This paper proposed a new systematic approach-functional evidential reasoning model(FERM) for exploring hazardous chemical operational accidents under uncertainty. First, FERM was introduced to identify various causal...This paper proposed a new systematic approach-functional evidential reasoning model(FERM) for exploring hazardous chemical operational accidents under uncertainty. First, FERM was introduced to identify various causal factors and their performance changes in hazardous chemical operational accidents, along with determining the functional failure link relationships. Subsequently, FERM was employed to elucidate both qualitative and quantitative operational accident information within a unified framework, which could be regarded as the input of information fusion to obtain the fuzzy belief distribution of each cause factor. Finally, the derived risk values of the causal factors were ranked while constructing multi-level accident causation chains to unveil the weak links in system functionality and the primary roots of operational accidents. Using the specific case of the “1·15” major explosion and fire accident at Liaoning Panjin Haoye Chemical Co., Ltd., seven causal factors and their corresponding performance changes were identified. Additionally, five accident causation chains were uncovered based on the fuzzy joint distribution of the functional assessment level(FAL) and reliability distribution(RD),revealing an overall increase in risk along the accident evolution path. The research findings demonstrated that FERM enabled the effective characterization, rational quantification and accurate analysis of the inherent uncertainties in hazardous chemical operational accident risks from a systemic perspective.展开更多
Purpose–This study aims to enhance the accuracy of key entity extraction from railway accident report texts and address challenges such as complex domain-specific semantics,data sparsity and strong inter-sentence sem...Purpose–This study aims to enhance the accuracy of key entity extraction from railway accident report texts and address challenges such as complex domain-specific semantics,data sparsity and strong inter-sentence semantic dependencies.A robust entity extraction method tailored for accident texts is proposed.Design/methodology/approach–This method is implemented through a dual-branch multi-task mutual learning model named R-MLP,which jointly performs entity recognition and accident phase classification.The model leverages a shared BERT encoder to extract contextual features and incorporates a sentence span indexing module to align feature granularity.A cross-task mutual learning mechanism is also introduced to strengthen semantic representation.Findings–R-MLP effectively mitigates the impact of semantic complexity and data sparsity in domain entities and enhances the model’s ability to capture inter-sentence semantic dependencies.Experimental results show that R-MLP achieves a maximum F1-score of 0.736 in extracting six types of key railway accident entities,significantly outperforming baseline models such as RoBERTa and MacBERT.Originality/value–This demonstrates the proposed method’s superior generalization and accuracy in domainspecific entity extraction tasks,confirming its effectiveness and practical value.展开更多
A literature review on AI applications in the field of railway safety shows that the implemented approaches mainly concern the operational,maintenance,and feedback phases following railway incidents or accidents.These...A literature review on AI applications in the field of railway safety shows that the implemented approaches mainly concern the operational,maintenance,and feedback phases following railway incidents or accidents.These approaches exploit railway safety data once the transport system has received authorization for commissioning.However,railway standards and regulations require the development of a safety management system(SMS)from the specification and design phases of the railway system.This article proposes a new AI approach for analyzing and assessing safety from the specification and design phases of the railway system with a view to improving the development of the SMS.Unlike some learning methods,the proposed approach,which is dedicated in particular to safety assessment bodies,is based on semi-supervised learning carried out in close collaboration with safety experts who contributed to the development of a database of potential accident scenarios(learning example database)relating to the risk of rail collision.The proposed decision support is based on the use of an expert system whose knowledge base is automatically generated by inductive learning in the form of an association rule(rule base)and whose main objective is to suggest to the safety expert possible hazards not considered during the development of the SMS to complete the initial hazard register.展开更多
City of Muskogee Animal Control Supervisor Phil Blair is known for his devotion to animals,but his quick thinking this week took that commitment to a whole new level-saving the life of an unborn baby deer after a trag...City of Muskogee Animal Control Supervisor Phil Blair is known for his devotion to animals,but his quick thinking this week took that commitment to a whole new level-saving the life of an unborn baby deer after a tragic accident.Blair was called to the scene of a deer struck by a car.Upon arrival,he found the mother deer had suffered four broken legs and sadly had to be put down to prevent further suffering.展开更多
Accident detection plays a critical role in improving traffic safety by enabling timely emergency response and reducing the impact of road incidents.The main challenge lies in achieving real-time,reliable and highly a...Accident detection plays a critical role in improving traffic safety by enabling timely emergency response and reducing the impact of road incidents.The main challenge lies in achieving real-time,reliable and highly accurate detection across diverse Internet-of-vehicles(IoV)environments.To overcome this challenge,this paper leverages deep learning to automatically learn patterns from visual data to detect accidents with high accuracy.A visual classification model based on the ResNet-50 architecture is presented for distinguishing between accident and non-accident images.The model is trained and tested on a labeled dataset and achieves an overall accuracy of 91.84%,with a precision of 94%,recall of 90.38%,and an F1-score of 92.14%.Training behavior is observed over 100 epochs,where the model has shown rapid accuracy gains and loss reduction within the first 30 epochs,followed by gradual stabilization.Accuracy plateaues between 90−93%,and loss values remain consistent between 0.1 and 0.2 in later stages.To understand the effect of training strategy,the model is optimized using three different algorithms,namely,SGD,Adam,and Adadelta with all showing effective performance,though with varied convergence patterns.Further,to test its effectiveness,the proposed model is compared with existing models.In the end,the problems encountered in implementing the model in practical automotive settings and offered solutions are discussed.The results support the reliability of the approach and its suitability for real-time traffic safety applications.展开更多
As tunnel engineering progresses,the complexity of geological strata and the presence of water bodies beneath tunnels have exacerbated the risk of water inrush incidents.Mutation theory is utilized to elucidate the me...As tunnel engineering progresses,the complexity of geological strata and the presence of water bodies beneath tunnels have exacerbated the risk of water inrush incidents.Mutation theory is utilized to elucidate the mech-anisms underlying stratum collapse-induced water inrush,with the Shijingshan Tunnel’s water inrush pattern identified as stratum collapse-induced.Finite element method(FEM)numerical models were developed for four conditions:original tunnel,Grade III surrounding rock,advanced grouting reinforcement,and sectional exca-vation.The evolution of the plastic zone,deformation,and support forces in the surrounding rock was compared across these models.The study demonstrates that shear failure of the rock mass,induced by concentrated stress and water pressure during excavation,results in the formation of water inrush pathways.Advanced grouting and sectional excavation effectively reduced the plastic zone and vertical deformation.This mitigation lessened support damage and decreased the likelihood of stratum collapse.This paper offers technical support and case analysis for the prevention of stratum collapse-induced water inrush in underwater blasting operations.展开更多
Emergency resources play a vital role in the emergency rescue process.The adequate and timely supply of emergency resources can effectively control the development of accidents and reduce accident losses.However,the c...Emergency resources play a vital role in the emergency rescue process.The adequate and timely supply of emergency resources can effectively control the development of accidents and reduce accident losses.However,the current emergency resource allocation of chemical enterprises lacks scientific analysis of accident scenarios,and the individual allocation method of enterprises increases the cost of emergency resource allocation.Given the above problems,this paper proposes a regional collaborative allocation method of emergency resources for enterprises within the chemical industry park(CIP)based on the worst credible accident scenario(WCAS).Firstly,the concept and analysis method of the WCAS is proposed.Then,based on the characteristics and consequences of the accident,the mapping relationship between accident scenarios and emergency resources is established.Finally,an optimization model for regional collaborative allocation of emergency resources is constructed to determine the amount of emergency resource allocation for each enterprise.Through the case study,the emergency resource allocation method based on the WCAS analysis can better meet the demands of accident emergency rescue.Simultaneously,the regional collaborative allocation optimization model can strengthen the cooperation ability among enterprises,greatly reducing the cost of emergency resource allocation for each enterprise.展开更多
Domestic accidents (DA) are common in children and responsible for high morbidity and mortality in developed countries. Objective: This work aimed to describe the epidemiological profile of AD in children aged 0 to 15...Domestic accidents (DA) are common in children and responsible for high morbidity and mortality in developed countries. Objective: This work aimed to describe the epidemiological profile of AD in children aged 0 to 15 years in Libreville. Materials and Methods: All children aged 0 to 15 years who were victims of unintentional trauma occurring at home or in its immediate surroundings were included. We studied the mother’s age, family situation, socioeconomic level, type of housing, age and sex of the child, characteristics of AD and their management. Results: The majority of mothers lived in an intermediate dwelling (80.6%). They were married (37.1%), middle managers (58.2%) and of average socioeconomic level (60.5%). The average age of the mothers was 39.9 ± 11.4 years. Families with more than three children were most exposed (39.2%) to the occurrence of AD. The average age of the children was 6.5 ± 3.3 years with a male predominance. The sex ratio was 1.8. The most common ADs were falls (34.7%), followed by cuts (22.3%) and burns (17.7%). Wounds (54.4%), followed by burns (33%) and fractures (5.1%) were the main types of injuries. The upper limbs were the most affected body part (33.9%) followed by the lower limbs (30.1%) and the head (27.3%). The yard was the preferred location for ADs to occur (51.1%), and particularly during the holiday period (48.4%). The risk factors related to the occurrence of AD were age, socioeconomic level, number of children and type of housing. Care was provided at home in 51.9% of cases. Conclusion: The occurrence of AD in children is not negligible;hence the need to implement preventive measures to minimize their frequency.展开更多
We analyzed accident factors in a 2020 ship collision case that occurred off Kii Oshima Island using the SHELL model analysis and examined corresponding collision prevention measures.The SHELL model analysis is a fram...We analyzed accident factors in a 2020 ship collision case that occurred off Kii Oshima Island using the SHELL model analysis and examined corresponding collision prevention measures.The SHELL model analysis is a framework for identifying accident factors related to human abilities and characteristics,hardware,software,and the environment.Beyond assessing the accident factors in each element,we also examined the interrelationship between humans and each element.This study highlights the importance of(1)training to enhance situational awareness,(2)improving decision-making skills,and(3)establishing structured decision-making procedures to prevent maritime collision accidents.Additionally,we considered safety measures through(4)hardware enhancements and(5)environmental measures.Furthermore,to prevent accidents,implementing measures grounded in(6)predictions is deemed effective.This study identified accident factors through prediction alongside the SHELL model analysis and proposed countermeasures based on the findings.By applying these predictions,more countermeasures can be derived,which,when combined strategically,can significantly aid in preventing maritime collision accidents.展开更多
Human factors are critical causes of modern aviation accidents. However, existing accident analysis methods encounter limitations in addressing aviation human factors, especially in complex accident scenarios. The exi...Human factors are critical causes of modern aviation accidents. However, existing accident analysis methods encounter limitations in addressing aviation human factors, especially in complex accident scenarios. The existing graphic approaches are effective for describing accident mechanisms within various categories of human factors, but cannot simultaneously describe inad- equate human-aircraft-environment interactions and organizational deficiencies effectively, and highly depend on analysts＇ skills and experiences. Moreover, the existing methods do not emphasize latent unsafe factors outside accidents. This paper focuses on the above three limitations and proposes an integrated graphi^taxonomic-associative approach. A new graphic model named accident tree （AceiTree）, with a two-mode structure and a reaction-based concept, is developed for accident modeling and safety defense identification. The AcciTree model is then integrated with the well-established human factors analysis and classification system （HFACS） to enhance both reliability of the graphic part and logicality of the taxonomic part for improving completeness of analysis. An associative hazard analysis technique is further put forward to extend analysis to fac- tors outside accidents, to form extended safety requirements for proactive accident prevention. Two crash examples, a research flight demonstrator by our team and an industrial unmanned aircraft, illustrate that the integrated approach is effective for identifying more unsafe factors and safety requirements.展开更多
The aim of this paper is to examine the causes of road accidents in Cameroon. The Douala-Yaoundé highway was chosen as the case of study. Available field data recorded from the year 2006 to 2011, have enabled the...The aim of this paper is to examine the causes of road accidents in Cameroon. The Douala-Yaoundé highway was chosen as the case of study. Available field data recorded from the year 2006 to 2011, have enabled the analysis of each accident. The method used here is the factorial correspondence analysis;which aims to bring in a small number of dimensions, most of the initial </span><span style="font-family:Verdana;">information, focusing not on the absolute values, but the correspondence between t</span><span style="font-family:Verdana;">he variables, that is to say the relative values. From this analysis, it appears that, of the 906 accidents recorded during this period, top five causes account for nearly 83% of the information provided by the set of variables on the occurrence of road accidents. These causes are: driver inattention, lack of control, over speeding, improper overtaking and tire puncture. These results </span><span style="font-family:Verdana;">require involvement in the construction of road safety policies through training,</span><span style="font-family:Verdana;"> sensitization and adequate repressions as well as administrative reforms and research policy in road safety.展开更多
The research paper in hand presents a thorough exploration of the fishing vessel accidents and near misses in the UK fishing industry as well as the underlying human element factors and sub-factors contributing to the...The research paper in hand presents a thorough exploration of the fishing vessel accidents and near misses in the UK fishing industry as well as the underlying human element factors and sub-factors contributing to them. In this respect, the regulatory regime in the fishing industry both at a national and international level is initially examined while also complemented by the investigation of past research efforts to address these issues. Furthermore, the analysis of the fishing vessels accidents and near misses as recorded in the UK MAIB （Marine Accident Investigation Branch） database for a period of 19 years is performed in order to derive the very causal factors leading to the fishing vessel accidents. It is initially shown that the fatalities and injuries taking place due to fishing vessels＇ accidents have alarmingly remained unchanged over the last 15-20 years. Another key finding is that the number of accidents and near misses per day and night shifis is quite similar while most accidents take place in coastal waters. Furthermore, human factors are related to the vast majority of fishing vessels accidents with the principal ones referring to ＂non-compliance＇, ＂equipment misuse or poorly designed＂, ＂training＂ and ＂competence＂. Finally, remedial measures are also suggested in order to address the main accident causes identified.展开更多
In this study, we used the Human Capital (HC) accident analysis method, to determine the road traffic accident costs in Sudan in two successive years (2010 and 2011) with slight modifications to the recommended and kn...In this study, we used the Human Capital (HC) accident analysis method, to determine the road traffic accident costs in Sudan in two successive years (2010 and 2011) with slight modifications to the recommended and known framework in the way it handles currently and future accident cost components. We evaluated and compared the significance and impact of the economic loss caused by road traffic accidents in Sudan using detailed information on road traffic accident casualties, classified by severity level, vehicle type, and other key parameters such as discount rates and medical and insurance information for Sudan in its entirety. The total cost of road traffic accidents in Sudan in 2010 was estimated at US $391 million, which represents 0.57% of the Gross Domestic Product (GDP), while in 2011 the cost was calculated to reach US $413 million, representing 0.62% of GDP. Findings show that the amount of accident costs is estimated to a certain extent at less than 1% of the total GDP of the country in the two estimation years, but we believe that the evaluation process used fulfilled the eligibility criteria of HC studies and that the produced values for Sudan are valid and reliable. Unit costs for each crash severity level were also estimated in the two years such as death, disability, serious injury, slight injury, and vehicle damage. Death or fatality was equal to US $38,932 and 39,508;disability was equal to US $43,113 and US $45,165;serious injury was equal to US $6963 and US $7596;slight injury was equal to US $2570 and US $3198 and vehicle damage only was equal to US $2268 and US $2579 in the assessment years 2010 and 2011, respectively.展开更多
A comparative study is conducted to compare the theory and application effect of two accident causation models, the human factors analysis and classification system（HFACS） and the accident causation ＂2-4＂ model（2...A comparative study is conducted to compare the theory and application effect of two accident causation models, the human factors analysis and classification system（HFACS） and the accident causation ＂2-4＂ model（24 Model）, as well as to provide a reference for safety researchers and accident investigators to select an appropriate accident analysis method. The two models are compared in terms of their theoretical foundations, cause classifications, accident analysis processes, application ranges, and accident prevention strategies. A coal and gas outburst accident is then analyzed using both models, and the application results are compared. This study shows that both the 24 Model and HFACS have strong theoretical foundations, and they can each be applied in various domains. In addition, the cause classification in HFACS is more practical, and its accident analysis process is more convenient. On the other hand, the 24 Model includes external factors, which makes the cause analysis more systematic and comprehensive. Moreover, the 24 Model puts forward more corresponding measures to prevent accidents.展开更多
In this paper, a new model is constructed for the causation analysis of railway accident based on the complex network theory. In the model, the nodes are defined as various manifest or latent accident causal factors. ...In this paper, a new model is constructed for the causation analysis of railway accident based on the complex network theory. In the model, the nodes are defined as various manifest or latent accident causal factors. By employing the complex network theory, especially its statistical indicators, the railway accident as well as its key causations can be analyzed from the overall perspective. As a case, the ＂7.23＂ China-Yongwen railway accident is illustrated based on this model. The results show that the inspection of signals and the checking of line conditions before trains run played an important role in this railway accident. In conclusion, the constructed model gives a theoretical clue for railway accident prediction and, hence, greatly reduces the occurrence of railway accidents.展开更多
At present, lightning is one of the 10 natural disasters, and it is also the top environmental factor of power interruption. It often causes huge losses to the electric system. The Wuhan High Voltage Institute of the ...At present, lightning is one of the 10 natural disasters, and it is also the top environmental factor of power interruption. It often causes huge losses to the electric system. The Wuhan High Voltage Institute of the State Grid Corporation of China and Huazhong University of Science and Technology have been researching and developing lightning location systems （LLSs） since the late 1980s. In the mid-1990s, a lightning detection network was created in 29 provinces and cities in China. It is primarily applied to rapidly find lightning accidents, which greatly reduces power interruption. Also, it ensures high efficiency and safe operation of the electricity system. Remarkable benefit is achieved. China＇s LLS went through an ＂orientation positioning - time difference positioning - integrated positioning＂ development process. The positioning precision, detection efficiency, degree of automation, practicability and applied range are improved. Also, a lightning information system plan of the national network has been implemented, which services the whole society.展开更多
The reliability expression of dynamic driving behavior is derived from the driving shaping behavioural model; and then, in accordance with the combination of computer simulation and mathematical expression of driving ...The reliability expression of dynamic driving behavior is derived from the driving shaping behavioural model; and then, in accordance with the combination of computer simulation and mathematical expression of driving reliability, an approach for assessing the effect of driving erroneous actions on the dynamic performance of the driver vehicle system is presented. The analysis of driving erroneous actions in the driver vehicle system has been performed to show that the reliability during perception with variety widely could result in the incidents and/or accidents in traffic system.展开更多
The analysis of huge data is a complex task that cannot be executed without a proper system. Geographic information systems (GISs) have been used by many transportation agencies and police departments to analyze and m...The analysis of huge data is a complex task that cannot be executed without a proper system. Geographic information systems (GISs) have been used by many transportation agencies and police departments to analyze and manage urban traffic accident (UTA) data and for decision making aimed at decreasing accident rates and increasing safety. The exact location of accidents and environmental characteristics must be analyzed as UTAs occur in specific locations with specific characteristics. ArcGIS software is the best choice for obtaining meaningful information and analysis results from UTAs in an observational time span. GIS technology is a fundamental element for investigating and evaluating the complex spatial relationship among different components and urban traffic accident is one of them. Micro or macro analysis of UTAs through the spatial prospective within the geographical environment and urban structure can make a deep micro understanding of UTAs patterns in addition to assisting in decision making. UTAs can be considered complex events that occur in two aspects which are spatial and temporal or space and time in other word. A GIS can integrate more than two different and unrelated databases. The evaluation among different spatial objects in a geographical environment and associated factors in urban structure which are included but not limited to land use category, road transportation network qualification, population density, etc., is one of the GIS specification. Traffic safety organizations and UTA researchers use GISs as a key technology to support their research and operational needs. In particular, GIS-T is an often-used GIS application used for planning and decision-making in transportation.展开更多
The possibility and causes of flight accidents by operational error/deviation in takeoff are analyzed in this paper. The following three stages are each described individually: before liftoff, near liftoff and initial...The possibility and causes of flight accidents by operational error/deviation in takeoff are analyzed in this paper. The following three stages are each described individually: before liftoff, near liftoff and initial climb. Relations of accident/incident causal factors by operational error with intrinsical flight mechanics are discussed.展开更多
The number of safety input directly determines the level of safety, and there exists dialectical and unified relations between safety input and accidents. Based on the field investigation and reliable data, this paper...The number of safety input directly determines the level of safety, and there exists dialectical and unified relations between safety input and accidents. Based on the field investigation and reliable data, this paper deeply studied the dialectical relationship between safety input and accidents, and acquired the conclusions. The security situation of the coal enterprises was related to the security input rate, being effected little by the security input scale, and build the relationship model between safety input and accidents on this basis, that is the accident model.展开更多
基金supported by the National Key Research&Development Program of China(2021YFB3301100)the National Natural Science Foundation of China(52004014)the Fundamental Research Funds for the Central Universities(ZY2406).
文摘This paper proposed a new systematic approach-functional evidential reasoning model(FERM) for exploring hazardous chemical operational accidents under uncertainty. First, FERM was introduced to identify various causal factors and their performance changes in hazardous chemical operational accidents, along with determining the functional failure link relationships. Subsequently, FERM was employed to elucidate both qualitative and quantitative operational accident information within a unified framework, which could be regarded as the input of information fusion to obtain the fuzzy belief distribution of each cause factor. Finally, the derived risk values of the causal factors were ranked while constructing multi-level accident causation chains to unveil the weak links in system functionality and the primary roots of operational accidents. Using the specific case of the “1·15” major explosion and fire accident at Liaoning Panjin Haoye Chemical Co., Ltd., seven causal factors and their corresponding performance changes were identified. Additionally, five accident causation chains were uncovered based on the fuzzy joint distribution of the functional assessment level(FAL) and reliability distribution(RD),revealing an overall increase in risk along the accident evolution path. The research findings demonstrated that FERM enabled the effective characterization, rational quantification and accurate analysis of the inherent uncertainties in hazardous chemical operational accident risks from a systemic perspective.
基金funded by the Technology Research and Development Plan Program of China State Railway Group Co.,Ltd.(No.Q2024T001)the Foundation of China Academy of Railway Sciences Co.,Ltd.(No:2024YJ259).
文摘Purpose–This study aims to enhance the accuracy of key entity extraction from railway accident report texts and address challenges such as complex domain-specific semantics,data sparsity and strong inter-sentence semantic dependencies.A robust entity extraction method tailored for accident texts is proposed.Design/methodology/approach–This method is implemented through a dual-branch multi-task mutual learning model named R-MLP,which jointly performs entity recognition and accident phase classification.The model leverages a shared BERT encoder to extract contextual features and incorporates a sentence span indexing module to align feature granularity.A cross-task mutual learning mechanism is also introduced to strengthen semantic representation.Findings–R-MLP effectively mitigates the impact of semantic complexity and data sparsity in domain entities and enhances the model’s ability to capture inter-sentence semantic dependencies.Experimental results show that R-MLP achieves a maximum F1-score of 0.736 in extracting six types of key railway accident entities,significantly outperforming baseline models such as RoBERTa and MacBERT.Originality/value–This demonstrates the proposed method’s superior generalization and accuracy in domainspecific entity extraction tasks,confirming its effectiveness and practical value.
文摘A literature review on AI applications in the field of railway safety shows that the implemented approaches mainly concern the operational,maintenance,and feedback phases following railway incidents or accidents.These approaches exploit railway safety data once the transport system has received authorization for commissioning.However,railway standards and regulations require the development of a safety management system(SMS)from the specification and design phases of the railway system.This article proposes a new AI approach for analyzing and assessing safety from the specification and design phases of the railway system with a view to improving the development of the SMS.Unlike some learning methods,the proposed approach,which is dedicated in particular to safety assessment bodies,is based on semi-supervised learning carried out in close collaboration with safety experts who contributed to the development of a database of potential accident scenarios(learning example database)relating to the risk of rail collision.The proposed decision support is based on the use of an expert system whose knowledge base is automatically generated by inductive learning in the form of an association rule(rule base)and whose main objective is to suggest to the safety expert possible hazards not considered during the development of the SMS to complete the initial hazard register.
文摘City of Muskogee Animal Control Supervisor Phil Blair is known for his devotion to animals,but his quick thinking this week took that commitment to a whole new level-saving the life of an unborn baby deer after a tragic accident.Blair was called to the scene of a deer struck by a car.Upon arrival,he found the mother deer had suffered four broken legs and sadly had to be put down to prevent further suffering.
基金the Deanship of Graduate Studies and Scientific Research at Najran University for funding this work under the Growth Funding Program grant code(NU/GP/SERC/13/358-6)。
文摘Accident detection plays a critical role in improving traffic safety by enabling timely emergency response and reducing the impact of road incidents.The main challenge lies in achieving real-time,reliable and highly accurate detection across diverse Internet-of-vehicles(IoV)environments.To overcome this challenge,this paper leverages deep learning to automatically learn patterns from visual data to detect accidents with high accuracy.A visual classification model based on the ResNet-50 architecture is presented for distinguishing between accident and non-accident images.The model is trained and tested on a labeled dataset and achieves an overall accuracy of 91.84%,with a precision of 94%,recall of 90.38%,and an F1-score of 92.14%.Training behavior is observed over 100 epochs,where the model has shown rapid accuracy gains and loss reduction within the first 30 epochs,followed by gradual stabilization.Accuracy plateaues between 90−93%,and loss values remain consistent between 0.1 and 0.2 in later stages.To understand the effect of training strategy,the model is optimized using three different algorithms,namely,SGD,Adam,and Adadelta with all showing effective performance,though with varied convergence patterns.Further,to test its effectiveness,the proposed model is compared with existing models.In the end,the problems encountered in implementing the model in practical automotive settings and offered solutions are discussed.The results support the reliability of the approach and its suitability for real-time traffic safety applications.
基金supported by Fundamental Research Funds for the Central Universities(No.2023JBRC005)Natu-ral Science Foundation Committee Program of China(Grant No.52308388)+1 种基金fund of State Key Laboratory of Geohazard Pre-vention and Geoenvironment Protection(Chengdu University of Tech-nology)(No.SKLGP2024K008)open project of State Key Laboratory of Performance Monitoring and Protecting of Rail Transit Infrastructure,East China Jiaotong University(No.HIGZ2023101).
文摘As tunnel engineering progresses,the complexity of geological strata and the presence of water bodies beneath tunnels have exacerbated the risk of water inrush incidents.Mutation theory is utilized to elucidate the mech-anisms underlying stratum collapse-induced water inrush,with the Shijingshan Tunnel’s water inrush pattern identified as stratum collapse-induced.Finite element method(FEM)numerical models were developed for four conditions:original tunnel,Grade III surrounding rock,advanced grouting reinforcement,and sectional exca-vation.The evolution of the plastic zone,deformation,and support forces in the surrounding rock was compared across these models.The study demonstrates that shear failure of the rock mass,induced by concentrated stress and water pressure during excavation,results in the formation of water inrush pathways.Advanced grouting and sectional excavation effectively reduced the plastic zone and vertical deformation.This mitigation lessened support damage and decreased the likelihood of stratum collapse.This paper offers technical support and case analysis for the prevention of stratum collapse-induced water inrush in underwater blasting operations.
基金support provided by the Qingdao Science and Technology Benefits People Demonstration and Guidance Project(21-1-4-sf-4-nsh).
文摘Emergency resources play a vital role in the emergency rescue process.The adequate and timely supply of emergency resources can effectively control the development of accidents and reduce accident losses.However,the current emergency resource allocation of chemical enterprises lacks scientific analysis of accident scenarios,and the individual allocation method of enterprises increases the cost of emergency resource allocation.Given the above problems,this paper proposes a regional collaborative allocation method of emergency resources for enterprises within the chemical industry park(CIP)based on the worst credible accident scenario(WCAS).Firstly,the concept and analysis method of the WCAS is proposed.Then,based on the characteristics and consequences of the accident,the mapping relationship between accident scenarios and emergency resources is established.Finally,an optimization model for regional collaborative allocation of emergency resources is constructed to determine the amount of emergency resource allocation for each enterprise.Through the case study,the emergency resource allocation method based on the WCAS analysis can better meet the demands of accident emergency rescue.Simultaneously,the regional collaborative allocation optimization model can strengthen the cooperation ability among enterprises,greatly reducing the cost of emergency resource allocation for each enterprise.
文摘Domestic accidents (DA) are common in children and responsible for high morbidity and mortality in developed countries. Objective: This work aimed to describe the epidemiological profile of AD in children aged 0 to 15 years in Libreville. Materials and Methods: All children aged 0 to 15 years who were victims of unintentional trauma occurring at home or in its immediate surroundings were included. We studied the mother’s age, family situation, socioeconomic level, type of housing, age and sex of the child, characteristics of AD and their management. Results: The majority of mothers lived in an intermediate dwelling (80.6%). They were married (37.1%), middle managers (58.2%) and of average socioeconomic level (60.5%). The average age of the mothers was 39.9 ± 11.4 years. Families with more than three children were most exposed (39.2%) to the occurrence of AD. The average age of the children was 6.5 ± 3.3 years with a male predominance. The sex ratio was 1.8. The most common ADs were falls (34.7%), followed by cuts (22.3%) and burns (17.7%). Wounds (54.4%), followed by burns (33%) and fractures (5.1%) were the main types of injuries. The upper limbs were the most affected body part (33.9%) followed by the lower limbs (30.1%) and the head (27.3%). The yard was the preferred location for ADs to occur (51.1%), and particularly during the holiday period (48.4%). The risk factors related to the occurrence of AD were age, socioeconomic level, number of children and type of housing. Care was provided at home in 51.9% of cases. Conclusion: The occurrence of AD in children is not negligible;hence the need to implement preventive measures to minimize their frequency.
文摘We analyzed accident factors in a 2020 ship collision case that occurred off Kii Oshima Island using the SHELL model analysis and examined corresponding collision prevention measures.The SHELL model analysis is a framework for identifying accident factors related to human abilities and characteristics,hardware,software,and the environment.Beyond assessing the accident factors in each element,we also examined the interrelationship between humans and each element.This study highlights the importance of(1)training to enhance situational awareness,(2)improving decision-making skills,and(3)establishing structured decision-making procedures to prevent maritime collision accidents.Additionally,we considered safety measures through(4)hardware enhancements and(5)environmental measures.Furthermore,to prevent accidents,implementing measures grounded in(6)predictions is deemed effective.This study identified accident factors through prediction alongside the SHELL model analysis and proposed countermeasures based on the findings.By applying these predictions,more countermeasures can be derived,which,when combined strategically,can significantly aid in preventing maritime collision accidents.
基金co-supported by the Program for Changjiang Scholars and Innovative Research Team in University of Ministry of Education of China (IRT0905)the Step Program of Beijing Key Laboratory (No. Z121104002812053)
文摘Human factors are critical causes of modern aviation accidents. However, existing accident analysis methods encounter limitations in addressing aviation human factors, especially in complex accident scenarios. The existing graphic approaches are effective for describing accident mechanisms within various categories of human factors, but cannot simultaneously describe inad- equate human-aircraft-environment interactions and organizational deficiencies effectively, and highly depend on analysts＇ skills and experiences. Moreover, the existing methods do not emphasize latent unsafe factors outside accidents. This paper focuses on the above three limitations and proposes an integrated graphi^taxonomic-associative approach. A new graphic model named accident tree （AceiTree）, with a two-mode structure and a reaction-based concept, is developed for accident modeling and safety defense identification. The AcciTree model is then integrated with the well-established human factors analysis and classification system （HFACS） to enhance both reliability of the graphic part and logicality of the taxonomic part for improving completeness of analysis. An associative hazard analysis technique is further put forward to extend analysis to fac- tors outside accidents, to form extended safety requirements for proactive accident prevention. Two crash examples, a research flight demonstrator by our team and an industrial unmanned aircraft, illustrate that the integrated approach is effective for identifying more unsafe factors and safety requirements.
文摘The aim of this paper is to examine the causes of road accidents in Cameroon. The Douala-Yaoundé highway was chosen as the case of study. Available field data recorded from the year 2006 to 2011, have enabled the analysis of each accident. The method used here is the factorial correspondence analysis;which aims to bring in a small number of dimensions, most of the initial </span><span style="font-family:Verdana;">information, focusing not on the absolute values, but the correspondence between t</span><span style="font-family:Verdana;">he variables, that is to say the relative values. From this analysis, it appears that, of the 906 accidents recorded during this period, top five causes account for nearly 83% of the information provided by the set of variables on the occurrence of road accidents. These causes are: driver inattention, lack of control, over speeding, improper overtaking and tire puncture. These results </span><span style="font-family:Verdana;">require involvement in the construction of road safety policies through training,</span><span style="font-family:Verdana;"> sensitization and adequate repressions as well as administrative reforms and research policy in road safety.
文摘The research paper in hand presents a thorough exploration of the fishing vessel accidents and near misses in the UK fishing industry as well as the underlying human element factors and sub-factors contributing to them. In this respect, the regulatory regime in the fishing industry both at a national and international level is initially examined while also complemented by the investigation of past research efforts to address these issues. Furthermore, the analysis of the fishing vessels accidents and near misses as recorded in the UK MAIB （Marine Accident Investigation Branch） database for a period of 19 years is performed in order to derive the very causal factors leading to the fishing vessel accidents. It is initially shown that the fatalities and injuries taking place due to fishing vessels＇ accidents have alarmingly remained unchanged over the last 15-20 years. Another key finding is that the number of accidents and near misses per day and night shifis is quite similar while most accidents take place in coastal waters. Furthermore, human factors are related to the vast majority of fishing vessels accidents with the principal ones referring to ＂non-compliance＇, ＂equipment misuse or poorly designed＂, ＂training＂ and ＂competence＂. Finally, remedial measures are also suggested in order to address the main accident causes identified.
文摘In this study, we used the Human Capital (HC) accident analysis method, to determine the road traffic accident costs in Sudan in two successive years (2010 and 2011) with slight modifications to the recommended and known framework in the way it handles currently and future accident cost components. We evaluated and compared the significance and impact of the economic loss caused by road traffic accidents in Sudan using detailed information on road traffic accident casualties, classified by severity level, vehicle type, and other key parameters such as discount rates and medical and insurance information for Sudan in its entirety. The total cost of road traffic accidents in Sudan in 2010 was estimated at US $391 million, which represents 0.57% of the Gross Domestic Product (GDP), while in 2011 the cost was calculated to reach US $413 million, representing 0.62% of GDP. Findings show that the amount of accident costs is estimated to a certain extent at less than 1% of the total GDP of the country in the two estimation years, but we believe that the evaluation process used fulfilled the eligibility criteria of HC studies and that the produced values for Sudan are valid and reliable. Unit costs for each crash severity level were also estimated in the two years such as death, disability, serious injury, slight injury, and vehicle damage. Death or fatality was equal to US $38,932 and 39,508;disability was equal to US $43,113 and US $45,165;serious injury was equal to US $6963 and US $7596;slight injury was equal to US $2570 and US $3198 and vehicle damage only was equal to US $2268 and US $2579 in the assessment years 2010 and 2011, respectively.
基金support from the State Key Program of the National Natural Science Foundation of China (No. 51534008)
文摘A comparative study is conducted to compare the theory and application effect of two accident causation models, the human factors analysis and classification system（HFACS） and the accident causation ＂2-4＂ model（24 Model）, as well as to provide a reference for safety researchers and accident investigators to select an appropriate accident analysis method. The two models are compared in terms of their theoretical foundations, cause classifications, accident analysis processes, application ranges, and accident prevention strategies. A coal and gas outburst accident is then analyzed using both models, and the application results are compared. This study shows that both the 24 Model and HFACS have strong theoretical foundations, and they can each be applied in various domains. In addition, the cause classification in HFACS is more practical, and its accident analysis process is more convenient. On the other hand, the 24 Model includes external factors, which makes the cause analysis more systematic and comprehensive. Moreover, the 24 Model puts forward more corresponding measures to prevent accidents.
基金Project supported by the National High Technology Research and Development Program of China (Grant No.2011AA110502)the National Natural Science Foundation of China (Grant No.71271022)the Research Foundation of State Key Laboratory of Rail Traffic Control and Safety,China (Grant No.RCS2012ZQ001)
文摘In this paper, a new model is constructed for the causation analysis of railway accident based on the complex network theory. In the model, the nodes are defined as various manifest or latent accident causal factors. By employing the complex network theory, especially its statistical indicators, the railway accident as well as its key causations can be analyzed from the overall perspective. As a case, the ＂7.23＂ China-Yongwen railway accident is illustrated based on this model. The results show that the inspection of signals and the checking of line conditions before trains run played an important role in this railway accident. In conclusion, the constructed model gives a theoretical clue for railway accident prediction and, hence, greatly reduces the occurrence of railway accidents.
文摘At present, lightning is one of the 10 natural disasters, and it is also the top environmental factor of power interruption. It often causes huge losses to the electric system. The Wuhan High Voltage Institute of the State Grid Corporation of China and Huazhong University of Science and Technology have been researching and developing lightning location systems （LLSs） since the late 1980s. In the mid-1990s, a lightning detection network was created in 29 provinces and cities in China. It is primarily applied to rapidly find lightning accidents, which greatly reduces power interruption. Also, it ensures high efficiency and safe operation of the electricity system. Remarkable benefit is achieved. China＇s LLS went through an ＂orientation positioning - time difference positioning - integrated positioning＂ development process. The positioning precision, detection efficiency, degree of automation, practicability and applied range are improved. Also, a lightning information system plan of the national network has been implemented, which services the whole society.
文摘The reliability expression of dynamic driving behavior is derived from the driving shaping behavioural model; and then, in accordance with the combination of computer simulation and mathematical expression of driving reliability, an approach for assessing the effect of driving erroneous actions on the dynamic performance of the driver vehicle system is presented. The analysis of driving erroneous actions in the driver vehicle system has been performed to show that the reliability during perception with variety widely could result in the incidents and/or accidents in traffic system.
文摘The analysis of huge data is a complex task that cannot be executed without a proper system. Geographic information systems (GISs) have been used by many transportation agencies and police departments to analyze and manage urban traffic accident (UTA) data and for decision making aimed at decreasing accident rates and increasing safety. The exact location of accidents and environmental characteristics must be analyzed as UTAs occur in specific locations with specific characteristics. ArcGIS software is the best choice for obtaining meaningful information and analysis results from UTAs in an observational time span. GIS technology is a fundamental element for investigating and evaluating the complex spatial relationship among different components and urban traffic accident is one of them. Micro or macro analysis of UTAs through the spatial prospective within the geographical environment and urban structure can make a deep micro understanding of UTAs patterns in addition to assisting in decision making. UTAs can be considered complex events that occur in two aspects which are spatial and temporal or space and time in other word. A GIS can integrate more than two different and unrelated databases. The evaluation among different spatial objects in a geographical environment and associated factors in urban structure which are included but not limited to land use category, road transportation network qualification, population density, etc., is one of the GIS specification. Traffic safety organizations and UTA researchers use GISs as a key technology to support their research and operational needs. In particular, GIS-T is an often-used GIS application used for planning and decision-making in transportation.
文摘The possibility and causes of flight accidents by operational error/deviation in takeoff are analyzed in this paper. The following three stages are each described individually: before liftoff, near liftoff and initial climb. Relations of accident/incident causal factors by operational error with intrinsical flight mechanics are discussed.
文摘The number of safety input directly determines the level of safety, and there exists dialectical and unified relations between safety input and accidents. Based on the field investigation and reliable data, this paper deeply studied the dialectical relationship between safety input and accidents, and acquired the conclusions. The security situation of the coal enterprises was related to the security input rate, being effected little by the security input scale, and build the relationship model between safety input and accidents on this basis, that is the accident model.
