Search

The paper presented introduces an innovative accident prevention system that employs deep learning models and sensors to identify and alert drivers who lose concentration while driving for a variety of reasons. The system targets drowsiness, cell phone use, and alcohol consumption, which are among the leading causes of automobile accidents. The proposed solution employs neural networks to identify specific patterns associated with driver inattention and generates an audible alert to refocus the driver's attention on the road. In addition, the system utilizes alcohol-detection sensors, as alcohol consumption is another significant cause of accidents. This system seeks to reduce the number of casualties by enhancing road safety considering the high number of daily collisions, which are primarily caused by speeding. The paper describes the design, architecture, and implementation of the system on a modest scale to provide a lifesaving, cost-effective solution. [ABSTRACT FROM AUTHOR]

This study addresses challenges associated with hydrogen's physio-chemical characteristics and the need for safety and public acceptance as a precursor to the emerging hydrogen economy. It highlights the gap in existing literature regarding lessons learned from events in the green hydrogen production value chain. The study aims to use the documented lessons learned from previous hydrogen-related events to assist in enhancing safety measures and to guide stakeholders on how to avoid and mitigate future hydrogen-related events. Given the potential catastrophic consequences, robust safety systems are essential for hydrogen economy development. The work underscores the importance of human and operational factors as root causes of these events. The paper recommends establishing a specialized hydrogen-related event database to support risk assessment and risk mitigation, thus catering to the growing hydrogen industry's needs, and facilitating quick access to critical information for stakeholders in the private and public sectors. • 82 hydrogen-only events were identified from available databases. • From the identified hydrogen events, lessons learned are defined and recommendations provided. • Cause identification of events that could result in damaging consequences. • Maintenance operations, poor process management and human error are major causes of events. • Main value chain components related to hydrogen events are identified. [ABSTRACT FROM AUTHOR]

• A railway operational hazard knowledge graph modelling method is developed. • A knowledge graph embedding-based hazard prediction method is proposed. • A procedure of formulating targeted hazard control measures is shown. • An application to real accident data demonstrates the effectiveness of the proposed approach in predicting hazards and assisting in making accident prevention decisions. Railway operational accidents are usually caused by the domino effects of hazards. Predicting such hazards before accidents is an essential way to prevent operational accidents of railways. Various railway operational hazards constitute a heterogeneous relationship network due to their interactions. It is useful to predict hazards from such a network. In this paper, a novel knowledge graph-based hazard prediction approach is proposed, aiming to capture hazards in advance for blocking potential accident causation paths. This approach serves as a powerful supplement to classical ways of predicting railway accident information. Its originality lies in the application of knowledge graph embedding-based link prediction theory to railway operational hazard prediction, by means of a translation-based embedding method adapting to the relational features of hazards. It also provides a feasible way to construct the railway operational hazard knowledge graph. The outcomes of this approach could offer railway operators the basis of decision regarding accident prevention. An example of application to a set of real railway operational accident data in the UK is presented. The results show that this approach is effective in terms of predicting hazards and assisting in developing targeted hazard control measures. [ABSTRACT FROM AUTHOR]

With the rapid development of global hydrogen energy industry, the issue of hydrogen energy safety has emerged, it is prone to cause a serious explosion accident once hydrogen leaks. Therefore, it is urgent to develop efficient suppression media to reduce the severity of hydrogen explosion accidents. In this paper, a new compounded powder composed of ordinary ultra-fine dry powder extinguishing agent (ODPEA) and zinc hydroxystannate (ZHS) is prepared. On the basis of material preparation, an experimental system of hydrogen explosive suppression is established to explore the inhibitory effect of ODPEA-ZHS. In terms of explosion overpressure, the results show that the peak overpressure suppression rates of ODPEA-ZHS are 90.12 %, 92.31 %, and 93.04 % for hydrogen release pressures of 2.0, 4.0, and 6.0 MPa, respectively. Besides, the flame front propagation velocity under the action of ODPEA-ZHS reaches a suppression rate of 40.55 %. Furthermore, the overpressure suppression efficiency of ODPEA-ZHS exceeds 90 % when ignites 1.0 m axially from leak port. Ultimately, the physicochemical synergistic inhibition mechanism of ODPEA-ZHS is revealed by combining material characterization and pyrolysis results. This study can provide effective countermeasures for accident prevention in hydrogen energy industry, and also contribute to the establishment of hydrogen energy safety standards and norms. [ABSTRACT FROM AUTHOR]

As an accident prevention mechanism, Port State Control (PSC) is essential for the development of maritime transportation and security. To evaluate the effectiveness of PSC and provide recommendations for its enhancement, we develop Dynamic Bayesian Network (DBN) models using the latest five inspection records from the Tokyo and Indian Memorandum of Understandings (MoUs). These models incorporate a hidden variable called "ship condition" to represent the overall influence of four ship characteristic factors. Additionally, a "risk level" hidden variable is determined by two inspection results during each inspection: detention and the number of deficiencies. Two analyses are conducted in this paper. One aims to identify changes in risk levels, thereby investigating the effectiveness of dynamic inspections. The other involves comparing inspected and uninspected ships, with the goal of assessing the impact of PSC and ship condition on accident type, consequences, and severity. The results indicate that the inspection effects of the two MoUs demonstrate the same changing pattern, with the ship risk levels initially rising and then falling. However, the higher detention rate of the Indian MoU justifies its lower level of risk. Ships with inspection records are less likely to encounter capsizing accidents and have a lower probability of being taken out of service, while collision accidents and casualties are more likely to occur. The findings provide valuable insights and practical suggestions on how to enhance the effectiveness of PSC. • It investigates the dynamic changes of ships' risk levels and their impacts on ship accidents. • Dynamic BNs are developed considering "ship condition" and "risk level" measuring by five consecutive PSC inspections. • It analyzes and discusses the effectiveness of dynamic inspections on ship risk and accident consequences. • It discloses the risk level pattern of rising first and then decreasing with the increase of inspection times. [ABSTRACT FROM AUTHOR]

• Analyzed the cause of secondary explosion accident in Hushan Gold mine in China. • Clarified the direct and indirect causes of the accident. • Calculated and verified the direct cause of the secondary explosion accident. • Put forward the suggestions for preventing secondary explosion accidents in mines. Explosion accidents often occur during mining, especially sudden secondary explosions, which pose a serious threat to the life and property safety of employees. Based on the development process and consequences of typical secondary explosion accidents in Hushan Gold Mine, Qixia City, Shandong Province, China, this paper uses accident analysis model and cone measurement calculation method to determine the direct cause of secondary explosion accidents. The main conclusions are as follows: The HFACS-CM model is used to analyze the causes of secondary explosion from five aspects: external environment, organizational influence, unsafe leadership, the prerequisite conditions of unsafe behavior and unsafe behavior. It is found that the CO ignition explosion in the mining process is the direct cause of secondary explosion. Then, combined with the experimental data of the cone measuring instrument, the field CO amount was calculated, and the M CO ≥ 101.4 m3 was obtained, indicating that the CO production did reach the condition of explosion range, and the analysis results of the model were verified. Through HFACS-CM model analysis and calculation verification, the key causes of secondary explosion accidents in such mines are found and lessons are learned, which provides an effective reference for the effective prevention of deflagration accidents in the field of mine safety. [ABSTRACT FROM AUTHOR]

• One hundred ninety-four data-driven articles are comprehensively examined from the past decade in four aspects: Paradigm, Model, Data Source, and Purpose. • The mapping between ML approaches and safety purposes is established. • Some future research directions of ML in the field of safety are proposed. • This paper describes the possible bias in the past data-driven safety research. Data-driven intelligent technologies are promoting a disruptive digital transformation of human society. Industrial accident prevention is also amid this change. Although many emerging technologies, such as machine learning (ML), are extensively employed in workplace safety, these approaches need to fit the intended safety purpose of accident analysis, risk assessment, adverse outcome prediction, or anomaly detection. Hence, examining the "real-world" need for accident prevention and the advantages of emerging data-driven methodologies to better integrate them is necessary. This study provides a systematic review to clarify the current research status, existing problems, and future insights into these evolving technologies in accident prevention. We present notable gaps and barriers in data-driven accident prevention by analyzing 194 published studies from four perspectives: Paradigm, Model, Data Source, and Purpose. The results demonstrate (1) lack of a systematic framework to guide the application of Big Data (BD) in the field of safety; (2) few prior studies have considered model interpretability; (3) more proactive data needs to be incorporated into accident analysis; (4) safety-related data and domain knowledge need to be further integrated; (5) some recent data-driven techniques are unexplored in safety science. Further, the future research opportunities are discussed based on these findings. Such review may help clarify the mapping of data-driven tasks to safety goals to accelerate the uptake of data-driven technologies in safety or accident analysis research. [ABSTRACT FROM AUTHOR]

• Accident modification functions for traffic law enforcement are compared. • All functions show that more enforcement improves safety. • Differences-in-differences estimates capture both increases and decreases in enforcement. • A decrease in enforcement worsens road safety. Traffic law enforcement is a road safety measure whose effects on accidents or injuries is best described by means of a function rather than a point estimate. An informative function should comprise both increases and decreases in enforcement. Currently available accident modification functions cannot serve this need. A fruitful approach to developing accident modification functions covering both increases and decreases in enforcement is differences-in-differences estimates based on multivariate accident prediction models. The paper explains how to develop such estimates and illustrates them. The interpretation of the results of empirical studies can be informed by a game-theoretic model of the effects of enforcement, previously published in Accident Analysis and Prevention (Bjørnskau and Elvik 1992, 507–520). [ABSTRACT FROM AUTHOR]

• A propagation method with risk entropy as the information carrier is proposed based on the improved system dynamics model. • Two different types of dynamic risk nodes, energy diffusion and energy conduction are identified. • The prediction accuracy of dynamic risk nodes of the improved model is increased. • The prediction of the path of energy-conducting type risk evolution direction is increased. The LNG unloading system is an important transit station for LNG storage, processing and outgoing transmission. The main processes include ship unloading, storage, gasification and outgoing transmission, BOG condensation, flare venting and other processes, which involve intensive personnel operation and safety management activities. Once LNG is leaked, frostbite will happen to personnel and fire and explosion will occur when encountering ignition sources, which will cause serious consequences that are difficult to bear. The risk path of the static safety evaluation method is based on qualitative judgment, and the dynamic evolution direction of the LNG unloading system risk factors is not accurately predicted, so how to accurately predict and warn the risk path during the risk evolution is a key issue. In this paper, based on the improved system dynamics model, a propagation method with risk entropy as the information carrier is established to identify two different types of dynamic risk nodes, energy diffusion and energy conduction. Compared with the traditional dynamics model, the prediction accuracy of dynamic risk nodes of the improved model is increased by 22%, 20% and 14% for the unloading process, storage process and loading and transfer process, respectively. The prediction of the path of energy-conducting type risk evolution direction is increased by 29.3%, 32.4% and 30%, respectively. The simulation results are beneficial to the dynamic risk control and accident prevention of LNG unloading system, and provide new ideas for natural gas energy safety and security. [ABSTRACT FROM AUTHOR]