Search Results (8)

Traffic violations, the primary cause of road accidents, threaten public safety by disrupting traffic flow and causing substantial casualties and economic losses. Accurate spatiotemporal prediction of violations offers critical insights for proactive traffic management. While Graph Attention Network (GAT) methods excel in spatiotemporal forecasting, their practical deployment is hindered by prohibitive computational costs when handling dynamic large-scale data. To address this issue, we propose a Lightweight Traffic Violation Prediction with Graph Attention Distillation (LTVPGA) model, transferring spatial topology comprehension from a complex GAT to an efficient multilayer perceptron (MLP) via knowledge distillation. Our core contribution lies in topology-invariant knowledge transfer, where spatial relation priors distilled from the teacher’s attention heads enable the MLP student to bypass explicit graph computation. This approach achieves significant efficiency gains for large-scale data—notably accelerated inference time and reduced memory overhead—while preserving modeling capability. We conducted a performance comparison between LTVPGA, Conv-LSTM, and GATR (teacher model). LTVPGA achieved revolutionary efficiency: consuming merely 15% memory and 0.6% training time of GATR while preserving nearly the same accuracy. This capacity enables practical deployment without sacrificing fidelity, providing a scalable solution for intelligent transportation governance. Full article

Urban underground space construction frequently encounters issues of inadequate prevention and ineffective resistance to various disturbances, resulting in safety accidents that are difficult to recover from. Resilience pertains to a system’s capacity to absorb, resist, recover, and adapt when faced with disruptions. Enhancing the construction safety resilience of underground spaces can effectively tackle the issue of frequent accidents and the challenge of pre-controlling risks at construction sites. Utilizing systems engineering theory, this paper investigates the factors that affect the construction safety resilience of underground spaces and establishes a general framework for evaluating the safety performance of the construction process. Utilizing a large-scale underground construction project as a case study, the Bayesian network inference technique is applied to ascertain the project’s safety resilience value. Through reverse reasoning, the method identifies the most likely sequence of causes leading to construction safety incidents, and subsequently, the resilience assessment framework’s efficacy is tested. The research findings suggest that the core of construction safety management is the prevention of unsafe human behaviors and that the key to enhancing resilience lies in the optimization of response capabilities. The proposed “PFR-EFR-LFR” whole-process resilience analysis method can be applied to safety assessments for various types of underground space construction projects. Full article

Aero-engines, particularly turbofan engines, are highly complex systems that play a critical role in the aviation industry. As core components of modern aircraft, they provide the thrust necessary for flight and are essential for safe and efficient operations. However, the complexity and interconnected nature of these engines also make them vulnerable to failures and, in the context of intelligent systems, potential cyber-attacks. Ensuring the secure and reliable operation of these engines is crucial as disruptions can have significant consequences, ranging from costly maintenance issues to catastrophic accidents. The innovation of this article lies in a proposed method for obtaining key points. The research method is based on convolution and the basic shape of convolution. Through feature fusion, a self-convolution operation, a half operation, and derivative operation on the original feature data of the engine, two key points of the engine in the entire lifecycle are obtained, and these key points are analyzed in detail. Finally, the key point-based acquisition method and statistical data analysis were applied to the engine’s health planning and lifespan prediction, and the results were validated on the test set. The results indicate that the key point-based method proposed in this paper has promising prospects. Full article

A Sodium-cooled Fast Reactor (SFR) is one of the optimized candidates in Generation IV nuclear reactor systems, but safety is an essential issue for SFR development and application. Most knowledge was accumulated through SFR safety investigations, especially for Core Disruptive Accidents (CDAs). During the CDA of SFRs, the molten materials in the core region are likely to discharge into subcooled sodium and form a debris bed on the lower region of the reactor vessel. Noticing that elaboration on the characteristics and mechanisms of Debris Bed Formation (DBF) behavior should be essential for the subsequent analysis of debris bed coolability and accident progression through various experimental and modeling studies, much knowledge was obtained during the past decades. Motivated to promote future investigations on CDAs of SFRs, the previous experiments and modeling studies on DBF behavior are systematically reviewed and discussed in this paper. The experimental results showed that the flow-regime and accumulated-bed characteristics during DBF were influenced by varying parameters and realistic conditions. Through the modeling studies, several empirical models were proposed for predicting the flow regime and accumulated-bed characteristics in DBF. In addition, to promote further development of research, the future prospects concerning DBF behavior are also described. Full article

The mechanical consequences of core disruptive accidents (CDAs) are a major safety concern in sodium-cooled fast reactors. Once core disruption occurs, liquefied core materials rapidly disperse vertically and radially. The dispersed materials penetrate the pin bundles and control rod guide tubes (CRGTs) before freezing at the edge of the penetration zone as heat is transferred to surrounding structures. Such freezing phenomena can suppress the negative reactivity feedback of fuel dispersion. The discharge of core materials can be impeded, resulting in a molten core pool formation when tight blockages occur inside CRGTs due to frozen material. Accordingly, freezing phenomena of core materials play a key role in governing the mechanical consequences of a CDA. To validate a freezing model implemented in our CDA analysis code, ASTERIA-SFR, a preliminary simulation of the THEFIS RUN#1 test, was performed. The calculation results show that freezing on the structural wall and crust formation were key phenomena affecting the penetration behavior, and the structural heat transfer is an important parameter. A remarkable reduction of the heat transfer coefficient was required to reproduce the penetration length observed in the experiment. This suggests that the momentum exchange and flow regime at the leading edge as well as heat transfer should be well modeled to predict the freezing phenomena in rapidly evolving CDAs. Full article

The capacity for subjective time in humans encompasses the perception of time’s unfolding from moment to moment, as well as the ability to traverse larger temporal expanses of past- and future-oriented thought via mental time travel. Disruption in time perception can result in maladaptive outcomes—from the innocuous lapse in timing that leads to a burnt piece of toast, to the grievous miscalculation that produces a traffic accident—while disruption to mental time travel can impact core functions from planning appointments to making long-term decisions. Mounting evidence suggests that disturbances to both time perception and mental time travel are prominent in dementia syndromes. Given that such disruptions can have severe consequences for independent functioning in everyday life, here we aim to provide a comprehensive exposition of subjective timing dysfunction in dementia, with a view to informing the management of such disturbances. We consider the neurocognitive mechanisms underpinning changes to both time perception and mental time travel across different dementia disorders. Moreover, we explicate the functional implications of altered subjective timing by reference to two key and representative adaptive capacities: prospective memory and intertemporal decision-making. Overall, our review sheds light on the transdiagnostic implications of subjective timing disturbances in dementia and highlights the high variability in performance across clinical syndromes and functional domains. Full article

In the safety analysis of sodium-cooled fast reactors, numerical simulations of various thermal-hydraulic phenomena with multicomponent and multiphase flows in core disruptive accidents (CDAs) are regarded as particularly difficult. In the material relocation phase of CDAs, core debris settle down on a core support structure and/or an in-vessel retention device and form a debris bed. The bed’s shape is crucial for the subsequent relocation of the molten core and heat removal capability as well as re-criticality. In this study, a hybrid numerical simulation method, coupling the multi-fluid model of the three-dimensional fast reactor safety analysis code SIMMER-IV with the discrete element method (DEM), was applied to analyze the sedimentation and bed formation behaviors of core debris. Three-dimensional simulations were performed and compared with results obtained in a series of particle sedimentation experiments. The present simulation predicts the sedimentation behavior of mixed particles with different properties as well as homogeneous particles. The simulation results on bed shapes and particle distribution in the bed agree well with experimental measurements. They demonstrate the practicality of the present hybrid method to solid particle sedimentation and bed formation behaviors of mixed as well as homogeneous particles. Full article

Since a fast reactor core with uranium-plutonium fuel is not in its most reactive configuration under operating conditions, redistribution of the core materials (fuel, steel, sodium) during a core disruptive accident (CDA) may lead to recriticalities and as a consequence to severe nuclear power excursions. The prevention, or at least the mitigation, of core disruption is therefore of the utmost importance. In the current paper, we analyze an innovative fast reactor concept developed within the CP-ESFR European project, focusing on the phenomena affecting the initiation and the transition phases of an unprotected loss of flow (ULOF) accident. Key phenomena for the initiation phase are coolant boiling onset and further voiding of the core that lead to a reactivity increase in the case of a positive void reactivity effect. Therefore, the first level of optimization involves the reduction, by design, of the positive void effect in order to avoid entering a severe accident. If the core disruption cannot be avoided, the accident enters into the transition phase, characterized by the progression of core melting and recriticalities due to fuel compaction. Dedicated features that enhance and guarantee a sufficient and timely fuel discharge are considered for the optimization of this phase. Full article