Search Results (8)

Aviation safety remains a critical area of research, requiring accurate and efficient classification of incident reports to enhance risk assessment and accident prevention strategies. This study evaluates the performance of three deep learning models, BERT, Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) for classifying incidents based on injury severity levels: Nil, Minor, Serious, and Fatal. The dataset, drawn from ATSB records covering the years 2013 to 2023, consists of 53,273 records and was used. The models were trained using a standardized preprocessing pipeline, with hyperparameter tuning to optimize performance. Model performance was evaluated using metrics such as F1-score accuracy, recall, and precision. Results revealed that BERT outperformed both LSTM and CNN across all metrics, achieving near-perfect scores (1.00) for precision, recall, F1-score, and accuracy in all classes. In comparison, LSTM achieved an accuracy of 99.01%, with strong performance in the “Nil” class, but less favorable results for the “Minor” class. CNN, with an accuracy of 98.99%, excelled in the “Fatal” and “Serious” classes, though it showed moderate performance in the “Minor” class. BERT’s flawless performance highlights the strengths of transformer architecture in processing sophisticated text classification problems. These findings underscore the strengths and limitations of traditional deep learning models versus transformer-based approaches, providing valuable insights for future research in aviation safety analysis. Future work will explore integrating ensemble methods, domain-specific embeddings, and model interpretability to further improve classification performance and transparency in aviation safety prediction. Full article

Gas distribution stations (GDSs), pivotal nodes in long-distance natural gas transportation networks, are susceptible to catastrophic fire and explosion accidents stemming from system failures, thereby emphasizing the urgency for robust safety measures. While previous studies have mainly focused on gas transmission pipelines, GDSs have received less attention, and existing risk assessment methodologies for GDSs may have limitations in providing accurate and reliable accident probability predictions and fault diagnoses, especially under data uncertainty. This paper introduces a novel dynamic accident probability assessment framework tailored for GDS under data uncertainty. By integrating Bayesian network (BN) modeling with fuzzy expert judgments, frequentist estimation, and Bayesian updating, the framework offers a comprehensive approach. It encompasses accident modeling, root event (RE) probability estimation, undesired event (UE) predictive analysis, probability adaptation, and accident diagnosis analysis. A case study demonstrates the framework’s reliability and effectiveness, revealing that the occurrence probability of major hazards like vapor cloud explosions and long-duration jet fires diminishes significantly with effective safety barriers. Crucially, the framework acknowledges the dynamic nature of risk by incorporating observed failure incidents or near-misses into the assessment, promptly adjusting risk indicators like UE probabilities and RE criticality. This underscores the importance for decision-makers to maintain a heightened awareness of these dynamics, enabling swift adjustments to maintenance strategies and resource allocation prioritization. By mitigating assessment uncertainty and enhancing precision in maintenance strategies, the framework represents a significant advancement in GDS safety management, ultimately striving to elevate safety and reliability standards, mitigate natural gas distribution risks, and safeguard public safety and the environment. Full article

A jet flame occurs when the release of flammable gas or liquid ignites, resulting in a long, intense, and highly directional flame. This type of fire is commonly associated with industrial incidents involving pipelines, storage tanks, and other pressurized equipment. Jet fires are a significant concern in the oil and gas industry due to the handling and processing of large volumes of flammable hydrocarbons under pressure. The new computational method presented here includes several aspects of hydrogen jet flame accidents and their mitigation: the CFD simulation of a hydrogen jet flame using the HyRAM code and Fire Dynamics Simulator (FDS) software 5.0 using a large eddy simulation (LES) turbulence model; the calculation of the gaseous mixture’s thermo-physical properties using the GASEQ thermochemical code; the calculation of convective and radiative heat fluxes using empirical correlation; and a heat transfer simulation on the pipe thermal barrier coating (TBC) using COMSOL Multiphysics software 4.2a during the heating phase. This method developed for the ceramic blanket was validated successfully against the previous experimental results obtained by Gravit et al. It was shown that a jet fire’s maximum temperature obtained using FDS software was similar to that obtained using GASEQ thermochemical software 0.79 and HyRAM software. The TBC’s surface temperature reached 1945 °C. The stainless steel’s maximal temperature reached 165.5 °C. There was a slight decrease in UTS at this temperature. Full article

Accidental hydrogen releases from pipelines pose significant risks, particularly with the expanding deployment of hydrogen infrastructure. Despite this, there has been a lack of thorough investigation into hydrogen leakage from pipelines, especially under complex real-world conditions. This study addresses this gap by modeling hydrogen gas dispersion, jet fires, and explosions based on practical scenarios. Various factors influencing accident consequences, such as leak hole size, wind speed, wind direction, and trench presence, were systematically examined. The findings reveal that both hydrogen dispersion distance and jet flame thermal radiation distance increase with leak hole size and wind speed. Specifically, the longest dispersion and radiation distances occur when the wind direction aligns with the trench, which is 110 m where the hydrogen concentration is 4% and 76 m where the radiation is 15.8 kW/m² in the case of a 325 mm leak hole and wind under 10 m/s. Meanwhile, pipelines lacking trenching exhibit the shortest distances, 0.17 m and 0.98 m, at a hydrogen concentration of 4% and 15.8 kW/m² radiation with a leak hole size of 3.25 mm and no wind. Moreover, under relatively higher wind speeds, hydrogen concentration stratification occurs. Notably, the low congestion surrounding the pipeline results in an explosion overpressure too low to cause damage; namely, the highest overpressure is 8 kPa but this lasts less than 0.2 s. This comprehensive numerical study of hydrogen pipeline leakage offers valuable quantitative insights, serving as a vital reference for facility siting and design considerations to eliminate the risk of fire incidents. Full article

Risk treatment is an effective way to reduce the risk of oil pipeline accidents. Many risk analysis and treatment strategies and models have been established based on the event tree method, bow-tie method, Bayesian network method, and other methods. Considering the characteristics of the current models, a risk treatment strategy model for oil pipeline accidents based on Bayesian decision network (BDNs) is proposed in this paper. First, the quantitative analysis method used in the Event-Evolution-Bayesian model (EEB model) is used for risk analysis. Second, the consequence weights and initial event likelihoods are added to the risk analysis model, and the integrated risk is obtained. Third, the risk treatment strategy model is established to achieve acceptable risk with optimal resources. The risk treatment options are added to the Bayesian network (BN) risk analysis model as the decision nodes and utility nodes. In this approach, the BN risk analysis model can be transformed into a risk treatment model based on BDNs. Compared to other models, this model can not only identify the risk factors comprehensively and illustrate the incident evolution process clearly, but also can support diverse risk treatment strategies for specific cases, such as to reduce the integrated risk to meet acceptable criterion or to balance the benefit and cost of an initiative. Furthermore, the risk treatment strategy can be updated as the risk context changes. Full article

The transportation infrastructure for petroleum products contains complex pipeline systems, developed on a global scale and totaling investments of hundreds of millions of dollars. The operation and maintenance of these systems have to be performed in relation to the analysis of incidents of various types, which take place in various areas of the world. The present paper aims to analyze in as much detail as possible, from a statistical point of view, the case of the pipeline system for petroleum products in Romania in order to streamline the operation of this critical infrastructure for Romania. Through the statistical tools, we established the hierarchies of the causes of the analyzed incidents, weights of the effects generated by these sources of accidents, and correlations between various parameters, in order to create a useful plan of measures and actions in the efficient operation of the pipeline system. The importance and topicality of the subject is also demonstrated by the major negative impact of the accidents in this sector, through product leaks from pipes in the soil and in watercourses, which generate significant pollution values, thus influencing the balance of the environment. Full article

This study employs a balanced panel of data which consists of 1281 firm-year pipeline accidents and incidents at a disaggregate level and 190 firm-year pipeline events at an aggregate level for 19 firms during the observation period between 2007 and 2016. This study examines the relationships among environmental accidents and incidents, environmental consciousness, and financial performance. Given that environmental consciousness acts as an overarching environmental context on the relationship between the accidents, incidents, and financial performance and could be relevant to shareholders to identify the weight of these accidents and incidents, this study carefully investigates how environmental consciousness moderates the relationship between pipeline accidents, incidents, and financial performance. This study applies the theoretical assumption of both corporate social responsibility (CSR) and corporate social irresponsibility, both of which explain the relationship between financial performance and the events that positively or negatively affect stakeholders. This study employs nested regression analyses with the fixed effects model to test the time-series panel data. The results show that environmental consciousness has an expected significant negative effect on financial performance, whereas pipeline accidents and incidents have no expected negative effect on financial performance. One surprising finding is that pipeline accidents and incidents weighted with environmental consciousness present a significant positive relationship with financial performance, suggesting that potential contextual factors should be considered to explain such an unexpected finding. Full article

Critical infrastructure such as power and water delivery is growing rapidly in the developing world and there are developed assets that must be maintained in developed nations. One underground component that is difficult to inspect is water supply pipelines. Most of the water line accidents occur in buildings is due to pipeline damage. To minimize accidental loss, a risk assessment method is needed to continuously assess risk and report any abnormality for preventative maintenance. In this work, a blended hierarchical fuzzy logic model for water supply pipeline risk index assessment is proposed. Four important parameters are inputs to the proposed blended hierarchical fuzzy logic model. The blended hierarchical fuzzy logic model dramatically reduces the number of conditions in the rule base. Rule reduction is important because the transparency and interpretation are compromised by an overly large set. Further, it is challenging to accurately design a large number of rules because rule design requires expert knowledge and uncertainty in predictions can lead to unforeseen incidents. A blended hierarchical fuzzy model is designed with a structure that takes fewer rules as compared to conventional fuzzy logic. For the four parameters, the proposed model takes 85 rules and for the same four parameters, the conventional fuzzy logic approach requires 900 rules. In this paper, four parameters are considered because these are available measurements. The proposed reduction method is also applicable for systems with more parameters. The numbers of rules increase exponentially in the conventional fuzzy logic as new parameters enter into the system. The blended hierarchical fuzzy logic is deployed on a water distribution network to compute the risk index of supply pipelines. The results indicate improved performance of the blended hierarchical fuzzy logic. This approach is usable in practical applications where the calculated risk index values of the water supply pipeline are plotted on a geographic information system (GIS) map to provide a graphical interface for the caretaker. The risk index visualization is necessary to trace the risk index location and to take preemptive measures to avoid failures. Full article