axial steel web, and these two components are unified by strain compatibility to show the composite action. Then, the proposed model is compared with existing shear equations using 25 existing specimens in the literature, and the results indicate that the proposed model can predict the shear strength of PEC beams with sufficient accuracy. Finally, the paper presents a simplified design method after validating the shear contributions of different anti-shear mechanisms, and the simplified method can facilitate practical design in engineering practices.

Static strengths of cold-formed steel elliptical hollow section X-joints

The newly emerged elliptical hollow section (EHS) has a vast of structural and architectural merits and is favorable for engineers and designers. This paper presents an experimental investigation concerning the structural behavior of cold-formed steel EHS X-joints. Thirty elliptical hollow section X-joints with three different brace-chord orientations were carefully designed, fabricated by robotic gas metal arc welding and tested with the braces axially compressed. The width ratio between brace and chord (β) ranged from 0.29 to 1. The brace-to-chord thickness ratio (τ) ranged from 0.58 to 1.83 and the chord width-to-thickness ratio (2γ) ranged from 10.1 to 52.6. The static strengths, failure modes and load-deformation responses are discussed. The current codified design provisions do not cover the design of cold-formed steel elliptical hollow section X-joints investigated in this study. As the performance of EHS lies between the circular and rectangular hollow sections, the feasibility of the design provisions initially calibrated for conventional X-joints as specified in the CIDECT and Eurocode 3 with incorporation of equivalent section methods as well as the design recommendations previously proposed for hot-rolled steel elliptical joints was evaluated. In general, these design methods provide accurate strength predictions for cold-formed steel elliptical hollow section X-joints. Nevertheless, the scattering of predictions is still a concern and the design method shall be further improved.

An improved method for predicting the shear strength of corroded reinforced concrete beams with experimental and numerical validation

Shear failure of reinforced concrete (RC) beams is a brittle failure without giving sufficient warning. Steel bar corrosion is one of the main deterioration phenomena for concrete structures in marine environments. However, the effect of steel bar corrosion on the shear-transfer mechanism of RC beams is not yet fully understood, and existing findings are insufficient for reasoned and accurate prediction of shear strength. Thus, the primary objective of this study was to propose and validate a revised fictitious-support-point method for better predicting the shear strength of corroded RC beams. The revised method determines the fictitious support points based on a more transparent mechanical model than previously. Finite element simulation confirms the validity of the revised method from the load-bearing mechanism point of perspective. Validation with copious previously-published test data show that the revised method predicts the shear strength of corroded RC beams more accurately and reasonably than the existing method proposed by other researchers. This study contributes to effective and reasonable maintenance of corroded RC structures.

Structural performance and design of S960 ultra-high strength steel non-slender welded I-sections subjected to combined loading

The structural performance of S960 ultra-high strength steel non-slender welded I-sections subjected to combined loading is studied in the present paper. Nonlinear finite element (FE) models were first created and validated with reference to test results collected from the literature, and then used for conducting parametric studies to derive numerical data over an extensive spectrum of cross-sectional geometries, aspect ratios, as well as loading combinations. Given the lack of existing design rules for S960 ultra-high strength steel structures, the suitability of the current provisions for lower strength steels given in the European, Australian and American specifications to S960 ultra-high strength steel was assessed based on the generated numerical data. It was found that (i) the European code and Australian standard can accurately predict the strengths of Class 1 and 2 (i.e. compact) S960 ultra-high strength steel welded I-sections subjected to both strong- and weak-axis combined loading, but results generally in conservative strength predictions for Class3 I-sections, and (ii) the American specification yields accurate strength predictions for S960 ultra-high strength steel welded I-sections subjected to strong-axis combined loading, but leads to conservative strength predictions for weak-axis combined loading. Finally, the continuous strength method (CSM) was applied to the studied S960 ultra-high strength steel non-slender welded I-sections subjected to combined loading and found to offer significantly improved design consistency and accuracy relative to the current codified provisions. The reliability of the latter design method was also confirmed by means of statistical analyses.

The Flexural Strength Prediction of Carbon Fiber/Epoxy Composite Using Artificial Neural Network Approach.

There is a developing demand for natural resources because of the growing population. Alternative materials have been developed to address these shortages, concentrating on characteristics such as durability and lightness. By researching composite materials, natural materials can be replaced. It is vital to consider the mechanical properties of composite materials when selecting them for a specific application. This study aims to measure the flexural strength of carbon fiber/epoxy composites. However, the cost of forming these composites is relatively high, given the expense of composite materials. Consequently, this study seeks to reduce molding costs by predicting flexural strength. Conducting many tests for each case is costly; therefore, it is necessary to discover an economical method. To accomplish this, the flexural strength of carbon fiber/epoxy composites was investigated using an artificial neural network (ANN) technique to reduce the expense of material testing. The output parameter investigated was flexural strength, while input parameters included ply orientation, manufacturing, width, thickness, and graphite filler percentage. The scope alternative was determined by identifying the values of variables that substantially affect the flexural strength. The prediction of flexural strength was deemed acceptable if the mean squared error (MSE) value was less than 0.001, and the coefficient of determination (R2) was greater than or equal to 0.95. The obtained results demonstrated an MSE of 0.003039 and an R2 value of 0.95274, indicating a low prediction error and high prediction accuracy for all flexural strength data. Thus, the outcomes of this study provide accurate predictions of flexural strength in the composite materials.