Search Results (470)

Bridge decks are continuously subjected to high environmental exposure, traffic loading, and material aging, leading to progressive delamination which can negatively affect structural integrity and public safety. More specifically, subsurface delamination of concrete and corroded steel reinforcement must be repaired to keep the decks operational. Among non-destructive evaluation techniques, Ground-Penetrating Radar (GPR) and Infrared Thermography (IRT) offer complementary capabilities for detecting subsurface and near-surface defects; however, effective GPR-IRT data fusion remains challenging due to fundamental differences in sensing principles, spatial resolution and sensitivity. This study introduces a Physics-Enhanced Multi-Modal Fusion (PE-MMF) framework that integrates GPR and IRT data to improve delamination detection in reinforced concrete bridge decks. The proposed approach leverages transfer learning, cross-modal attention mechanisms, and gated fusion to enable robust learning from heterogeneous sensor inputs. Furthermore, a systematic feature selection protocol is integrated to identify physically meaningful indicators that remain consistent across different bridges, enhancing generalization capability. The framework is trained and validated using the publicly available SDNET2021 dataset, comprising co-registered GPR and IRT measurements from five in-service bridge decks with verified delamination ground truth. Results demonstrate substantial performance improvements, with average F1-score gains of up to 55% over IRT-based methods and 25% over GPR-based methods across all tested bridges. Comparative analysis against state-of-the-art methods confirmed the superior generalization capability of the proposed multi-modal approach over single-modality approaches. The findings highlight the potential of deep learning-based sensor fusion as a scalable and data-efficient decision-support tool to prioritize regions for detailed physical investigation during long-term infrastructure monitoring. Full article

316L stainless steel and T91 heat-resistant steel are key structural materials for lead-cooled fast reactors (LFRs). Lead–bismuth eutectic (LBE) corrosion induces oxide layer formation and remarkably degrades thermal conductivity, endangering reactor safety and efficiency. Systematic experimental studies on and predictive tools for the thermal conductivity of stainless steels after LBE corrosion are currently scarce. To address the lack of experimental data and predictive capabilities regarding changes in thermal conductivity following LBE corrosion, this study experimentally obtained thermal conductivity data from stainless steels after lead–bismuth corrosion and developed machine learning models to predict thermal conductivity under multi-parameter coupled LBE corrosion conditions. Three machine learning models were established using material composition and corrosion parameters as inputs. Overall, the hyperparameter-optimized Gradient Boosting Regression model showed competitive predictive performance with low overall prediction error. The model therefore provides a preliminary data-driven tool for estimating the thermal conductivity of corroded 316L stainless steel and T91 heat-resistant steel, thereby providing technical support for material selection, thermal design, and safety assessment of LFRs, with further specimen-level validation required for broader engineering application. Full article

Rapid detection of foodborne pathogenic and spoilage microorganisms is critical for ensuring food safety and quality in liquid matrices. While Raman tweezers spectroscopy (RTS) enables label-free single-cell analysis, its application in high-throughput inline inspection faces a fundamental bottleneck: high flow rates required for efficiency induce severe motion blur and low signal-to-noise ratios (SNR), which blind automated control systems and destabilize optical trapping. To overcome this, we present a Spatiotemporal Video-Enhanced Raman Tweezers (SVERT) system integrating a deceleration-optimized microfluidic chip with a deep learning-based visual feedback loop. We propose a Local–Global Unified Denoising Network (LGU-Net) tailored to recover high-fidelity bacterial structures from low-SNR video streams, achieving a deterministic processing latency of ~0.49 ms. Experimental results demonstrate that SVERT improves the optical trapping success rate from 21.27% ± 2% to 91.47% ± 1.8% compared to raw video input, enabling a four-fold increase in spectral acquisition efficiency. Leveraging the acquired high-quality dataset, we achieved a classification accuracy of 96.74% across four bacterial species of relevance to food safety and quality. Crucially, we validated the system’s practical robustness by successfully isolating and tracking trace E. coli in an unpurified commercial beverage. This capability to effectively mitigate natural background interference demonstrates the system’s promising potential to be expanded for broader applications in liquid food safety screening. Full article

Agentic artificial intelligence (AI) offers new opportunities for intelligent clinical decision support, but deployment in emergency and crisis settings remains challenging because time-critical recommendations must often be generated under incomplete patient information and system constraints. Conventional clinical decision support systems rely on rule-based workflows that degrade when structured data are absent, while standalone language models lack coordination mechanisms to enforce mandatory safety checks. We present TriAgent, a multi-agent framework that unifies adaptive orchestration, iterative retrieval, embedded safety verification, and end-to-end auditability within a single crisis clinical decision support workflow. An Orchestrator Agent dynamically selects specialist modules for clinical assessment, retrieval, treatment planning, safety verification, and system coordination, with routing determined by model reasoning rather than fixed execution paths. A retrieval sub-agent performs iterative query refinement and relevance grading over 49,000 MIMIC-IV discharge notes, while medication-conflict screening and allergy-risk assessment are invoked in parallel only when clinically indicated. A Critique Agent reviews the full reasoning trace before recommendation finalization. In a retrospective evaluation on 1000 real emergency presentations under synthesized incomplete-information inputs, TriAgent achieved 85.0% critical-case recall and 65.7% overall triage accuracy, versus at most 14.7% and 43.4% for matched single-model and retrieval-only baselines, with safety checks executed on every continuation pathway and adaptive routing invoking only the modules each case required. These results support multi-agent orchestration as a promising design pattern for transparent and auditable AI in healthcare. These gains are internal system properties; clinical-safety benefit remains to be established through prospective, clinician-involved validation. Full article

Rock pillars in deep underground mines are subjected to complex stress environments. The combined effects of in situ stress and cyclic disturbances from mining activities lead to a redistribution of the surrounding rock mass stress field, which readily triggers instability and failure, posing severe threats to mining engineering safety. To investigate the damage mechanism of cyclic loading on rock and its weakening effect on the bearing capacity of mine pillars, this study takes limestone as the research object. A series of uniaxial compression tests were conducted on limestone specimens subjected to triaxial cyclic pre-damage, complemented by numerical simulations to further characterize the energy and deformation evolution of the damaged limestone under cyclic loading conditions. The findings are as follows: (i) Triaxial cyclic tests on limestone show that both the input energy and dissipated energy follow similar trends, decreasing rapidly in the initial stage before stabilizing. The elastic strain energy remains largely constant, with most of the input energy being stored as elastic strain energy. Under constant stress levels and cycle numbers, increases in confining pressure and frequency reduce the rock’s input energy, elastic strain energy, and dissipated energy. (ii) The peak stress of damaged limestone exhibits a positive correlation with the pre-damage confining pressure and cyclic frequency, while it decreases with an increasing number of cycles. Higher confining pressure and frequency raise the input energy, elastic potential energy, and dissipated energy at the peak stress point. (iii) Deformation and failure in damaged limestone originate from the development and propagation of localized deformation zones. Increased lateral displacement within these zones promotes the formation of macroscopic fractures. Due to significant structural heterogeneity inside the localized areas, the evolution of deformation energy is influenced by regional characteristics. (iv) Simulation results indicate that the uniaxial compressive failure of limestone involves the accumulation and propagation of micro-scale tensile cracks, which ultimately coalesce into macro-scale shear fracture surfaces. During uniaxial loading of pre-damaged limestone, newly generated cracks predominantly initiate around pre-existing cracks, with only a limited number distributed randomly. Their peak intensity shows a positive correlation with the pre-damage confining pressure. Full article

The high-pressure spherical gas storage tank in a wind tunnel energy storage and gas supply system is a critical pressure-bearing component of the wind tunnel operation system. The linearized stress in its critical control region is a key parameter for structural safety assessment. Therefore, investigating and evaluating the linearized stress and its associated uncertainty in this region is essential for enhancing operational safety. In this study, a three-dimensional finite element model of the spherical tank was developed, and the critical control region was identified through stress linearization. The operating internal pressure, working temperature, and shell wall thickness were treated as random input variables. Based on the stress linearization results, the stability of the critical control location was assessed. For physically homogeneous intervals, a non-intrusive polynomial chaos expansion surrogate model was constructed, and a conditional uncertainty propagation model for the linearized stress was established. Compared with the Monte Carlo and GUM methods, the non-intrusive polynomial chaos expansion method achieves substantially higher computational efficiency while producing consistent evaluation results. The uncertainty analysis shows that the operating internal pressure is the dominant contributor to the uncertainty of the linearized stress, followed by the effective wall thickness of the spherical shell. In contrast, the working temperature has a minor effect, and the interactions among the input variables are weak. Full article

Large-format photovoltaic modules are increasingly adopted to improve power output and reduce system cost, but their larger exposed area may also increase wind-induced structural demand and reduce structural safety under strong wind loading. This study investigated whether large-size photovoltaic modules and their support system could remain within an acceptable safety range under representative wind loading conditions in boundary free one-directional solar arrays in Ontario. Finite element models were developed in SAP2000 to assess the effects of module size, wind speed, and tilt angle on internal force, displacement, stress, and safety factor under static wind loading. For the array comparison, literature-derived pressure coefficients were used to represent the difference between the isolated single-row case and the front row of the 8-row array. The results showed that the large-size module consistently developed higher bending moments and larger displacements than the normal-size module under the same loading condition, indicating a clear size effect. The isolated single-row case produced a larger immediate structural response than the front row of the 8-row array under the selected loading input. Under a fixed 0° tilt angle and increasing wind speed, the glass panel remained the governing safety component. Under the fixed 27 m/s wind condition and increasing tilt angle, the governing component shifted to the purlin in the large-size module, especially under high-tilt cases. These findings provide a design-oriented basis for assessing the structural safety of large-size photovoltaic systems under wind loading. Full article

Against the background of observed climate change, which increases the risk of glacier-system degradation and the formation of hidden crevasses, the development of lightweight, wideband, and highly directional antenna systems has become a key factor in ensuring the safety of logistics operations and enhancing the spatial resolution and interpretability of ground-penetrating radar monitoring of near-surface snow–ice layers. The effectiveness of such systems is largely determined by the characteristics of the antenna unit, including the operating frequency band, gain, radiation pattern, weight, and resilience under extreme climatic conditions. The aim of this review is to provide a systematic analysis of modern Vivaldi antenna designs and Vivaldi-based antenna arrays, as well as to assess their prospects for application in X-band ground-penetrating radar systems for probing Antarctic snow-ice media. The paper considers the main types of ground-penetrating radar (GPR) antennas, their advantages and limitations, substantiates the priority of detecting hazardous near-surface inhomogeneities, and analyzes the capabilities of the X-band for the high-resolution identification of these inhomogeneities. Particular attention is paid to modern modifications of Vivaldi antennas, including antipodal, balanced, director-loaded, metamaterial-based, and array configurations. The analysis shows that Vivaldi antennas represent a promising basis for lightweight, wideband, and directional GPR systems; however, they require further improvement in terms of gain enhancement, sidelobe and back-lobe suppression, radiation-pattern stabilization, and adaptation to Antarctic operating conditions. Future research should focus on the development of adaptive and phased Vivaldi arrays, the use of metamaterials, Electromagnetic Band-Gap/Frequency-Selective Surfaces (EBG/FSS) structures, and director elements, the creation of lightweight, frost-resistant substrate materials, the advancement of multi-polarization multiple-input multiple-output (MIMO) systems, and the integration of antenna arrays with synthetic aperture radar (SAR) processing adapted to a multilayer snow–ice medium. Full article

Accurate prediction of pile-cap strain is crucial for the safety of wind-turbine foundations, yet conventional methods struggle to screen key features from high-dimensional monitoring data and to model the nonlinear coupling between endogenous and exogenous variables, hindering both accuracy and interpretability. To address these limitations, this paper proposes a pile-cap-strain prediction method integrating XGBoost-SHAP feature selection with the TimeXer deep-learning model. XGBoost-SHAP first identifies critical predictors from high-dimensional pile-stress data; the TimeXer model then exploits its endogenous–exogenous fusion mechanism for strain prediction. The results show that XGBoost-SHAP effectively selected 10 key features, of which the upper-middle and middle windward-side stresses (Z1-4A, Z1-5A) contributed over 40% of the explanatory power. This stage performs dimensionality reduction and sensor-importance interpretation, halving the input dimensionality while maintaining accuracy comparable to the full 19-channel input. TimeXer achieved a coefficient of determination (R²) of 0.993 in single-step prediction, comparable to the best-performing baselines, and maintained stable performance over a 120 min multi-step horizon. In a zero-shot cross-site transfer test, TimeXer attained the highest eight-step average R² (0.914) among all models, indicating strong cross-site generalization. Attention-mechanism visualization further suggested consistency between the model’s prediction logic and structural mechanics principles. The proposed framework provides a technical solution combining high accuracy with strong interpretability for wind-turbine foundation health monitoring. Full article

The mining industry faces complex operational hazards that necessitate systematic risk assessments to enable proactive accident prevention. While Large Language Models (LLMs) offer significant potential for the automated generation of safety measures, the limited availability of domain-specific terminology and high-quality labelled safety data (in low-resource environments) hinders their direct application. This study investigates and optimises data augmentation strategies to fine-tune LLMs to generate accurate, context-sensitive safety measures from structured coal mine risk records. The study systematically explored four experimental configurations, leveraging the Mistral-7B-Instruct model in conjunction with Quantised Low-Rank Adaptation (QLoRA) for efficient fine-tuning. These configurations comprised: (i) a baseline without augmentation, (ii) input-side lexical augmentation, (iii) output-side multi-reference augmentation, and (iv) a combined strategy. Performance was measured using BLEU, ROUGE, METEOR, and BERTScore metrics, along with statistical significance testing and qualitative analyses. The results show that, compared to other strategies, the input-side data augmentation strategy performs better. The findings indicate that input-side data augmentation yields significant improvements; this strategy increased the BERTScore (F1) from 0.360 to 0.530 and the BLEU score from 16.02 to 29.50 compared to the baseline model. In contrast, output-side multi-reference augmentation contributed to greater learning uncertainty and a consequent decline in performance. Statistical and qualitative analyses confirm that increasing input variety minimises model overfitting and enables the model to generate consistent, applicable, domain-specific safety measures. The proposed methodology provides a highly scalable solution for automated risk management in high-risk industrial environments, such as mining, offering a reliable, data-driven decision-support mechanism that minimises the limitations of manual review. Full article

Trustworthy deployment of artificial intelligence in safety-critical systems requires accurate diagnosis of anticipated scenarios and reliable rejection of out-of-distribution (OOD) inputs that fall outside the modeled operational scope. Existing data-driven diagnostic models typically assume that test inputs are drawn from the training distribution or rely on heuristically tuned thresholds that lack enforceable safety guarantees. This article presents SCOPE (Safety-Calibrated Out-of-distribution Prediction via Contrastive Embeddings), a framework integrating supervised contrastive learning with split-conformal prediction to provide statistically grounded OOD rejection with finite-sample false-alarm control. SCOPE employs a causal residual convolutional encoder to map multivariate sensor streams into a hyperspherical embedding space with a compact, class-specific structure. A k-nearest-neighbor density nonconformity score, computed in the encoder embedding space, flags transients that occupy low-density regions relative to known accident manifolds; an ablation shows that this density score outperforms prototype distance, entropy, and conservative maximum fusion as well as a panel of standard OOD baselines (MSP, ODIN, energy, Mahalanobis, OpenMax, MC-dropout, and a reconstruction autoencoder). To support temporally evolving trajectories, SCOPE aggregates window-level scores under a monotone decision policy and performs trajectory-level conformal calibration, yielding distribution-free guarantees that bound the probability of falsely rejecting a known accident run. SCOPE is evaluated on the Nuclear Power Plant Accident Data (NPPAD) benchmark using high-openness splits that withhold entire accident families as unknowns, and all metrics are reported as mean ± standard deviation across multiple random seeds. Results demonstrate strong diagnostic accuracy on accepted trajectories, conservative false-alarm rates satisfying user-specified safety constraints across multiple operating points, and timely rejection of unseen accident mechanisms, making SCOPE suitable for deployment in safety-critical monitoring applications. Full article

Structural planes widely developed in slope rock masses are key geological elements governing deformation, failure modes and engineering stability. Traditional manual logging suffers from low efficiency, high safety risks and inadequate data integrity, failing to meet large-scale and refined survey needs. This paper proposes a cross-modal collaborative recognition system for slope discontinuities. The principal methodological contribution is the cross-modal ROI-guidance mechanism itself: 2D detection bounding boxes are back-projected through pixel-to-point-cloud registration to construct region-of-interest constraints in 3D space, transforming intractable global blind-search segmentation into localized oriented analysis within bounded volumes—to the best of the authors’ knowledge, the first systematic establishment of such a “visual detection → ROI-guided 3D analysis” framework for slope discontinuity characterization. Within this paradigm, established modules are adapted to the discontinuity recognition task rather than newly invented: channel attention, bidirectional multi-scale fusion and angle-aware regression are integrated into the detection backbone to address the weak texture contrast, large-scale span and extreme aspect-ratio morphology of discontinuity targets, while a PCA–DBSCAN–RANSAC cascade operating within the ROI volumes extracts dip direction, dip angle, spacing and trace length. Validated on two typical slopes in Hunan Province, the improved network achieves a mAP@0.5 of 89.4%, the average IoU of point cloud segmentation is 82.6–86.3%, the dip angle RMSE is 2.46° and the spacing average relative error is 6.8%. The full workflow takes about 86 min, a 19.5-fold efficiency gain over manual methods, and provides an automated pipeline from heterogeneous remote sensing data to engineering-usable structural parameters. The resulting outputs are organized in a tabular schema compatible with mainstream discrete-element software such as 3DEC and UDEC, where they serve as geometric inputs to downstream stability modelling once site-specific mechanical calibration is performed. The two-site validation reported here should accordingly be read as a proof of operational feasibility within the limestone and sandstone–mudstone envelope examined, with broader deployment to other lithologies identified as the natural next phase of evaluation. Full article

Aquaculture solid waste (ASW) from intensive farming poses significant environmental challenges, yet its potential as a composting feedstock remains insufficiently evaluated. This study systematically assessed the feasibility of aerobic composting for ASW valorization through integrated feedstock characterization, composting process monitoring, microbial community analysis, and pot experiment validation. ASW collected from intensive aquaculture facilities was characterized by high phosphorus (mean TP: 6.80 mg/g), potassium (TK generally >10 mg/g), and iron (mean Fe: 49,112 mg/kg) content but low organic matter (17.60%) and total nitrogen (0.72%). Composted with rice straw powder, meat and bone meal, and mineral amendments, ASW was successfully converted into mature compost, with the thermophilic phase (>50 °C) lasting only 4 days and the seed germination index exceeding the 80% safety threshold within 15 days. The composting process exhibited an organic matter degradation rate of approximately 20.82%, along with low electrical conductivity and stable pH in the final product. Microbial community analysis revealed that ASW addition significantly altered bacterial and fungal community structure, enriching functional taxa associated with organic matter decomposition and nutrient transformation. Pot experiments conducted under equal nutrient input conditions demonstrated that the ASW-derived compost supported satisfactory crop growth, with the fresh weight of Fast-growing Cabbage reaching 106.95 g per plant. The compost also improved soil properties, including reduced electrical conductivity (72.8% lower than urea), increased soil organic matter (17.8% increase over original soil), and enhanced available phosphorus (93.0% increase over original soil). These results indicate that aerobic composting is a technically viable pathway for converting ASW into a qualified organic fertilizer, providing a preliminary scientific basis for future waste management strategy for the sustainable development of the aquaculture industry. Full article

As sustainable development becomes increasingly important, technologies for liquid hydrogen (LH₂) storage and transportation are advancing rapidly. Safety concerns regarding LH₂ tanks in fire accidents require further attention. In this study, a one-dimensional thermodynamic model was developed based on layer-by-layer analysis to assess the heat transfer performance of the insulation structure in LH₂ tanks under fire conditions. Through the transformation of the solving target and iteration rules, a novel and efficient solution method was proposed for such thermodynamic problems. The thermodynamic performance of the insulation structure coupled with spray-on foam and variable-density multilayer under normal temperature (NT) and standardized fire conditions (863.15 K) was analyzed, and the effects of insulation structure parameters and environmental factors were evaluated. A case study of a 500 L vehicle LH₂ tank was conducted using the software package BoilFAST, with the total heat leakage as the key input, to analyze the evolution of internal pressure and temperature. Results show that within the insulation structure, temperature decreases rapidly by 80.35% and 89.55% under fire and NT conditions, respectively. Spray-on foam insulation thickness, layer density, residual gas pressure, and hydrogen temperature exert minor effects, while the temperature of the external environment and the number of layers significantly affect the heat flux under the fire condition. Under the NT condition, heat leakage is primarily attributed to support structures and accessory pipelines, whereas under the fire condition, heat leakage from the insulation structure becomes the main source, accounting for 63%. This study provides a reference for heat transfer assessment of LH₂ tanks in fire scenarios. Full article

Large Language Models (LLMs) are typically safety-aligned using high-resource language data, but it remains unclear whether these constraints transfer reliably across distinct linguistic manifolds. This study examines the mathematical foundations of cross-lingual guardrail degradation using Bengali as a low-resource test case. We evaluate Meta-Llama-3-8B, Gemma-2-9B, and Llama-Guard-3 through an automated English-to-Bengali translation pipeline, paired statistical testing, latent-space visualization, and tokenization-based structural analysis. The results show a statistically significant increase in Gemma-2’s Attack Success Rate from 32.0% in English to 41.2% in Bengali ($p<0.0001$, McNemar’s test), while Llama-Guard-3 fails to detect 39.5% of malicious Bengali prompts. Latent-space projections indicate weaker separation between safe and unsafe Bengali representations, and tokenization analysis shows a 4.69-fold token fertility expansion associated with a normalized perplexity of 887.32. Furthermore, projecting low-resource inputs back into the high-resource latent space successfully restores optimization constraints, whereas natively translating safety prompts exacerbates vulnerability. Together, these findings suggest that cross-lingual safety failures are associated with representational entanglement and token fragmentation rather than only superficial prompt translation effects. The study supports the need for multilingual alignment methods that better account for tokenization geometry, latent-space structure, and language-dependent safety evaluation. Full article