☆ 4.7 Article

Quantification analysis of potential risk in railway accidents: A new random walk based approach

RELIABILITY ENGINEERING & SYSTEM SAFETY (2024)

Related references

Note: Only part of the references are listed.

Article Engineering, Industrial

A railway accident prevention method based on reinforcement learning-Active preventive strategy by multi-modal data

Dongyang Yan et al.

Summary: This paper proposes a railway accident prevention method based on the reinforcement learning model and multi-modal data to achieve active railway accident prevention strategies. Three metrics are designed to show the performance of active prevention methods, and the effectiveness of the proposed method is verified in the case study by introducing two methods as baselines. The results also show that nearly 30% of accidents can be effectively prevented through active preventive measures with the proposed method. Finally, this paper analyzes the influence of personal skills on the proposed model and makes relevant suggestions for improving railway safety based on the analysis of the results.

RELIABILITY ENGINEERING & SYSTEM SAFETY (2023)

Add to Collection

Article Geosciences, Multidisciplinary

The prediction of disaster risk paths based on IECNN model

Yanyan Liu et al.

Summary: In this paper, an improved embedding layer of convolution neural network (CNN) called IECNN is proposed to predict the disaster risk path. A disaster risk network is established and random walk paths are generated. The structural characteristics of nodes in the paths are considered in the improved embedding layer. The proposed model shows effective prediction and high performance in terms of evaluation indexes.

NATURAL HAZARDS (2023)

Add to Collection

Article Engineering, Industrial

Accident risk tensor-specific covariant model for railway accident risk assessment and prediction

Yangpeng Wang et al.

Summary: In this paper, an accident risk tensor field is derived from the safety-cusp catastrophe model using tensor analysis, and an accident risk tensor-specific covariant model is constructed to dynamically assess railway accident risk. By combining this model with mixture density networks, the high accident risk faced by a railway system can be accurately predicted in real time by identifying the Gaussian disturbance.

RELIABILITY ENGINEERING & SYSTEM SAFETY (2023)

Add to Collection

Article Engineering, Industrial

Accident investigation and lessons not learned: AcciMap analysis of successive tailings dam collapses in Brazil

Rodrigo L. Rose et al.

Summary: Tailings dam collapses have severe consequences on human beings, economies, and the environment, although they are rare events. This study focuses on the analysis of two tailings dam collapses in Brazil in 2015 and 2019, investigating the first accident and exploring its causal factors in the subsequent disaster. The study presents an overview of tailings dam failures, reviews the literature on the Mariana and Brumadinho disasters, and synthesizes the findings to identify technical, managerial, and governmental factors contributing to each accident. Recommendations are proposed to improve tailings dam safety, enhance the safety culture in the regulatory environment, and reform the investigation process for dam accidents. The restructuring of chains of accountability through nonpartisan inspection and investigation is identified as a key aspect in preventing similar accidents.

RELIABILITY ENGINEERING & SYSTEM SAFETY (2023)

Add to Collection

Article Engineering, Environmental

Uncertainty analysis of accident causality model using Credal Network with IDM method: A case study of hazardous material road transportation accidents

Song Ding et al.

Summary: This paper proposes a Credal Network model based on Imprecise Dirichlet Model for addressing cognitive uncertainty in accident causal inference, with a case study on hazardous material road transportation accidents. The results demonstrate that the method can effectively represent uncertainty propagation in the accident causal model and offer a new approach for accident risk analysis.

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION (2022)

Add to Collection

Article Engineering, Industrial

A hierarchical Bayesian-based model for hazard analysis of climate effect on failures of railway turnout components

Serdar Dindar et al.

Summary: This paper investigates the impact of climates with different features across the US on the derailments, and identifies extreme climate patterns considerably impacting the component failures of rail turnouts. The findings suggest that large-scale region with extreme cold and hot zones should be investigated using the suggested methodology of this paper.

RELIABILITY ENGINEERING & SYSTEM SAFETY (2022)

Add to Collection

Article Engineering, Multidisciplinary

Quantitative Risk Analysis on Rail Transportation of Hazardous Materials

Iraj Mohammadfam et al.

Summary: This study develops a comprehensive risk assessment model for hazardous material transportation by rail, incorporating potential health risk factors and obstacles using Bayesian networks and fuzzy set theory.

MATHEMATICAL PROBLEMS IN ENGINEERING (2022)

Add to Collection

Article Physics, Multidisciplinary

A network-based CNN model to identify the hidden information in text data

Yanyan Liu et al.

Summary: With the development of the internet and big data, identifying missing or hidden information in text data has become a crucial task. This paper proposes a keyword-based hidden information extraction framework that utilizes a network and convolutional neural network model to discover hidden information related to keywords. Experimental results demonstrate the effectiveness of the model in identifying hidden information in the source text data.

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS (2022)

Add to Collection

Article Engineering, Environmental

Accident causes data-driven coal and gas outburst accidents prevention: Application of data mining and machine learning in accident path mining and accident case-based deduction

Xie Xuecai et al.

Summary: This study focuses on analyzing and preventing coal and gas outburst accidents by exploring the primary accident path and conducting applied research on accident reasoning. The study proposes a method for mining the main accident path and establishes a Bayesian network model for probabilistic reasoning of accident causes. The application results show that the proposed method is feasible and provides valuable insights for accident prevention and reasoning analysis.

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION (2022)

Add to Collection

Article Engineering, Industrial

The prediction of potential risk path in railway traffic events

Shuang Gu et al.

Summary: In this paper, a new network-based risk prediction model is proposed to investigate the propagation path of potential risk in railway traffic operation. The model considers three kinds of information hidden in network connections: local and global structural information, as well as attribute information. Keyword extraction and an improved breadth-first search algorithm are used for data preprocessing and path identification. The case study results show that the proposed model can effectively predict potential risk paths and performs best in terms of evaluation metrics.

RELIABILITY ENGINEERING & SYSTEM SAFETY (2022)

Add to Collection

Article Transportation Science & Technology

A batch reinforcement learning approach to vacant taxi routing

Xinlian Yu et al.

Summary: This study formulates the optimal routing problem of a single vacant taxi as a Markov Decision Process (MDP) and proposes a batch offline reinforcement learning method to learn the optimal policy. With the training and evaluation on a large dataset of taxi trajectories, the batch RL method outperforms traditional methods in terms of computational efficiency and performance.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2022)

Add to Collection

Article Green & Sustainable Science & Technology

Railway Signaling Safety Factors Quantitative Analysis Using an Improved 5M Model

Haixiang Lin et al.

Summary: This research proposes an improved hierarchical model for railway signaling accidents, which analyzes the safety factors quantitatively and establishes a safety evaluation index system for railway signaling system. The results show that the Management element is the most important factor in rail signaling accidents, and factors such as equipment material, safety management, external humans affected, and hidden danger should also not be ignored.

SUSTAINABILITY (2022)

Add to Collection

Article Engineering, Multidisciplinary

A feed-forwarded neural network-based variational Bayesian learning approach for forensic analysis of traffic accident

Yuxi Xie et al.

Summary: In this study, a computation algorithm based on variational Bayesian learning is developed to identify the deformation field and residual strain fields of crashed cars. It shows great potential in three-dimensional collision reconstruction and forensic analysis of car crashes.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2022)

Add to Collection

Article Engineering, Mechanical

Traceability and failure consequences of natural gas explosion accidents based on key investigation technology

Qianran Hu et al.

Summary: This study investigates a typical natural gas leakage and explosion accident, providing a detailed analysis of the accident process and causes. The findings offer scientific guidance for the investigation and evaluation of explosion effects in similar accidents.

ENGINEERING FAILURE ANALYSIS (2022)

Add to Collection

Article Ergonomics

Fatal train accidents on Europe's railways: An update to 2019

Andrew W. Evans

Summary: This paper analyzes the fatal train accident rates and trends on Europe's main line railways from 1990-2019. The data shows a consistent decrease in the number of fatal train collisions and derailments per train-kilometer over the past three decades. The main contributing factor to this decrease is believed to be the increasing deployment of train protection systems.

ACCIDENT ANALYSIS AND PREVENTION (2021)

Add to Collection

Article Engineering, Industrial

Analysis of occupational accidents in Spain using shrinkage regression methods

Vicente Gallego et al.

Summary: This paper analyzes the relationship between occupational health indicators and factors related to the labor market, productivity structure, and economy using regression shrinkage methods. AdaLasso method provides the best results for FR and DLA, showing strong positive relationship with Factor Hours Worked and strong negative relationship with Total Females Employed and Agriculture Sector. The study offers insights into previously unexplored occupational indicators.

SAFETY SCIENCE (2021)

Add to Collection

Article Computer Science, Information Systems

Using improved Group 2 and Linguistic Z-numbers combined approach to analyze the causes of railway passenger train derailment accident

Wencheng Huang et al.

Summary: An improved Group 2 and Linguistic Z-numbers combined approach is proposed to analyze the causes of railway passenger train derailment accidents. Various methods such as Fault Tree, minimum nonempty intersection sets, left offset rate, and right offset rate are applied to improve the analysis of accident causes and risk assessment. The study uses the Puyuma case as a case study and shows that the IG2-LZs approach is more reliable and reasonable compared to other methods such as AHP, IG2-TFN, or G2-LZs.

INFORMATION SCIENCES (2021)

Add to Collection

Article Chemistry, Multidisciplinary

Dynamic Railway Derailment Risk Analysis with Text-Data-Based Bayesian Network

Liu Yang et al.

Summary: This paper introduces a text-based Bayesian network method for establishing a safety analysis model of transportation systems, demonstrating its effectiveness and higher accuracy compared to other methods through experiments. Analysis based on text data helps identify high-risk barriers, providing guidance to strengthen safety measures.

APPLIED SCIENCES-BASEL (2021)

Add to Collection

Article Engineering, Industrial

A new approach for risk assessment of failure modes considering risk interaction and propagation effects

Qun Wang et al.

Summary: Failure Mode and Effect Analysis (FMEA) is an efficient method for risk prevention and control, but previous research has not adequately examined the impacts of interactions among failure modes on risk priority accuracy. The proposed method considers the initial strength effect of failure modes on risk propagation and uses the PageRank algorithm to recursively calculate the final risk priority, demonstrating its effectiveness in a case study of smart bracelets.

RELIABILITY ENGINEERING & SYSTEM SAFETY (2021)

Add to Collection

Article Engineering, Industrial

A novel risk evaluation method for fire and explosion accidents in oil depots using bow-tie analysis and risk matrix analysis method based on cloud model theory

Shuyi Xie et al.

Summary: This study focuses on the prevention and control of Fire and Explosion Accidents in Oil Depots (FEAOD) by building a Bow-tie (BT) model and proposing a novel risk quantitative assessment algorithm based on Cloud Model (CM) theory. Through a case study, it was found that the proposed method can more accurately identify the weak links in the safety system, providing a theoretical basis for risk prevention and control.

RELIABILITY ENGINEERING & SYSTEM SAFETY (2021)

Add to Collection

Article Engineering, Industrial

A knowledge graph-based approach for exploring railway operational accidents

Jintao Liu et al.

Summary: This study introduces a novel knowledge graph-based approach to explore railway operational accidents, aiming to uncover accident patterns. By constructing an accident knowledge graph, it provides railway operators with decision-making basis for accident prevention efforts.

RELIABILITY ENGINEERING & SYSTEM SAFETY (2021)

Add to Collection

Article Physics, Multidisciplinary

Biased random walk with restart for link prediction with graph embedding method

Yinzuo Zhou et al.

Summary: In this paper, a refined random walk approach incorporating graph embedding method is proposed to provide biased transferring probabilities and exploit topological properties for link prediction in complex networks. The method outperforms commonly used indexes in terms of prediction accuracy.

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS (2021)

Add to Collection

Article Transportation Science & Technology

A deep neural network inverse solution to recover pre-crash impact data of car collisions*

Qijun Chen et al.

Summary: The study successfully developed a data-driven AI solution for traffic collision reconstruction using a machine learning computational algorithm and deep neural network. By using permanent plastic deformation as forensic data signatures, the machine learning algorithm accurately identified initial collision conditions.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2021)

Add to Collection

Article Computer Science, Information Systems

Improving Human Reliability Analysis for Railway Systems Using Fuzzy Logic

Lorenzo Ciani et al.

Summary: Human factor is one of the main causes of railway accidents. The RARA method for railway applications faces challenges such as subjectivity and difficulty in parameter evaluation. The innovative fuzzy method introduced in this manuscript simplifies parameter evaluation, reduces analyst subjectivity, and provides more compliant results with a simpler and more intuitive approach.

IEEE ACCESS (2021)

Add to Collection

Article Public, Environmental & Occupational Health

A Study of Risk Relevance Reasoning Based on a Context Ontology of Railway Accidents

Tiancheng Cao et al.

RISK ANALYSIS (2020)

Add to Collection

Article Engineering, Mechanical

Stochastic response analysis of multi-degree-of-freedom vibro-impact system undergoing Markovian jump

Rongchun Hu et al.

NONLINEAR DYNAMICS (2020)

Add to Collection

Article Engineering, Industrial

An improved risk assessment method based on a comprehensive weighting algorithm in railway signaling safety analysis

Chang Liu et al.

SAFETY SCIENCE (2020)

Add to Collection

Article Physics, Applied

An effective method for identifying the key factors of railway accidents based on the network model

Keping Li et al.

INTERNATIONAL JOURNAL OF MODERN PHYSICS B (2020)

Add to Collection

Article Engineering, Industrial

Risk state changes analysis of railway dangerous goods transportation system: Based on the cusp catastrophe model

Wencheng Huang et al.

RELIABILITY ENGINEERING & SYSTEM SAFETY (2020)

Add to Collection

Article Engineering, Industrial

Railway dangerous goods transportation system risk analysis: An Interpretive Structural Modeling and Bayesian Network combining approach

Wencheng Huang et al.

RELIABILITY ENGINEERING & SYSTEM SAFETY (2020)

Add to Collection

Article Transportation Science & Technology

Modeling parking search behavior in the city center: A game-based approach

Nir Fulman et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2020)

Add to Collection

Article Engineering, Industrial

Incorporation of human factors into maritime accident analysis using a data-driven Bayesian network

Shiqi Fan et al.

RELIABILITY ENGINEERING & SYSTEM SAFETY (2020)

Add to Collection

Article Social Sciences, Interdisciplinary

Safety risk analysis of restricted-speed train accidents in the United States

Zhipeng Zhang et al.

JOURNAL OF RISK RESEARCH (2020)

Add to Collection

Review Computer Science, Artificial Intelligence

Random Walks: A Review of Algorithms and Applications

Feng Xia et al.

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE (2020)

Add to Collection

Article Multidisciplinary Sciences

Supervised and extended restart in random walks for ranking and link prediction in networks

Woojeong Jin et al.

PLOS ONE (2019)

Add to Collection

Article Engineering, Industrial

Four studies, two methods, one accident - An examination of the reliability and validity of Accimap and STAMP for accident analysis

Anastacio Pinto Goncalves Filho et al.

SAFETY SCIENCE (2019)

Add to Collection

Article Energy & Fuels

A Network Method for Identifying the Root Cause of High-Speed Rail Faults Based on Text Data

Liu Yang et al.

ENERGIES (2019)

Add to Collection

Article Engineering, Industrial

Understanding railway operational accidents using network theory

Liu Jintao et al.

RELIABILITY ENGINEERING & SYSTEM SAFETY (2019)

Add to Collection

Article Engineering, Civil

Analysis of Fire-Accident Factors Using Big-Data Analysis Method for Construction Areas

Joon-Soo Kim et al.

KSCE JOURNAL OF CIVIL ENGINEERING (2018)

Add to Collection

Article Engineering, Industrial

Paths between latent and active errors: Analysis of 407 railway accidents/incidents' causes in China

Jian-Lan Zhou et al.

SAFETY SCIENCE (2018)

Add to Collection

Article Engineering, Industrial

A network accident causation model for monitoring railway safety

Keping Li et al.

SAFETY SCIENCE (2018)

Add to Collection

Article Transportation Science & Technology

A deep learning approach for detecting traffic accidents from social media data

Zhenhua Zhang et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2018)

Add to Collection

Article Engineering, Environmental

Scale-reasoning based risk propagation analysis: An application to fluid catalytic cracking unit

Shuang Cai et al.

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION (2018)

Add to Collection

Article Engineering, Industrial

A hybrid human and organizational analysis method for railway accidents based on HFACS-Railway Accidents (HFACS-RAs)

Qingjian Zhan et al.

SAFETY SCIENCE (2017)

Add to Collection

Article Physics, Multidisciplinary

A method for modeling and analysis of directed weighted accident causation network (DWACN)

Jin Zhou et al.

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS (2015)

Add to Collection

Article Physics, Multidisciplinary

Analyzing the causation of a railway accident based on a complex network

Ma Xin et al.

CHINESE PHYSICS B (2014)

Add to Collection

Review Physics, Multidisciplinary

Link prediction in complex networks: A survey

Linyuan Lue et al.

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS (2011)

Add to Collection

Article Engineering, Industrial

Development and evaluation of a computer-aided system for analyzing human error in railway operations

Dong San Kim et al.

RELIABILITY ENGINEERING & SYSTEM SAFETY (2010)

Add to Collection

Article Engineering, Industrial

Investigation of key factors for accident severity at railroad grade crossings by using a logit model

Shou-Ren Hu et al.

SAFETY SCIENCE (2010)

Add to Collection

Article Engineering, Industrial

STAMP-based analysis on the railway accident and accident spreading: Taking the China-Jiaoji railway accident for example

Min Ouyang et al.

SAFETY SCIENCE (2010)

Add to Collection

Article Physics, Fluids & Plasmas

Similarity index based on local paths for link prediction of complex networks

Linyuan Lue et al.

PHYSICAL REVIEW E (2009)

Add to Collection

Article Physics, Fluids & Plasmas

Resilience to damage of graphs with degree correlations

A Vazquez et al.

PHYSICAL REVIEW E (2003)

Add to Collection

© Peeref 2019-2024. All rights reserved.