Machine Learning Approach for Prediction and Reliability Analysis of Failure Strength of U-Shaped Concrete Samples Joined with UHPC and PUC Composites

Journal of Composites Science, Journal Year: 2025, Volume and Issue: 9(1), P. 23 - 23

Published: Jan. 6, 2025

To meet the increasing demand for resilient infrastructure in seismic and high-impact areas, accurate prediction reliability analysis of performance composite structures under impact loads is essential. Conventional techniques, including experimental testing high-quality finite element simulation, require considerable time resources. address these issues, this study investigated individual hybrid models support vector regression (SVR), Gaussian process (GPR), improved eliminate particle swamp optimization hybridized artificial neural network (IEPANN) predicting failure strength concrete developed by combining normal (NC) with ultra-high (UHPC) polyurethane-based polymer (PUC), considering different surface treatments subjected to various static loads. An dataset was utilized train ML perform on dataset. Key parameters included compressive (Cfc), flexural load U-shaped specimens (P), density (ρ), first crack (N1), splitting tensile (ft). Results revealed that all had high accuracy, achieving NSE values above acceptable thresholds greater than 90% across datasets. Statistical errors such as RMSE, MAE, PBIAS were calculated fall within limits. Hybrid IEPANN appeared be most effective model, demonstrating highest value 0.999 lowest PBIAS, MAE 0.0013, 0.0018, 0.001, respectively. The times (N1 N2) reduced survival probability increased.

Language: Английский

Mechanical and Impact Strength Properties of Polymer-Modified Concrete Supported with Machine Learning Method: Microstructure Analysis (SEM) Coupled with EDS

Journal of Composites Science, Journal Year: 2025, Volume and Issue: 9(3), P. 101 - 101

Published: Feb. 24, 2025

This study investigated the mechanical and impact resistance properties of U-shaped polymer-modified concrete (PMC) incorporated with epoxy (EP) polyacrylate (PA) binders. The mixtures were prepared varying binder contents (0 to 30%) at intervals 10% for each EP PA binder. Moreover, scanning electron microscopy (SEM) analysis coupled energy-dispersive X-ray spectroscopy (EDS) was used microstructure mixtures. An Artificial Neural Network (ANN) model developed predict failure crack strength (N2). results indicate that binders enhance but decrease compressive strength, whereas slightly improve both properties. Introducing into PCM reduces by 4.91%, 15.09%, 33.02% EP10, EP20, EP30, respectively, compared reference specimen, initial improved 127.64%, 221.95%, 17.07% 10, 20, 30, respectively. ANN demonstrated high accuracy in predicting N2, achieving R² values 0.9892 0.9664 during training testing,

Language: Английский

Curing Kinetics of Biobased Resins Based on Soybean Oil and Isosorbide Catalyzed by Al(OTf)₃

Journal of Applied Polymer Science, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 27, 2025

ABSTRACT The curing kinetics of a biobased epoxy, formulated based on epoxidized soybean oil (ESO) and isosorbide (ISO), catalyzed by aluminum triflate, Al(OTf) 3 , were investigated using differential scanning calorimetry (DSC). resins synthesized with catalyst concentrations at 0.05, 0.07, 0.10 mol% upon two different ratios ESO to ISO (1:1 1:2). exothermic peak associated the epoxy ring opening was observed temperatures ranging from 80°C 115°C, influenced both heating rate amount catalyst. To analyze determine activation energy (E ) as well autocatalytic parameters, model‐free isoconversional model‐based methods employed. kinetic mechanism found be significantly affected contents. For compounds lower ISO, (Bna Cn) yielded fits deviations less than 3%, confirming nature reactions. In contrast, higher led complex reaction mechanisms, resulting in approximately 30% rendering Friedman numerical optimization ineffective.

Language: Английский