• Physics-informed neural networks for elastoplasticity in strong and weak forms. • Strong form supports forward prediction and parameter inversion with data loss. • Data-free weak form captures plastic evolution via energy minimization. • Kolmogorov–Arnold network is compared with multilayer perceptron in both forms. Physics-informed neural networks have recently achieved remarkable success in solving elastic problems by embedding governing equations into the training of neural networks. Building upon these advances, this study extends physics-informed neural networks to material nonlinearity and develops two computational frameworks for small-strain von Mises elastoplasticity. The strong-form framework enforces governing equations through pointwise residual minimization, enabling unified forward–inverse modeling of field variables and unknown material parameters. In contrast, the weak-form framework derived from total potential energy minimization allows data-free learning of elastoplastic evolution through incremental loading, yielding stable and physically consistent predictions. The recently developed Kolmogorov–Arnold network is further incorporated and compared with the conventional multilayer perceptron. Results show that the Kolmogorov–Arnold network alleviates the gradient oscillation and convergence instability in the weak-form framework but performs less effectively in the strong form. Furthermore, validations against reference solutions from conventional numerical methods demonstrate the potential of the developed physics-informed neural network frameworks as mesh-free surrogates for elastoplastic analysis.

I PEBA sono strumenti che servono alle amministrazioni pubbliche per individuare ed eliminare le barriere architettoniche, rendendo gli spazi accessibili a tutti. Anche gli ospedali sono obbligati a dotarsi di questi piani, non solo per rispettare la legge, ma soprattutto per migliorare la qualità dei servizi per gli utenti. In questo caso, l’Azienda Ospedaliero-Universitaria Pisana ha collaborato con l’Università di Firenze per sviluppare un piano di accessibilità per l’ospedale di Cisanello. L’obiettivo non era solo rispettare le norme, ma anche creare un metodo pratico per organizzare e pianificare gli interventi nel tempo. Il progetto è partito dall’analisi della situazione esistente e ha previsto la raccolta di dati, coinvolgendo anche persone con disabilità per avere una valutazione più concreta. Tutte le informazioni sono state poi inserite in una piattaforma digitale, così da poter aggiornare e monitorare gli interventi nel tempo. In sintesi, il progetto serve sia a capire lo stato attuale delle strutture, sia a definire delle linee guida per migliorare quelle future, formando anche persone in grado di gestire questi processi. È organizzato in diverse fasi e aiuta a passare dall’analisi alla realizzazione concreta del piano.

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 growing demand for concrete poses a significant environmental challenge, but alkali-activated high-performance concrete (AA-HPC) offers a more sustainable alternative by potentially reducing carbon emissions and ecological harm. This study explores the latest developments in machine learning (ML) applications aimed at predicting the compressive strength of AA-HPC, with a focus on minimizing experimental expenses, construction duration, and environmental impact. Among nine evaluated ML models, the combination of extreme gradient boosting (XGBoost) with the African vultures optimization algorithm (AVOA) emerged as the most effective. AVOA proved highly efficient in optimizing model parameters, achieving the lowest root mean square error (RMSE) during hyperparameter tuning. On the training dataset, XGB-AVOA reached an R2 of 0.994 and an RMSE of 2.368, while on the testing dataset, it maintained superior performance with an R2 of 0.975 and an RMSE of 5.664. These findings highlight AVOA’s strength in fine-tuning XGBoost compared to alternative optimizers such as grey wolf optimizer (GWO), whale optimization algorithm (WOA), social spider optimization (SSO), and gorilla troops optimizer (GTO). To support practical implementation, a graphical user interface (GUI) has also been developed, allowing researchers to efficiently utilize the XGB-AVOA model for accurate, cost-effective, and time-saving predictions in laboratory environments.

Abstract The field of reinforced concrete (RC) strengthening continues to evolve as the construction industry seeks cost‐effective and sustainable alternatives to structural replacement. This study, therefore, aimed to comprehensively investigate the pioneering application of steel‐reinforced grout (SRG) for strengthening large‐scale, 3.5‐meter‐long continuous RC beams. The main purpose was to explore the complex interplay among SRG density, the number of SRG layers, and the steel reinforcement ratio, and to assess their collective impact on the structural performance of the strengthened beams. Extensive experimental testing was carried out on 10 large‐scale RC continuous beams, including two pristine beams serving as references. The experimental findings demonstrated significant enhancements in the load‐carrying capacity of the strengthened beams, achieving increases ranging from 24% to 104% compared to the corresponding reference beams. Although a reduction in ductility was observed, this emphasized the need to optimize the balance between strength and deformation in the strengthened members. The use of low‐density SRG proved remarkably effective, providing superior bonding and higher efficiency, while high‐density SRG exhibited slightly lower performance due to reduced matrix penetration. Additionally, the number of SRG layers was found to play a crucial role in boosting the load capacity, with more pronounced effects in beams with lower steel reinforcement ratios. To complement the experimental investigation, two theoretical models based on the SRG effective strain were developed and validated against the experimental results. The close agreement between the models and the experimental data underscores their potential as practical tools for the design and optimization of SRG‐strengthened beams, thereby contributing critical insights for engineering applications.

Accurate and efficient rock mass quality classification is a prerequisite for assessing slope stability, designing support schemes, and ensuring mining safety in open-pit mines. However, traditional empirical classification methods rely heavily on expert judgment and often struggle to capture the complex, nonlinear relationships among factors influencing slope stability. Existing intelligent classification models also suffer from limitations, including sensitivity to incomplete data, insufficient feature interaction learning, and unstable performance on small-scale datasets. To address these issues, this study develops a deep forest (DeepForest) model optimized by three metaheuristic algorithms—brown bear optimizer (BBO), tuna swarm optimizer (TSO), and sparrow search algorithm (SSA)—to intelligently classify slope rock mass quality. A rock mass quality dataset containing 204 groups of slope and non-slope cases was established to train and evaluate the classification performance of the DeepForest models. Six influencing factors were set as input parameters: uniaxial compressive strength (UCS) of rock, rock quality designation (RQD), spacing of discontinuities (Sd), rock mass integrity coefficient (Kv), groundwater conditions (W), and site type (St). Multivariate imputation by chained equations (MICE), isolation forest (IsoForest), and synthetic minority over-sampling technique (SMOTE) were used to handle missing values, outliers, and imbalance in the dataset, respectively. The performance of the proposed models was evaluated using five metrics: accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). The experimental results indicate that the BBO-DeepForest model performed best on the independent test set, with accuracy, precision, recall, F1-score, and average AUC values of 0.878, 0.682, 0.678, 0.678, and 0.961, respectively. A comparison with seven well-known imputation algorithms revealed the superiority of the selected imputation algorithm in recovering incomplete rock mass quality datasets. Model interpretation results showed that RQD and UCS are critical feature parameters for classifying slope rock mass quality. At last, the proposed BBO-DeepForest model was employed to verify the rock mass quality of three slopes at the Luming molybdenum mine, resulting in classifications consistent with on-site observations. It demonstrates that combining DeepForest with metaheuristic optimization algorithms is a feasible and accurate approach for intelligently classifying the rock mass quality of slopes.

In this study, a novel digital twin (DT) modeling approach is developed to enhance the reliability assessment of civil structures subjected to multi-source uncertainties. Referring to the proposed procedure, a modular Bayesian inference (MBI) with the Transitional Markov Chain Monte Carlo (TMCMC) sampling algorithm is first used to calibrate the DT model of structures based on measured structural responses. Distinguished from the classic Bayesian inference approach, the uncertainty caused by modeling errors is added to the extended likelihood function by using a bias function. Then, the DT model calibration of structures can be achieved by three modules. Based on the calibrated DT model of structures, a finite number of discrete structural response samples can be generated by performing nonlinear dynamic analysis. Then, the generalized extreme value distribution (GEVD) is used to fit the probability density function (PDF) of these discrete response samples based on the maximum likelihood estimation (MLE) algorithm. Subsequently, the earthquake-induced failure probability of structures can be assessed by directly integrating the fitted GEVD and predefined structural failure thresholds. Numerical simulations on a three-story steel frame structure subjected to seismic excitations are developed to validate the feasibility of the proposed approach. The shake table tests on a scaled reinforced concrete (RC) column structure are further conducted to verify the effectiveness of the proposed approach. Both numerical and experimental results demonstrate that the proposed approach is reliable and highly effective for structural reliability assessment.

Distance-decay models are fundamental to accessibility modeling; yet their alignment with actual travel behavior remains insufficiently examined in empirical terms. To help address this gap, we propose a dual-component Tanner–Gaussian decay model that seeks to mitigate two key limitations of traditional accessibility frameworks by simultaneously describing the phenomena of full decay and local peaks. The model is calibrated using survey data from an urban park in Hangzhou, China, and subsequently assessed on two additional datasets from Wuhan and Shanghai. Results indicate that: (1) traditional Gaussian functions may overestimate short-distance and underestimate long-distance accessibility, while Tanner functions tend to capture long-tail decay more effectively and appear more suitable for long-distance accessibility estimation; (2) the proposed dual-component model performs favorably in large samples, though its stability appears sensitive to sample size. By comparing the application of multiple accessibility models across three datasets, we highlight how their suitability varies depending on the specific context. This comparison may offer a reference that could assist designers in identifying underserved areas and supporting more equitable access to urban green spaces in the context of rapid urbanization.

This study investigates chloride ingress and the attainment of steel depassivation conditions in fully saturated concrete exposed to seawater under long-term temperature scenarios. A coupled reactive-transport model is implemented in Toughreact by integrating multi-ion diffusion, thermodynamic aqueous speciation/mineral equilibria, kinetic dissolution-precipitation of major hydrates, chloride binding, and porosity feedback on the effective diffusion coefficient D e . The model is benchmarked against published long-term submerged chloride profiles to ensure realistic coupled transport-reaction behavior. Results show that non-Fickian near-surface features (chloride “drop” and subsurface peaks) can persist even under permanently submerged conditions, driven by a thin altered surface layer with reduced transport porosity/D e and diminished binding capacity (reduced bound chloride). Parametric simulations over 5-40°C (up to 50 years) demonstrate that higher temperature accelerates mineral alteration, alkalinity loss, and the advance of depassivation indicators. A consistent comparison of three criteria (free chloride, total chloride, and [Cl - ]/[OH - ]) shows that they may diverge when alkalinity, binding, and porosity evolve; thus, [Cl - ]/[OH - ] provides a chemistry-consistent depassivation index. For a representative cover depth of d=50 mm, depassivation conditions are reached within decades under warm exposure.