Abstract Reinforcement corrosion is a major cause that leads to the deterioration of reinforced concrete (RC) structures. As a result, quickly assessing its impact on structural components has become a priority in recent research. This study examines the use of machine learning (ML) models, an advanced approach in structural engineering, to predict the performance of corroded RC beams, specifically their load‐carrying capacity and bending moment. A substantial database of 804 beam samples is utilized, consisting of 649 corroded beams and 155 uncorroded beams, to capture the complex relationships between input features and structural responses. Nine ML models are trained and compared to determine their effectiveness for this task. Additionally, advanced optimization techniques are employed to improve the predictive accuracy and feature selection of the best‐performing models. Finally, the optimized models are integrated into graphical user interfaces, offering a practical tool to support future research and facilitate predictions regarding the performance of corroded RC beams.

The oriental river prawn (Macrobrachium nipponense, de Haan 1849) is a freshwater crustacean species with high economic value and strong development potential. The success of artificial reproduction greatly depends on broodstock conditioning and the method of egg incubation. This study aims to determine the appropriate broodstock rearing density and incubation method in river prawn seed production. In this experiment, male and female prawns were reared at densities of 50, 100, and 150 individuals per square meter in tanks, using commercial feed for white-leg shrimp with a protein 40% and lipid 7%. The results showed that at a rearing density of 50 individuals/m², the survival rate (71.0%) and maturation rate (79.1%) were significantly higher ( P <0.05) compared to the densities of 100 and 150 individuals/m². During the broodstock maturation process, female prawns carrying eggs on days 9-10 were selected to test two egg incubation methods: natural incubation (eggs carried by the female) and artificial incubation (eggs removed from the female and incubated separately). After 9 days of observation at temperatures ranging from 24.5 to 26.5°C, the results showed that natural incubation achieved a higher hatching rate (80.4%) compared to artificial incubation (71.8%). However, artificial incubation offers advantages in environmental control and is more suitable for large-scale production.

Material creep, defined as time-dependent strain accumulation under constant loading, can result in severe deformation and eventual component failure, posing a significant engineering challenge. Therefore, the possibility of early prediction of creep behavior is highly desirable. The objective of this study is to propose a robust method for predicting creep failure. To this end, we investigate the creep behavior of paper samples (quasi-brittle fiber composites) used as a model material, subjected to constant uniaxial tensile loads. Local strain fields are obtained through Digital Image Correlation and analyzed using dimensionality reduction techniques, a form of unsupervised machine learning, to identify universal indicators of deformation. This approach enables the detection of the onset of tertiary creep phase (deformation acceleration towards final failure), prediction of failure time, and accurate prediction of the failure location on the material surface just before the tertiary creep phase begins. Among the techniques used—Principal Component Analysis (PCA), Independent Component Analysis (ICA), Factor Analysis (FA), Non-negative Matrix Factorization (NMF), and Dictionary Learning (DL)—PCA and FA perform better in both detecting the onset of tertiary creep and predicting failure locations. The comparative analysis reveals the presence of universal characteristics in the evolution of local strain fields, offering a novel framework for studying material mechanics and providing key insights into failure prediction. In particular, the prediction of failure location as well as the comparison of the efficacy of various dimensionality reduction techniques are clearly novel aspects introduced in this work. • Universal characteristics of local strain field evolution were revealed. • Failure time and location were predicted through dimensionality reduction analysis. • Failure location was predicted well before visible macroscopic localization. • Principal Component Analysis and Factor Analysis outperformed other methods. • The approach employing DIC strain field data is applicable also to other materials.

This study investigates how second-language (L2) listeners from five first-language (L1) backgrounds—English, Dutch, Mandarin, Spanish, and Korean—perceive English lexical stress, focusing on their use of vowel quality, pitch, and duration cues. Participants completed a cue-weighting perception task (Tremblay et al., 2021) in which two acoustic dimensions were manipulated orthogonally while the third was neutralized. Data for Dutch listeners come from the original study. Predictions about cross-lin-<br/>guistic transfer were based on the functional weight of each cue in the L1. The following L1 effects were predicted: For vowel quality: English, Mandarin &gt; Dutch &gt; Spanish, Korean; for pitch: Mandarin &gt; Korean &gt; Dutch, Spanish &gt; English; for duration: English, Mandarin&gt; Dutch, Spanish &gt; Korean. Bayesian mixed-effects models tested the effects of cues and L1 with L2 proficiency (Lemh€ofer &amp; Broersma, 2012) as a covariate. The results aligned broadly with our predictions: for vowel quality, English-&gt; Mandarin &gt; Dutch &gt; Korean &gt; Spanish; for pitch: Mandarin &gt; Korean, Dutch &gt; Spanish &gt; English; for duration: English, Mandarin, Dutch &gt; Spanish &gt; Korean. These findings support a cue-weighting typology shaped by L1-specific cue prominence, with implications for theories of transfer and perceptual learning in L2 acquisition.

The development of small‐scale wind turbines with composite materials continues to gain momentum due to their cost‐effectiveness, high energy conversion efficiency, and ease of deployment. Despite these advantages, such composite structures are susceptible to operational failures such as fiber rupture, matrix cracking, and delamination. This research introduces a comprehensive design and analysis methodology for a 30 kW‐class small wind turbine blade engineered for low noise and enhanced durability. The blade incorporates a sandwich composite structure, utilizing E‐glass, S‐glass, and carbon fiber face sheets combined with a balsa wood core to improve weight efficiency and mechanical stability. To determine the most effective structural configuration and understand potential failure modes, nine composite sandwich variants were analyzed, considering core and layer failure limits, fiber orientation, and laminate stress distribution. Finite element analysis (FEA) was applied to evaluate stress responses and deformation behavior under static loads. Among the configurations tested, the one employing epoxy S‐glass unidirectional face sheets with a multidirectional fiber layup exhibited the lowest peak stress and superior resistance to deformation. An experimental tensile test on dog‐bone specimens further supported the numerical outcomes, with the unidirectional carbon fiber sample achieving the highest tensile strength of approximately 92 MPa. The FEA results for the optimized configuration remained safely within this failure limit. This study establishes a robust, data‐driven framework for optimizing composite blade structures, ensuring both performance and structural integrity in small wind turbine applications.

In this chapter, a numerical study to investigate the seismic vulnerability of the two storey colonnade of the Forum in Pompeii has been conducted. Software based on the Distinct Element Method (DEM) of analysis has been used. The colonnade was represented as an assemblage of distinct blocks connected together by zero thickness interfaces which could open and/or close depending on the magnitude and direction of stresses applied to them. Both static and non-linear static analyses have been undertaken. Also, a sensitivity study has been performed to investigate the effect of frictional resistance of the joints on the structural response of the colonnade. This was to simulate potential joint degradation effects and/or possible water lubrication at the joint.

Thermal drying (100–300 °C) is usually required to reduce moisture from chromium (Cr)-containing sludge before incineration, storage, or other resource recovery processes. Yet, part of trivalent chromium (Cr(III)) is oxidized to the toxic hexavalent chromium (Cr(VI)) during thermal drying. Currently, the molecular-level Cr(III) oxidization pathways during thermal drying remain poorly understood. In this paper, the molecular reaction pathway and the influence of Fe(III) substitution on CrxFe1–x(OH)3 oxidation in thermal drying are clearly elucidated. CrO3 is identified as a formed Cr(VI) product, and the oxidation pathway is heavily dependent on temperature and CrxFe1–x(OH)3 hydration. CrxFe1–x(OH)3 is oxidized through a well-defined pathway involving CrO3 as a key metastable intermediate, which sequentially decomposes into Cr5O12 and CrnFe2–nO3 at higher temperatures. The substitution of Fe(III) enhanced CrxFe1–x(OH)3 oxidation and lowered initial oxidation temperature, because Fe3d orbital hybridization with exogenous O2p orbitals facilitated electron transfer between Cr–O systems, and expanded electron transition regions. Since Cr(OH)O is an essential intermediate product during the Cr(VI) formation process, PO43–, SO42–, and Cl– ions were introduced to preferentially combine Cr(III) before the CrxFe1–x(OH)3 dehydration process, thereby preventing the generation of Cr(OH)O and subsequent Cr(VI) products. This study provides fundamental insights into the molecular-level mechanism of Cr(III) oxidation during thermal drying of Cr-containing sludge.

Ultra-high-performance fiber-reinforced concrete (UHPFRC) is a relatively new material known for its superior mechanical properties, particularly its compressive strength (CS), making it suitable for advanced structural applications. Traditional experimental methods for predicting CS are time-consuming and costly. In this study, a dataset of 276 samples with 12 input parameters was compiled from existing literature to develop predictive analytical models. The input variables include cement, sand, water, superplasticizer, silica fume, fiber content, water–binder ratio, water–cement ratio, curing age, fiber aspect ratio, temperature, and fiber volume. The reported CS values range from 90 to 186 MPa. Five modeling techniques—Linear Regression (LR), Log Base Regression (LBR), Nonlinear Regression (NLR), M5P-tree, and Artificial Neural Network (ANN)—were employed to predict the compressive strength of UHPFRC. Among these models, ANN demonstrated the highest prediction accuracy across all evaluation criteria, followed by the M5P-tree model. Residual error analysis confirmed that the ANN produced the lowest prediction error. Sensitivity analysis revealed that temperature, curing age, and superplasticizer content significantly influence CS. Optimization results indicated that a fiber content between 2.05% and 2.09% yields maximum compressive strength. These findings provide valuable insights for optimizing UHPFRC mix design using machine learning approaches.

This pioneering research involved an in-depth experimental evaluation of the mechanical properties of ambient-cured alkali-activated mortar (AAM), while assessing an innovative machine learning (ML) driven solution for sustainable construction. A comprehensive dataset was used, comprising 635 compressive strength and 94 flexural strength data points, including data from previous studies. The performance of six ML algorithms in predicting the compressive and flexural strengths of AAM was evaluated. Hyperparameter optimisation was performed with Optuna and ten-fold cross-validation. Multi-objective optimisation aimed to maximise compressive strength while minimising the carbon dioxide footprint. The findings highlight the significant impact of ground granulated blast-furnace slag (GGBS) content on strength, with higher GGBS improving compressive and flexural strengths but reducing workability. The highest compressive strength was 56.28 MPa at 28 days, for the AAM with 100% GGBS. The highest flexural strength was 0.580 MPa at 28 days, with 75% GGBS. Extreme gradient boosting was found to be the most reliable model in predicting the compressive strength, achieving a coefficient of determination (R2) of 98.1% on training data and 86.8% on testing data. Extra tree regression showed high accuracy in predicting the flexural strength of the AAM, achieving R2 = 90% on the testing dataset. A user-friendly interface was developed for predicting the mechanical properties of AAMs.

Ultra-High-Performance Concrete (UHPC) is an advanced cementitious material with exceptional strength and durability, widely used in high-performance structural applications. However, predicting its compressive strength remains a challenge due to the complex nonlinear interactions among its mix constituents. This study employs machine learning (ML) models—Adaptive Boosting (AdaBoost), Gradient Boosting Machine (GBM), and Extreme Gradient Boosting (XGBoost)—to develop predictive models for UHPC compressive strength. To further enhance predictive accuracy, four advanced metaheuristic optimization algorithms were integrated —Grey Wolf Optimizer (GWO), Whale Optimization Algorithm (WOA), Giant Trevally Optimizer (GTO), and Mountain Gazelle Optimizer (MGO)—to fine-tune hyperparameters of the ML models. A dataset of 810 UHPC mix samples with 15 input variables was used to train and evaluate the models. Among the tested approaches, the MGO-optimized XGBoost (MGO-XGB) model achieved the highest accuracy, with an R² of 0.9966 in training and 0.9839 in testing, along with the lowest root mean square error (RMSE) and mean absolute error (MAE). The results demonstrate that integrating metaheuristic optimization significantly improves ML model performance, with MGO-XGB emerging as the best predictor. Additionally, SHAP analysis identified key influencing factors, including silica fume content, superplasticizer dosage, and curing age, which play a critical role in UHPC strength development. The findings indicate that ML-assisted optimization can reduce reliance on extensive experimental testing, offering a cost-effective and efficient approach for UHPC mix design and quality control. To enhance practical usability, a graphical user interface (GUI) was developed, allowing engineers and researchers to input mix parameters and obtain immediate strength predictions. This study contributes to data-driven advancements in concrete technology, enabling more efficient and sustainable UHPC design and construction. • Revealing of material’s nature. • Hybrid ML models and metaheuristic optimization were used for UHPC strength prediction. • XGBoost optimized with MGO demonstrated the best predictive performance. • SHAP analysis identified key mix components influencing UHPC strength. • A user-friendly GUI was developed for real-time strength estimation.

This study evaluates the performance of foamed geopolymer concrete (FGC) incorporating rigid polyurethane (PU) waste as a partial sand replacement and aluminum powder (AP, 1%) as a foaming agent. The mixtures were based on metakaolin, fly ash, and silica fume. Fresh and hardened properties were assessed, including workability, setting time, density, compressive strength, flexural strength, splitting tensile strength, elastic modulus, water absorption, porosity, gas permeability, and chloride ion penetration. Microstructural characteristics were examined using scanning electron microscopy (SEM). The results show that moderate PU incorporation significantly enhances mechanical performance. The optimal mixture (PU30) achieved a compressive strength of 47.25 MPa at 180 days, representing a 15.6% increase compared to the control. Flexural and splitting tensile strengths improved by 19.9% and 16.7%, respectively, while the elastic modulus increased by 33.8% to 0.95 GPa. These improvements are attributed to enhanced particle packing and more efficient stress transfer within the matrix. In contrast, higher PU contents (&gt;30%) reduced mechanical performance due to increased total porosity and weakened interfacial bonding. Durability-related properties indicated that mixtures PU20–PU30 exhibited reduced permeability and optimized pore structure, characterized by lower pore connectivity. SEM observations confirmed a denser matrix with uniformly distributed pores at optimal PU levels. Additionally, the integration of Random Forest regression with GLCM-based texture analysis demonstrated strong capability in predicting mechanical properties from SEM images. Overall, the combined use of PU waste and AP enables the production of lightweight, structurally efficient, and sustainable FGC with improved mechanical and durability performance.

A reactive-transport model for chloride binding in cementitious materials is developed and validated over four temperatures (5, 21, 35, and 80°C) and three chloride concentrations (5, 10, and 20 g.L−1). Diffusive transport is coupled with surface complexation reactions (SCRs), in which the equilibrium constants (logK) are described by a nonlinear temperature-dependent formulation, and with kinetic laws for Friedel salt precipitation and dissolution that depend explicitly on temperature and chloride activity. Compared with equilibrium-only approaches, the proposed model avoids over-prediction of early-age bound chloride at elevated temperature. The nonlinear logK formulation provides a more consistent representation of SCR behavior from 5 to 80°C, while the chloride-activity-dependent Friedel salt kinetics is required to capture the delayed precipitation observed at 80°C under high chloride exposure. . The simulations further show that Friedel salt should be retained as the governing chloride-binding AFm phase in the final model formulation, whereas Kuzel salt does not reproduce the observed bound-chloride level satisfactorily under the investigated high-temperature conditions. In addition, kinetic Portlandite dissolution regulates Ca2+ supply and shifts the balance among competing phases. An additional assessment using CEM V indicates that the framework remains applicable up to 35°C, whereas the discrepancy at 80°C reveals a binder-specific limitation of the current high-temperature mineralogical submodel.