Search Results (271)

Aviation accidents during the final approach phase of transport aircraft account for nearly half of all accidents in the flight stage, with unstable approaches being a notable contributing factor. In related accident analysis research, traditional single-parameter threshold monitoring methods have shown difficulty in capturing the complex coupling relationship between kinetic energy and potential energy. This weakness results in insufficient adaptability under variable meteorological disturbances and poor risk identification. To address this limitation, this study establishes an evaluation framework based on the concepts of “energy altitude” and “balance energy, shifting the analytical focus of aircraft state variations to energy evolution. A hybrid dynamic safety boundary function is further constructed by integrating flight mechanics principles with civil aviation regulatory constraints. This boundary integrates a height attenuation mechanism, enhancing adaptability to environmental disturbances. The study adopts QAR flight data of Boeing aircraft collected at an international airport from 2015 to 2020 as the database for machine learning modeling, and selects two additional independent flight datasets under calm-air and wind-shear conditions respectively for model verification. The research results indicate that this framework provides a robust theoretical foundation for the early identification of unstable approaches and provides actionable insights for optimizing energy control strategies, thus improving flight safety under complex operational conditions. Nevertheless, the verification only relies on two groups of typical flight cases under limited meteorological conditions, which restricts the generalizability of the research conclusions. Follow-up work will expand multi-type and multi-meteorological flight samples to carry out quantitative performance evaluation and further optimize the model’s practicality under diverse operational environments. Full article

Maritime accident analysis increasingly uses machine learning to support safety management, but many existing studies focus on single-output prediction, such as accident-occurrence probability, severity class, near-miss frequency, or one specific consequence. This study proposes a data-driven decision-support framework based on a Multi-Input Multi-Output Artificial Neural Network (MIMO-ANN) for the simultaneous prediction of multiple maritime accident consequences. A dataset of 582 recorded accident cases is constructed by integrating SafePASS project records with consequence, severity, and structural-damage information from the literature. The dataset includes 15 input variables covering ship characteristics, operational context, environmental conditions, accident type, and geographical zone and 15 consequence outputs covering structural damage, casualties, emergency-response indicators, total loss, and secondary consequence/escalation mechanisms. The ANN is trained using the Scaled Conjugate Gradient (SCG) algorithm and evaluated under different network configurations and data-partitioning strategies. The best-performing model uses 30 hidden neurons with a 60/20/20 split, achieving a correlation coefficient (R) equal to 0.9249 and a mean squared error (MSE) equal to 0.0240 for testing, and a R equal to 0.9278 and a MSE equal to 0.0231 for validation. Ten-fold cross-validation further confirms internal predictive stability, with mean testing R equal to 0.8803 ± 0.0827 and MSE equal to 0.0445 ± 0.0478. Permutation-based sensitivity analysis shows that accident type, zone, flag, natural light, environment, and visibility are key drivers of predicted consequences, whereas vessel-specific parameters have a secondary, context-dependent influence. The framework should be interpreted as predicting the relative likelihood, severity, or magnitude of accident consequences in recorded or scenario-defined accident cases, not the probability of accident occurrence. Future work should address dataset imbalance, include near-miss and nonserious records, incorporate richer AIS and metocean data, integrate exposure data, and validate the framework using independent accident datasets. Full article

To improve emergency response efficiency in passenger ship fire accidents and ensure the life safety of passengers and crew, this paper proposes a dynamic route planning model for passenger ship fire evacuation that accounts for fire spread. Firstly, a passenger ship fire spread model is established based on the field simulation theory, and an emergency evacuation network model is constructed by determining the evacuation network topology from the fire propagation process. Secondly, the factors affecting emergency evacuation route planning during fire spread are analyzed, and a multi-objective optimization model for dynamic evacuation routes is developed. Thirdly, an improved ant colony optimization algorithm is designed to solve the problem. Finally, using the RP1 vessel from the publicly available ship evacuation dataset of the EU Seventh Framework Program SAFEGUARD project as a case study, simulation and comparative experiments are conducted. The results show that, in medium- and large-scale evacuation problems, the proposed method consistently maintains higher computational efficiency compared with the DABD algorithm and the FOA. In terms of objective optimization, it demonstrates that the proposed method has better effectiveness and feasibility than the shortest-path evacuation strategy, as it minimizes evacuation cost while satisfying assembly station capacity constraints and achieves a more balanced utilization of all emergency exits. Full article

Proactive accident prediction is a fundamental prerequisite for the environmental and social sustainability of high-risk sectors. Accident prediction research has expanded rapidly across transportation, construction, fire safety, chemical/process industries, and mining, yet many models that perform well in offline benchmarks fail in field deployment because algorithm capability, data regime, and operational constraints are misaligned. This review synthesizes cross-industry evidence on how accident prediction is practiced under distinct data conditions, including spatiotemporal, multimodal, and data-scarce settings, and compares mainstream methods from statistical baselines to machine learning and deep learning in terms of deployability rather than accuracy alone. Building on this synthesis, we propose the Model–Data–Scenario Adaptation (MDSA) framework, a systems-level protocol that operationalizes deployment-aware model selection through a multi-dimensional scoring rubric and an iterative validation loop. MDSA balances predictive performance with interpretability, robustness, data dependency, and implementation cost. A chemical industry case study demonstrates how accuracy-centric selection can fail operationally and how MDSA yields a more viable choice under real constraints. The framework ultimately facilitates long-term sustainable risk governance by balancing predictive performance with operational constraints, thereby contributing to the United Nations Sustainable Development Goals (SDGs 3, 8, 9, and 11). Full article

It is of great significance for accident prevention to explore the causes and evolution laws of ship collisions at sea. The paper aims to constructs a systematic MMEM-FTA integrated analysis framework and applies the framework to analyze the causes of ship collisions in Taizhou coastal waters. Ship collision cases in Taizhou coastal waters from 2017 to 2025 are collected, and a statistical analysis is conducted on the characteristics of collision accidents. Under the MMEM frame, 16 accident influencing factors are identified from four aspects: personnel negligence, ship failure, management failure and environmental degradation. Based on FTA, a fault tree diagram of ship collision accidents in Taizhou coastal waters is constructed. Results of both quantitative and quantitative analysis show that the structural importance of ship failure, management failure and complex environment is the largest and an event with higher probabilistic and critical importance is “Unseaworthiness.” These mentioned events are main reasons for ship collision accidents. Suggestions on risk control options (RCOs) for accident prevention are put forward under the MMEM frame. The proposed MMEM-FTA integrated analysis framework is feasible for accident causation analysis. This research can provide theoretical and practical supports for identifying causes of ship collisions, for elucidating the evolution mechanism of accidents and for taking targeted measures to prevent accidental risks. Full article

Plunger pumps serve as core power equipment in oilfield water injection systems, where their reliable operation directly affects crude oil recovery efficiency and production safety. Failures such as mechanical wear and seal leakage can cause injection pressure fluctuations, increased energy consumption, and even pipeline burst accidents. This study addresses the challenges in plunger pump fault diagnosis, including the difficulty in capturing multi-scale fault features, interference from redundant information in high-dimensional feature spaces, and high model computational complexity. We propose a lightweight fault diagnosis approach called Multi-scale Attention Neural Network (MSLAN), which combines multi-scale convolution and attention mechanisms. In this model, a Separable Multi-scale Fusion Module (SMSF) employs parallel multi-branch convolutional kernels to acquire fault signatures across multiple scales, while computational overhead is reduced through depthwise separable convolution and shared pointwise convolution. Additionally, a Multi-Branch Parallel Attention Module (MBPA) is introduced to finely model complex inter-channel dependencies through a four-branch parallel structure, enhancing the perception of key features and suppressing redundant information. Experimental results on a self-constructed plunger pump dataset, the Case Western Reserve University bearing dataset, and the Southeast University gearbox dataset demonstrate that MSLAN achieves F1-scores of 88.95%, 98.89%, and 99.90%, respectively. While maintaining high diagnostic accuracy, the model exhibits significantly lower parameter count and computational cost compared to baseline models, effectively balancing diagnostic precision and computational efficiency. Ablation studies and visualization analyses further validate the effectiveness of each module. This study establishes an accurate and efficient intelligent fault diagnosis solution for plunger pumps, which is also readily applicable to a broader range of rotating machinery. Full article

As sea ice recedes, the strategic importance of Arctic shipping routes has intensified, yet the complex polar environment poses severe challenges to navigational safety. Through a systematic search of the Scopus database, relevant key studies in both English and Chinese were identified and selected based on predefined inclusion criteria for in-depth review. The present study establishes a systematic categorization framework to parse existing research on Arctic navigational risk assessment. It structurally analyzes the literature across three core dimensions: sea ice characteristics, accident statistical analysis, and risk modeling methodologies. Addressing current limitations in data sparsity, factor coupling, and dynamic forecasting, this study proposes that future research should focus on the construction of structural models for risk interdependencies, multi-source data-driven environmental risk learning, and intelligent small-sample assessment based on Case-Based Reasoning (CBR), which extracts effective risk solutions from limited historical samples by interpreting past navigational successes and failures to improve decision quality. This review aims to provide a comprehensive reference for developing a systematic and intelligent risk assessment architecture for Arctic shipping. Full article

The basic renovation of old urban communities is an important livelihood project for urban renewal, but there are many problems in the decision-making of renovation schemes, such as strong dependence on experience, lack of quantitative basis for multi-objective trade-off, and difficulty in describing residents’ risk attitude. Combining Case-Based Reasoning (CBR) and utility theory, this paper constructs a set of intelligent decision support models driven by data and knowledge. First of all, through literature analysis and expert investigation, a decision-making index system is established, which includes four dimensions and 16 quantitative indicators: policy and financial support, residential conditions and needs, residents’ consensus and social coordination, and implementation management and long-term maintenance. Secondly, the framework representation method is used to describe the reconstruction case, a hybrid retrieval strategy combining inductive retrieval and nearest-neighbor retrieval is designed, and the subjective and objective data combination weights are calculated by using AHP and the entropy method. On this basis, a loss utility function and risk aversion coefficient based on accident and public opinion data (a = 0.02) are introduced to modify the similarity calculation results to describe the risk avoidance behavior of decision-makers. Through 40 real renovation projects, a case base is built, and two types of target cases, “typical inclusive” (F5) and “key renovation” (F35), are selected for empirical verification. The results show that the model can effectively retrieve similar cases, and the similarity ranking changes in line with risk aversion expectations after utility correction. Taking F5 as an example, by reusing and revising the reconstruction scheme of a similar case, targeted suggestions are generated, which give consideration to safety, economy and operability. This model provides a new quantifiable and reusable method for scientific decision-making in basic renovation of old residential areas. Full article

Masonry structures are widely used in civil engineering due to their favorable load-bearing capacity and construction efficiency; however, the threat posed by long-duration blast loads from industrial accidents and large-yield explosions has become increasingly prominent. Existing research has primarily focused on the response of masonry walls under conventional short-duration explosions, while systematic investigations remain limited regarding the differentiated failure mechanisms induced by long-duration blasts. To address this gap, this study adopts and validates a full-scale simplified micro-modeling approach for clay brick masonry walls using LS-DYNA. The model enables systematic comparison of long-duration blast loads and conventional blast loads simulated by the CONWEP method under equal peak overpressure and equal impulse conditions. Numerical results indicate that, under equal peak overpressure (0.18 MPa), the long-duration blast load induces global deformation and cumulative damage leading to complete collapse, whereas the conventional blast load results in only elastic response. Under equal impulse (13.5 kPa·s), both loads cause severe damage, yet the conventional blast load triggers instantaneous localized fragmentation with a higher collapse rate, while the long-duration blast load governs failure through sustained overpressure-induced global deformation and crack propagation. The comparison of mid-span displacement–time histories across different loading cases further quantifies these distinct failure modes, revealing fundamentally different deformation development rates and collapse characteristics. The key contributions of this study are summarized as follows: A validated simplified micro-model is developed that reproduces the experimental damage patterns of masonry walls. A comparison identifies and mechanistically explains the differentiated failure modes between the two load types. Under the conditions considered in this study, critical transition thresholds of peak overpressure and impulse governing the damage mode shift from minor cracking to global collapse are determined. These findings provide a scientific basis for distinguishing blast-resistant design strategies for masonry structures according to explosion type. Full article

To improve risk control at coal mining faces and reduce accident risks, this study first extracts high–frequency risk factors from 171 valid coal mining face accident cases (2020–2023) and integrates synthesis of the literature to establish a 21–factor risk indicator system covering human–machine–environment–management dimensions, and invites 10 senior experts in coal mine safety–covering mining engineering, safety science and engineering, mine ventilation, geological disaster prevention and coal mine safety management–for evaluation. Secondly, a hierarchical structure of factors is developed based on adversarial interpretive structural modeling (AISM), and the driving force and dependence of each factor are analyzed using the matrix impact cross–reference multiplication applied to a classification (MICMAC). A fuzzy Bayesian network (FBN) model is then constructed with the AISM structure as a topological constraint to clarify factor relationships and quantify the risk propagation uncertainty. Finally, an empirical analysis is conducted using the X Coal Mine. The results indicate that the “illegal and irregular organization of production” is the root control factor. The risk probability of the mining face is 86.1%, with “inadequate specialized prevention and control” having a high occurrence probability, and “illegal operation” and “illegal command” showing the most significant probability changes. Sensitivity analysis identifies “inadequate specialized prevention and control” as the most sensitive factor, which, together with the environmental factors, falls into the Level I unacceptable risk category. This research determines risk control priorities and provides a theoretical basis for coal mine safety management. Full article

Accident reports provide a detailed account of environmental causes, unsafe human behaviors, and subsequent chain reactions. These records serve as essential resources for analyzing accident mechanisms and exploring potential risk patterns within production safety processes. Currently, Graph based Retrieval-Augmented Generation (RAG), which integrates Large Language Models (LLMs) with Knowledge Graphs (KGs), has emerged as a leading approach for complex causal question answering over extensive unstructured accident documentation. However, the application of this technology in the production safety domain still encounters two primary challenges. First, knowledge graph construction using a single granularity fails to capture fine-grained case details and macro-level standard systems. Second, traditional one-step retrieval paradigms lack the capacity to track deep causal chains or interpret the complex logic of multi-factor coupling. To address these limitations, we propose CausalAgent, a hierarchical graph-enhanced multi-agent framework for causal question answering in production safety accident reports. This framework innovatively combines a Hierarchical Causal Graph (HC-Graph) and a Multi-Agent Collaborative Reasoning (MACR) mechanism. Specifically, the HC-Graph employs a two-layer architecture that links a fine-grained instance layer with a national standard causation layer to resolve conflicts in semantic granularity. The MACR mechanism converts complex natural language queries into executable structured queries and logic verification steps through the sequential cooperation of four specialized agents, namely the Graph Parsing Agent, the Problem Analysis Agent, the Query Generation Agent, and the Reasoning Insight Agent. CausalAgent enables in-depth mining of accident causation mechanisms and provides scientific, robust and interpretable intelligent support for data-driven risk assessment and emergency decision-making. Experiments on real-world accident datasets demonstrate that CausalAgent achieves a $100.0\%$ query execution rate and an $87.3\%$ reasoning accuracy, outperforming the SOTA baseline by $45.2\%$ in terms of absolute accuracy. Full article

The construction industry remains among the most hazardous, with workers in horizontal transportation infrastructure facing additional risks from dynamic work zones, live traffic exposure, and variable environmental conditions. Immersive technologies such as Virtual Reality (VR) and Augmented Reality (AR) offer new approaches to accident analysis and prevention, yet their applications toward improving occupational safety in transportation construction have not been comprehensively reviewed. This paper presents a systematic review of 54 studies published between 2016 and 2025 collected from two online databases (Transportation Research International Documentation and Web of Science). This review synthesizes how immersive technologies contribute to occupational risk assessment, safety training, and real-time hazard monitoring in the construction of roads, bridges, tunnels, and work zones. Each study is classified across two dimensions: the immersive medium (VR, AR, etc.) and the operational context within the construction lifecycle (onsite tools, offsite monitoring and planning, simulation-based analysis, and workforce education). This dual classification is the first to systematically map immersive technology applications for occupational safety, specifically within horizontal transportation infrastructure. The findings of this review demonstrate the unique use cases of each immersive medium, revealing that VR is primarily used for controlled experimentation and full-immersion remote analysis, whereas AR and handheld devices are preferred for field-deployed applications. Despite these promising capabilities, widespread adoption remains limited by hardware constraints, challenging field conditions, and organizational resistance. This suggests that future work should focus on safety systems tested in real-world settings and rigorously evaluated by domain experts to enable their integration into standard workplace risk management practices. Full article

Compared with other construction operations, high-altitude operations are more dangerous. Falling from a height is the main type of accident in construction. It is important to study the human risk of falling from height to reduce falling accidents. Based on the Human Factors Analysis and Classification System (HFACS) model, a preliminary evaluation index system for fall risk in building construction was established. Through the Delphi method and sensitivity analysis, the initial indicators were screened, the index factors that did not meet the requirements were removed, and the final human risk index evaluation system was determined. The system includes five first-level indicators and 17 s-level indicators of organizational influence, unsafe supervision, preconditions for unsafe behavior, and unsafe behavior. Subsequently, the analytic network process–entropy weight method (ANP-EWM) is used to subjectively and objectively weight the evaluation indicators, and the combined weight is obtained through game theory. The matter–element extension model is constructed to evaluate the human risk of falling from height in construction. Finally, an empirical analysis is carried out with the Y project as a case study. The novelty of this study lies in integrating human-factor analysis with the matter–element extension model for fall risk assessment in construction, while combining ANP, the entropy weight method, and game theory to balance subjective and objective weighting. The proposed model provides a practical tool for evaluating and controlling human risk in high-altitude construction operations. The results show that the correlation degree calculated according to the matter–element extension model is K₄ = 3.5, and the human risk of falling from height in the construction of Y project has generally reached an excellent level. However, the evaluation level of some evaluation indexes is still low, which is consistent with the actual situation of construction enterprises in Y project. This model provides a direction for the study of human risk assessment of falling from different construction heights. Full article

Renewable energy sources, and wind energy in particular, constitute a central pillar of energy policy at both national and European levels. Nevertheless, the deployment of onshore wind farms is frequently associated with spatial, environmental, and social conflicts, making the evaluation of existing projects imperative. The present study aimed to assess the sustainability of existing onshore wind farms in the Region of Thessaly, with particular emphasis on their spatial planning, technical characteristics, and environmental impacts. The methodological framework consists of four distinct stages: (i) identification and spatial mapping of existing wind farms in the study area, (ii) assessment of the compliance of existing wind installations with the Specific Framework for Spatial Planning and Sustainable Development for Renewable Energy Sources (SFSPSD–RES), (iii) application of the Rapid Impact Assessment Matrix (RIAM) to enable a systematic and comparable evaluation of the impacts of wind installations on specific environmental and anthropogenic parameters, and (iv) estimation of project hazard and operational vulnerability through the application of Operational Risk Management (ORM). Geographic Information Systems (GISs) were employed for data processing and spatial analysis. The assessment showed that 40% of the evaluated wind farms fully comply with all eleven exclusion criteria of the SFSPSD-RES, whereas the remaining 60% show partial compliance, failing to meet between one and three criteria. RIAM results indicate that the most significant adverse impacts (−D and −C) during construction are associated with morphology/soils and the natural environment, mainly due to loss/fragmentation of vegetation and disturbance of fauna, and, in some cases, in areas of increased sensitivity. During operation, the main negative effects (−D and −C) relate to landscape and visual quality, as well as continued disturbance to the natural environment. At the same time, the operation generates important positive effects (+E) on the atmospheric environment through reduced CO₂ emissions. The ORM analysis further shows that the most important risks for most wind farms arise during construction (ORM = 2 and 3), particularly from serious worker accidents during lifting, roadworks, and foundation activities. The study demonstrates that the sustainability of existing wind installations depends on a complex set of spatial, environmental, and technical factors. The proposed framework integrates spatial compliance screening, RIAM-based environmental impact assessment, and ORM-based risk and opportunity evaluation. This connection links the importance of impacts with their operational manageability during construction and operation phases, as well as across sustainability dimensions. Consequently, the study provides a more decision-focused approach for assessing existing wind farms and supporting policy development. Full article

Construction sites implement various safety management activities, including toolbox meetings, risk assessments, and safety knowledge assessments, to reduce accidents. Multiple-choice question (MCQ)-based assessments are widely used to evaluate worker safety competencies. However, the effectiveness of MCQ assessments depends critically on distractor quality; incorrect options must be plausible enough to challenge uninformed respondents while remaining clearly distinguishable from knowledgeable ones. Manual distractor creation requires substantial expertise and is prone to inconsistency, whereas large language models (LLMs) often generate options that lack domain relevance. This paper proposes context-aware multipath adaptive safety scoring (CoMPASS), an algorithm that integrates construction safety domain knowledge with LLM capabilities for MCQ distractor generation. CoMPASS operates through two pathways: CoMPASS-H leverages a hierarchical hazard factor ontology for hazard identification questions, whereas CoMPASS-R uses hybrid retrieval-augmented generation (RAG) for risk control questions. An evaluation using 50 real construction accident cases with a robotic assessment test (RAT) using frontier LLMs as virtual examinees demonstrated that CoMPASS-R achieved a 90% quality pass rate, whereas all baseline methods failed to meet the composite quality criteria. The proposed framework provides a scalable approach to generating assessment content that supports effective safety management at construction sites. Full article