Abstract: This paper presents an outline of the problems facing the Polish energy sector. It high-lights the significant role of wind energy in the National Power System, while limiting the possibility of installing new wind farms. It is suggested that repowering and ex-tending the operational life of wind turbines will be an important solution to this problem. The possibility of using data from existing turbines to inform operational strategies was analyzed. Historical data was obtained for selected wind turbines and statistically analyzed. The main goal of the study was to develop regression models for wind conditions and electricity production. The best fit between the actual distribu-tions of the analyzed variables and selected theoretical distributions was determined. It was demonstrated that in the analyzed case, the Log-Normal distribution provided a better fit than the Weibull distribution, preferred by the energy industry.

Abstract: Unexploded ordnance (UXO) poses a significant hazard in military training areas. This paper assesses the effectiveness of aerial drone-mounted magnetometry for detecting buried UXO located outside the designated impact zones of the National Training Center (CENAD) of San Gregorio (Zaragoza, Spain), considered the largest maneuver area in Europe. To this end, a high-resolution aeromagnetic survey was conducted using a GEM GSMP-35U proton magnetometer mounted on a hexacopter drone. Data were collected at flight altitudes of 7 m and 2 m above ground level along a grid with 1-m line spacing. For its validation, eleven UXOs were deliberately buried at known coordinates to evaluate the system’s sensitivity and spatial resolution under operational conditions. The results demonstrate the capability of aerial drone-based magnetometry to detect small magnetic anomalies (with amplitudes between 2 and 18 nT) associated with buried UXO in complex environments characterised by high ferromagnetic noise, achieving signal-to-noise ratios greater than 5 (SNR > 5) at 2-m altitude and a geolocation accuracy of approximately 0.5 m. These findings support the use of unmanned aerial magnetometry as a viable tool for identifying hazardous remnants in military training ranges and operational scenarios, enabling coverage of 0.53 ha in less than one hour of effective flight time.

Abstract: In complex energy storage operating scenarios, batteries seldom undergo complete charge–discharge cycles required for periodic capacity calibration. Methods based on accelerated aging experiments can indicate possible aging paths; however, due to uncertainties like changing operating conditions, environmental variations, and manufacturing inconsistencies, the degradation information obtained from such experiments may not be applicable to the entire lifecycle. To address this, we develop a stage-wise state-of-health (SOH) prediction approach that combines offline training with online updating. During the offline training phase, multiple single-cell experiments were conducted under various combinations of depth of discharge (DOD) and C-_rate. Multi-dimensional health features (HFs) were extracted and an accelerated aging probability p_AA was defined. Based on the correlation statistics between HF, k_HF, SOH, and p_AA, all cells in the dataset were divided into general early, middle, and late aging stages. For each stage, cells were further classified by their longevity (long, medium, short), and multiple models were trained offline for each category. The results show that models trained on cells following similar aging paths achieve significantly better performance than a model trained on all data combined. Meanwhile, HF optimization was performed via a three-step process: an initial screening based on expert knowledge, a second screening using Spearman correlation coefficients, and an automatic feature importance ranking using a random forest regression (RFR) model. The proposed method offers the following innovations: (1) The stagewise multi-model strategy significantly improves SOH prediction accuracy across the entire lifecycle, maintaining the mean absolute percentage error (MAPE) within 1%. (2) The improved model provides uncertainty quantification, issuing a warning signal at least 50 cycles before the onset of accelerated aging, thereby enabling early detection of accelerating degradation. (3) Analysis of feature importance from the model outputs allows indirect identification of the primary aging mechanisms at different stages. (4) The model is robust against missing or low-quality HFs—if certain features cannot be obtained or are of poor quality, the prediction process does not fail.

Abstract: Workplace safety and health remain a major global challenge, with work-related accidents and diseases still causing millions of deaths each year despite decades of regulatory, technical and organizational advances. In parallel, the digitalization of Industry 4.0/5.0 is generating unprecedented volumes of safety-relevant data and new opportunities to move from reactive analysis to proactive, data-driven prevention. This review maps how artificial intelligence (AI), with a specific focus on natural language processing (NLP) and large language models (LLMs), is being applied to occupational risk prevention across sectors. A structured search of the Web of Science Core Collection (2013– October 2025), combined OSH-related terms with AI, NLP and LLM terms. After screening and full-text assessment, 126 studies were discussed. Early work relied on text mining and traditional machine learning to classify accident types and causes, extract risk factors and support incident analysis from free-text narratives. More recent contributions use deep learning to predict injury severity, potential serious injuries and fatalities (PSIF) and field risk control program (FRCP) levels, and to fuse textual data with process, environmental and sensor information in multi-source risk models. The latest wave of studies deploys LLMs, retrieval-augmented generation and vision–language architectures to generate task-specific safety guidance, support accident investigation, map occupations and job tasks, and monitor personal protective equipment (PPE) compliance. Together, these developments show that AI-, NLP- and LLM-based systems can exploit unstructured OSH information to provide more granular, timely and predictive safety insights. However, the field is still constrained by data quality and bias, limited external validation, opacity, hallucinations and emerging regulatory and ethical requirements. In conclusion, AI and LLMs should be positioned as human-in-the-loop decision-support tools and outlines a research agenda centered on high-quality OSH datasets, hybrid models integrating domain knowledge and AI, and rigorous evaluation of fairness, robustness, explainability and governance.

Abstract: Early detection of bubble generation from tube arrays in systems such as fast reactor steam generators, Pressurized Water Reactor (PWR) cores, and Liquefied Natural Gas (LNG) regasification units is critical for safety. While various methods have been proposed, they face challenges such as high spatial resolution requirements, rapid response times, and varying strengths and weaknesses, suggesting the need for a combined approach. This study integrates the ultrasonic testing (UT) with Machine Learning (ML) to identify the presence, location, and direction of bubbles within a complex tube array that cause signal attenuation. A Convolutional Neural Network (CNN) successfully achieved 100% identification accuracy. Furthermore, a novel method was developed that uses an autoencoder as a feature extractor, combined with a One-Class Support Vector Machine (SVM) and k-means. This approach achieved high accuracy and a correct decision basis. It also demonstrated strong generalization, successfully detecting anomalies without requiring labels for anomalous data, enabling robust bubble identification.

Abstract: The acceptance or rejection of a measurement is determined based on its associated measurement uncertainty. This decision-making process inherently carries the risk of errors, including the possible rejection of compliant measurements or the acceptance of non-conforming ones. This study introduces a mathematical model for the spatial evaluation of global risk to both producers and consumers, grounded in Bayes' theorem and with the application of a decision rule incorporating a guard band. The proposed model is well-suited for risk assessment within the framework of multivariate linear regression. The model's applicability was demonstrated through an example involving the flatness of the workbench table surface of the CMM. The least-risk direction on the workbench was identified, and risks were calculated under varying selections of the reference planes and differing measurement uncertainties anticipated in future measurement processes. Model evaluation was conducted using performance metrics derived from confusion matrices. The spaces of the most used metrics over the domain limited by the dimensions of the CMM workbench were constructed. Using the tested metrics, the optimal widths of the guard band were determined, which ensures the smallest values of the global producer's and consumer's risk.

Abstract: Corporate bankruptcy prediction has become increasingly critical amid economic uncertainty. This study proposes a novel two-stage machine learning approach to enhance bankruptcy prediction accuracy, applied to Tokyo Stock Exchange-listed companies. First, models were trained using 173 financial indicators. Second, a wrapper-based feature selection process was employed to reduce dimensionality and eliminate noise, thereby identifying an optimal seven-feature set. Two ensemble learning methods, Random Forest and LightGBM, were used. Random Forest correctly predicted 566 bankruptcies using the reduced feature set (88 more than when using all features) compared with 451 by LightGBM (31 more than when using all features). The study also addresses challenges posed by imbalanced data by employing resampling techniques (SMOTE, SMOTE-ENN, and KMeans). Additionally, the need for industry-specific modeling is recognized by constructing models for the six industry sectors. These findings highlight the importance of feature selection and ensemble learning for improving model generalizability and uncovering industry-specific patterns. This study contributes to the field of bankruptcy prediction by providing a robust framework for accurate and interpretable predictions for both academic research and practical applications. Future work will focus on further enhancing prediction accuracy to identify more potential bankruptcies.

Abstract: This study assesses the impact of ISO/IEC 17025 accreditation on quality performance, operational efficiency, and customer satisfaction at Eskom’s Flow Laboratory, a key calibration facility in South Africa’s power generation sector. It investigates how ac-creditation has influenced technical competence, service delivery, and customer con-fidence. Data was collected through questionnaires from 82 customers across sectors including power generation (28%), environmental testing (24%), manufacturing (20%), mining (15%), and other industries (13%). Results show strong positive perceptions of post-accreditation performance, with an overall satisfaction mean of 4.55/5 and 88% agreement among respondents. The highest scores were for result accuracy and relia-bility (4.7), staff competence (4.6), and customer willingness to recommend the lab (4.8). Furthermore, 91% agreed that accreditation improved confidence in test results, while 88% cited stronger quality control and traceability. Reported benefits included enhanced efficiency (85%), transparency (83%), and international recognition (87%). Overall, ISO/IEC 17025 accreditation has significantly strengthened the laboratory’s technical credibility, operational consistency, and client trust. The study concludes that sustaining these gains will require ongoing investment in staff development, customer engagement, and technology, in support of Eskom’s broader goals of operational ex-cellence, reliability, and customer satisfaction.

Abstract: Oversight of U.S. airports under FAA Part 139 is primarily checklist-driven, whereas the ICAO Safety Management System (SMS) emphasizes proactive, performance-based safety practices. Despite widespread adoption of both approaches, quantitative comparisons remain limited. This study develops a structured mapping framework aligning FAA Part 139 requirements with the four ICAO SMS pillars: safety policy, risk management, safety assurance, and safety promotion. Publicly available FAA inspection findings were normalized using OPSNET operational exposure data and compared with ICAO’s Universal Safety Oversight Audit Programme (USOAP) indicators to identify areas of overlap and divergence and to assess whether checklist compliance and SMS routines produce consistent outcomes. The study presents a detailed crosswalk between the two frameworks, descriptive statistics on inspection deficiencies, and comparative assessments of regulatory coverage. Regression modeling evaluates the relationship between SMS implementation levels and FAA inspection outcomes while controlling for airport size and operational context. Findings indicate that Part 139 oversight performs effectively in high-consequence areas, including Aircraft Rescue and Firefighting (ARFF), while SMS contributes to early hazard detection and strengthens safety culture. Based on these results, a hybrid oversight model integrating mandatory inspections with predictive SMS practices is proposed to enhance U.S. aviation safety and support alignment with international standards.

Abstract:

Structure detection(SD) has emerged as a critical technology for ensuring the safety and longevity of infrastructure, particularly in housing and civil engineering. Traditional SD methods often rely on manual inspections, which are time-consuming, labor-intensive, and prone to human error, especially in complex environments such as dense urban settings or aging buildings with deteriorated materials. Recent advances in autonomous systems—such as Unmanned Aerial Vehicles (UAVs) and climbing robots—have shown promise in addressing these limitations by enabling efficient, real-time data collection. However, challenges persist in accurately detecting and analyzing structural defects (e.g., masonry cracks, concrete spalling) amidst cluttered backgrounds, hardware constraints, and the need for multi-scale feature integration . The integration of machine learning (ML) and deep learning (DL) has revolutionized SD by enabling automated feature extraction and robust defect recognition. For instance, RepConv architectures have been widely adopted for multi-scale object detection, while attention mechanisms like TAM (Technology Acceptance Model) have improved spatial feature fusion in complex scenes. Nevertheless, existing works often focus on singular sensing modalities (e.g., UAVs alone) or neglect the fusion of complementary data streams (e.g., ground-based robot imagery) to enhance detection accuracy. Furthermore, computational redundancy in multi-scale processing and inconsistent bounding box regression in detection frameworks remain underexplored. This study addresses these gaps by proposing a generalized safety inspection system that synergizes UAV and stair-climbing robot data. We introduce a novel multi-scale targeted feature extraction path (Rep-FasterNet TAM block) to unify automated RepConv-based feature refinement with dynamic scale fusion, reducing computational overhead while preserving critical structural details. For detection, we combine traditional methods with remote sensor fusion to mitigate feature loss during image upsampling/downsampling, supported by a structural model GIOU [Mathematical Definition：GIOU=IOU-（C-U）/C] that enhances bounding box regression through shape/scale-aware constraints and real-time analysis. By siting our work within the context of recent reviews on ML/DL for SD, we demonstrate how our hybrid approach bridges the gap between autonomous inspection hardware and AI-driven defect analysis, offering a scalable solution for large-scale housing safety assessments. In response to challenges in detecting objects accurately during housing safety assessments—including large/dense objects, complex backgrounds, and hardware limitations—we propose a generalized inspection system leveraging data from UAVs and stair-climbing robots. To address multi-scale feature extraction inefficiencies, we design a Rep-FasterNet TAM block that integrates RepConv for automated feature refinement and a multi-scale attention module to enhance spatial feature consistency. For detection, we combine dynamic scale remote feature fusion with traditional methods, supported by a structural GIOU model that improves bounding box regression through shape/scale constraints and real-time analysis. Experiments demonstrate that our system increases masonry/concrete assessment accuracy by 11.6% and 20.9%, respectively, while reducing manual drawing restoration workload by 16.54%. This validates the effectiveness of our hybrid approach in unifying autonomous inspection hardware with AI-driven analysis, offering a scalable solution for SD in housing infrastructure.

Abstract: Traditional route optimization frameworks often suffer from "spatial blindness," ad-dressing the problem through abstract matrices devoid of geographical context, which yields suboptimal solutions in complex landscapes. To address this fundamental methodological gap, this study proposes the Iterative Score Propagation Algorithm (ISPA), a transparent, GNN-inspired framework that reframes optimization from a set of isolated points to a holistic corridor problem. The robustness and superiority of ISPA were rigorously tested against established Multi-Criteria Decision-Making (MCDM) methods (WLC, TOPSIS, VIKOR). This comparative analysis was conducted across three diverse engineering scenarios—ranging from balanced engineering (rural high-way) and cost-centric optimization (pipeline) to experience maximization (trekking trail)—and under two distinct weighting philosophies (objective Entropy and subjec-tive AHP). The holistic analysis reveals that ISPA achieves the highest final score (0.815) across all six test conditions, demonstrating both the highest overall mean per-formance and the greatest stability. Furthermore, its flexible cost function successfully modeled unconventional objectives, such as a "climbing reward," showcasing a para-digm shift from cost minimization to experience maximization. We conclude that ISPA's superior performance stems from its structural advantage in contextualizing spatial data, rather than a dependency on any specific weighting scheme. Conse-quently, this work introduces not just a novel algorithm but a new, spatially-aware approach that transforms route planning from a static calculation into a dynamic de-sign and scenario analysis tool for planners and engineers.

Abstract: The present study examines the mechanisms of overtopping failure and the evolution laws of homogeneous earth embankments during the flood season. To this end, the Changkai embankment in Fuzhou City, Jiangxi Province, was selected as a case study, with seven groups of indoor model tests conducted to consider the effects of different embankment top widths, embankment heights, river water depths, and river flow rates. The test results are as follows: Overtopping failure of earth embankments can be categorised into three distinct stages. The breach formation process can be categorised into three stages: vertical erosion (stage I), breach expansion (stage II) and breach stabilisation (stage III). River water levels and inflow rates were identified as pivotal factors influencing the final morphology of the breach and the flow velocity within it. Conversely, the height of the dike was found to have little influence on the shape of the breach and the flow velocity. The breach width ranges from 6 cm to 12 cm. An increase in water depth, corresponding to a greater difference in water levels on both sides of the river, has been observed to result in a deeper breach and faster widening rate. Elevated water levels have been shown to increase the potential energy of the water, which is subsequently converted into greater kinetic energy during breach formation. This, in turn, increases the flow velocity at the breach. However, a negative correlation has been observed between inflow velocity and flow at the breach. This paper combines the material properties of the embankment to discuss the overtopping failure mechanism and the breach evolution law of homogeneous earth embankments. This provides a basis for preventing and controlling embankment failure disasters.

Abstract: Accurately estimating total accident costs is essential for managing construction safety budgets. While direct costs are well-documented, indirect costs—such as productivity loss, material damage, and legal expenses—are difficult to predict and often overlooked. Traditional ratio-based methods lack accuracy due to variability across projects and accident types. This study introduces a two-tiered machine learning framework for real-time indirect cost estimation. In the first tier, classification models (decision tree, random forest, k-nearest neighbor, and XGBoost) predict total cost categories; in the second, regression models (decision tree, random forest, gradient boosting, and light-gradient boosting machine) estimate indirect costs. Using a dataset of 1,036 construction accidents collected over two years, the model achieved accuracies above 87% in classification and an R² of 0.95 with a training MSE of 0.21 in regression. Compared to conventional statistical and single-step models, it demonstrated superior predictive performance, reducing average deviations to $362.63 and sometimes achieving zero deviation. This framework enables more precise, real-time estimation of hidden costs, promoting better safety investment, reduced financial risk, and adaptive learning through retraining. When integrated with a national accident cost database, it supports ongoing improvement and informed risk management for construction stakeholders.

Abstract: Construction accidents continue to threaten worker safety despite advances in management systems. Existing research catalogs accident attributes but rarely explains how triggers like human error, equipment failure, or procedural lapses interact with project types and tasks. This limits recognition of high-risk scenarios and hampers targeted prevention. To address this, a two-step framework combining Multiple Correspondence Analysis (MCA) and Association Rule Mining (ARM) is proposed. Using the Korean Construction Safety Management Integrated Information (CSI) database, MCA reduces dimensionality and clusters similar accident cases, while ARM extracts context-specific rules linking accident types, causes, and activities. The analysis reveals key patterns: (i) worker negligence during setup or formwork often leads to tool-related cuts; (ii) poor judgment or inadequate waste removal during excavation heightens hit or stuck incidents; and (iii) negligence frequently triggers hit and fall accidents during transportation, dismantling, and finishing. By mapping causes to operational risk factors, the framework supports actionable guidance for daily risk assessments. Safety professionals can align planned tasks with identified risks, enabling proactive interventions such as focused training, stricter supervision, and engineering controls. Thus, the MCA–ARM method establishes a data-driven foundation for improving safety decision-making and reducing construction accidents.

Abstract: Constructing reusable accident-text corpora is hindered by anonymization, heterogeneous sources, and sparse labels, which complicate cross-document event linking. We propose a spatiotemporal lattice–constrained approach that encodes administrative hierarchies and temporal granularity, defines domain-informed consistency criteria, estimates anchor weights via smoothing with monotonic projection, and fuses signals using a constrained monotonic network with explicit probability calibration. An active-learning decision rule—combining maximum probability with a probability-gap criterion—supports scalable automatic labeling, and controlled augmentation leverages instruction-tuned LLMs under lattice constraints. Experiments show competitive ranking (Hit@1 = 41.51%, Hit@5 = 77.33%) and discrimination (ROC-AUC = 87.34%), with the best F1 (62.46%). The method yields the lowest calibration errors (Brier = 0.14; ECE = 1.97%), maintains performance across sources, and exhibits the smallest F1 fluctuation across thresholds (Δ = 1.7%). In deployment-oriented analyses, it auto-labels 77.7% of cases with 97.5% accuracy among high-confidence outputs while routing 22.3% to review, where the true-positive rate is 81.4%. These findings indicate that integrating structured constraints with calibrated probabilistic fusion enables accurate, auditable, and scalable event linking for accident-corpus construction.

Abstract: The present contribution aims to analyze and highlight the potential of piezoelectric materials in actuation and sensing duties performing reliable high precision outcomes in cutting-edge applications including medical involvements. These engage high precision, actuations of robotized procedures as well as monitoring and controlling various physical phenomena via structural sensing. The characteristics of these applications project en-hanced, precision machinery and robotic tools, medical robotic precise interventions and high accuracy structural sensing. The paper exposed, analyzed, reviewed and discussed different subjects related to piezoelectric actuators involving their displacement and posi-tioning strategies, piezoelectric sensors, medical applications of piezoelectric actuators and sensors including robotic actuation for medical interventions, structural sensing in monitoring of healthcare wearable tools. Discussions among others on the advantages and limitations of piezoelectric sensors and actuators in general as well as future research perspectives in medical involvements, are also presented at the end of the article. The spe-cific features in the illustrated applications reflect crucial behaviors in robotic actuation for medical interventions, structural sensing in monitoring of healthcare wearable tools, and control of various structural physical occurrences.

Abstract: One of the biggest risks to safety on offshore platform safety is the ignition of high pressure natural gas streams. Currently, the size and number of fugitive emissions on offshore platforms is unknown and methods used to detect fugitives have significant shortcomings. To investigate the frequency, size and potential impact of fugitives, a data collection exercise was conducted using incidents reported, leak survey data and independent measurements. The size and number of fugitives on offshore facilities were simulated to investigate likely areas of safety concern. Incident reports indicate in 2021 there were 113 reports of gas leaks on 1119 offshore facilities suggesting 0.02 fugitives per Type 1 facility (older, shallow water platforms) and 0.31 fugitives per Type 2 facility (larger deeper-water facilities). Leak survey data report 12 fugitives per Type 1 facility (average emission 0.6 kg CH4 h-1 leak-1) and 15 fugitives per Type 2 facility (average emission 1.5 kg CH4 h-1 leak-1). Reconciliation of direct measurements with a bottom-up model suggests that the number of fugitive emissions generated from the leak report data is an underestimate for Type 1 platforms (44 fugitives facility-1; average emission 0.6 kg CH4 h-1 leak-1) and in general agreement for the Type 2 platforms (15 fugitives facility-1; average emission 1.5 kg CH4 h-1 leak-1). Analysis of the fugitive emission rates on an offshore platform suggests that gas will not collect to explosive concentration if any air movement is present (> 0.36 mph), however, large volumes of air (~600 m3) near representative leaks on the working deck could become explosive in hour-long zero-wind conditions. We suggest that wearable technology could be employed to indicate gas build up, safety regulations amended to consider low-wind conditions and real-world experiments are conducted to test assumptions of air mixing on the working deck.

Abstract: Requirements elicitation is a fundamental activity in a software development process, which means it needs to be carried out effectively, aiming the requirements to perform the behavior expected by the software. Problem: The need for assertiveness in requirements elicitation tasks can impact subsequent activities of software development. Solution: It is proposed an experiment focusing on the security non-functional requirement expressed in the ISO/IEC 25010:2023 Standard through Large-Language Models (LLMs) using Behavior-Driven Development (BDD). Method: Via an experiment, this study is qualitative and descriptive. It is possible to analyze, through statistical tests, the effectiveness of LLMs to elicit non-functional requirements. Summarization of Results: The study presented the effectiveness of using pre-defined prompts for test automation through machine learning. Contributions and impact: Through this experiment, it is possible to present an effective collaboration between human and artificial intelligence, generating time savings for automatic generation of tests.

Abstract: This paper introduces Contextual Object Grouping (COG), a specific computer vision framework that enables automatic interpretation of technical security diagrams through dynamic legend learning for intelligent sensing applications. Unlike traditional object detection approaches that rely on post-processing heuristics to establish relationships between detected elements, COG embeds contextual understanding directly into the detection process by treating spatially and functionally related objects as unified semantic entities. We demonstrate this approach in the context of Cyber-Physical Security Systems (CPPS) assessment, where the same symbol may represent different security devices across different designers and projects. Our proof-of-concept implementation using YOLOv8 achieves robust detection of legend components (mAP50 ≈ 0.99, mAP50–95 ≈ 0.81) and successfully establishes symbol–label relationships for automated security asset identification. The COG framework introduces a new ontological class — the contextual COG class that bridges atomic object detection and semantic interpretation, enabling intelligent sensing systems to perceive context rather than infer it through post-processing reasoning. This advancement supports real-time security assessment and building automation applications in smart sensing environments.

Abstract: A condition-based maintenance modeling approach for a multi-state system under competing failures and imperfect repairs is proposed. The multi-state system will experience three states (normal, defective and failed) through its lifecycle caused by two competing failure processes, i.e., natural degradation and external shocks. If the system becomes defective, an imperfect repair is adopted to restore the system to a normal state. Firstly, imperfect repairs aimed at addressing defects are mathematically characterized, based on which two kinds of system renewal scenarios and corresponding occurrence probabilities are simulated and derived, respectively. Subsequently, the cost of downtime caused by hidden failures are deduced. Then, a maintenance model of the expected cost rate is constructed and the optimal inspection period that minimizes the expected cost rate is determined. Finally, the correctness and effectiveness of the constructed maintenance model are verified by a numerical example.