Safe railway line equipment operation is crucial for ensuring railway transportation safety. In this study, cloud models (CMs), Bayesian networks (BNs), and risk matrices are integrated to construct a risk assessment model for railway line equipment, enabling quantitative evaluation and classification of risk occurrence likelihoods. First, based on engineering practices, technical reports, accident cases, and expert knowledge, risk events related to railway line equipment and their corresponding risk factors are identified. Leveraging the grid method to consider the spatiotemporal dynamic characteristics of railway line equipment, the system is divided into grid units, and risk factor state data within each grid are dynamically collected across different time periods. Subsequently, drawing on expertise, CMs are applied to handle uncertainties in qualitative knowledge, while BNs are used to calculate the probability of risk events occurring in each grid unit over various time intervals. Finally, risk levels are determined by integrating likelihood and consequence levels through a risk matrix. The model was validated using a rail break case study, demonstrating its ability to accurately identify high-risk grid areas and times. These findings provide a scientific basis for railway authorities to develop refined and targeted risk mitigation strategies, thereby enhancing railway transportation safety and stability.
State Administration for Market Regulation, Standardization Administration of China. Risk management—Risk assessment techniques: GB/T 27921-2023. Standards Press of China, 2023.
2.
DongXM. Railway safety risk management. China Railway Publishing House, 2014.
3.
Ministry of Railways, Safety Supervision Department. Implementation opinions on safety risk management for the permanent way system: Document No. Yungong Gaoxian Han [2012] 124. China Railway Publishing House, 2012.
4.
National Standard of the People’s Republic of China. GB/T 23694-2024, risk management—vocabulary. Standards Press of China, 2024.
5.
TzanakakisK. Managing risks in the railway system: a practice-oriented guide. Springer, 2021.
6.
YangXYanLZengL. How to handle uncertainties in AHP: the Cloud Delphi hierarchical analysis. Inf Sci2013; 222: 384–404.
7.
HuXLiXHuangY. Urban rail transit risk evaluation with incomplete information. In: 6th International conference on green intelligent transportation system and safety (GITSS), 2016; 138, pp.467–477.
8.
HuangWZhangYYinD, et al. Using improved Group 2 and linguistic Z-numbers combined approach to analyze the causes of railway passenger train derailment accident. Inf Sci2021; 576: 694–707.
9.
LeitnerB. A general model for railway systems risk assessment with the use of railway accident scenarios analysis. In: 10th International scientific conference on transportation science and technology (TRANSBALTICA)2017; 187, pp.150–159.
10.
HuangGXiaoL. Failure mode and effect analysis: an interval-valued intuitionistic fuzzy cloud theory-based method. Appl Soft Comput2021; 98: 106834.
11.
SarwarMAliGChaudhryNR. Decision-making model for failure modes and effect analysis based on rough fuzzy integrated clouds. Appl Soft Comput2023; 136: 110148.
12.
KyriakidisMMajumdarAOchiengWY. Data based framework to identify the most significant performance shaping factors in railway operations. Saf Sci2015; 78: 60–76.
13.
CiszewskiTWojciechowskiJKornaszewskiM, et al. Assessment of the risk of failure in electric power supply systems for railway traffic control devices. Sensors2025; 25(14): 4501.
14.
GhofraniFYousefianmoghadamSHeQ, et al. Rail breaks arrival rate prediction: a physics-informed data-driven analysis for railway tracks. Measurement2021; 172: 108858.
15.
ShenJLiuSZhangJ. Using text mining and Bayesian network to identify key risk factors for safety accidents in metro construction. J Constr Eng Manag2024; 150(6): 4024052.
16.
ChowTShahTIParkPY, et al. A GIS approach to the development of a segment-level derailment prediction model. Accid Anal Prev2021; 151: 105897.
17.
NezvalVAndrášikRBílM. Identification of factors contributing to broken and buckled rails: insights from long-term data. Eur Transp Res Rev2025; 17(1): 28.
18.
GhofraniFSunHHeQ. Analyzing risk of service failures in heavy haul rail lines: a hybrid approach for imbalanced data. Risk Anal2022; 42(8): 1852–1871.
19.
ZareiEKhakzadNCozzaniV, et al. Safety analysis of process systems using Fuzzy Bayesian Network (FBN). J Loss Prev Process Ind2019; 57: 7–16.
20.
LiuCYangSCuiY, et al. An improved risk assessment method based on a comprehensive weighting algorithm in railway signaling safety analysis. Saf Sci2020; 128: 104768.
21.
AnMChenYBakerCJ. A fuzzy reasoning and fuzzy-analytical hierarchy process based approach to the process of railway risk information: A railway risk management system. Inf Sci2011; 181(18): 3946–3966.
22.
VeskovićSTepićJIvićM, et al. Model for predicting the frequency of broken rails. Met2012; 51(2): 221–224.
23.
LiDCheungDShiX, et al. Uncertainty reasoning based on cloud models in controllers. Comput Math Appl1998; 35(3): 99–123.
24.
ChaiNZhouW. Evaluating operational risk for train control system using a revised risk matrix and FD-FAHP-Cloud model: a case in China. Eng Fail Anal2022; 137: 106268.
25.
HanBJiaWFengW, et al. Safety risk assessment of loess tunnel construction under complex environment based on game theory-cloud model. Sci Rep2023; 13(1): 12249.
26.
XuCBZhaoLJWangY, et al. Risk assessment model of relay protection system based on multi-state BNs. In: 2017 IEEE transportation electrification conference and expo, Asia-Pacific (ITEC ASIA-PACIFIC), 2017, pp.1563–1567.
27.
PanYZhangLLiZ, et al. Improved fuzzy Bayesian network-based risk analysis with interval-valued fuzzy sets and D–S evidence theory. IEEE Trans Fuzzy Syst2020; 28(9): 2063–2077.
28.
DindarSKaewunruenSAnM, et al. Bayesian network-based probability analysis of train derailments caused by various extreme weather patterns on railway turnouts. Saf Sci2018; 110: 20–30.
29.
ChenHShenQFengZ, et al. Vulnerability assessment in urban metro systems based on an improved cloud model and a Bayesian network. Sustain Cities Soc2023; 98: 104823.
30.
ChenCZhangLTiongRLK. A novel learning cloud Bayesian network for risk measurement. Appl Soft Comput2020; 87: 105947.
31.
ChenHShenQLiT, et al. Modeling the dynamic safety management of buildings adjacent to karst shield construction: an improved cloud Bayesian network. Adv Eng Inform2023; 58: 102192.
32.
BaiLLiuRWangF, et al. Estimating railway rail service life: a rail-grid-based approach. Transp Res Part A: Policy Pract2017; 105: 54–65.
33.
XuCWangG. Bidirectional cognitive computing model for uncertain concepts. Cognit Comput2019; 11(5): 613–629.
34.
LiDLiuCGanW. A new cognitive model: cloud model. Int J Intell Syst2009; 24(3): 357–375.
35.
QinGZhangMYanQ, et al. Comprehensive evaluation of regional energy internet using a fuzzy analytic hierarchy process based on cloud model: A case in China. Energy2021; 228: 120569.
36.
RøedWMoslehAVinnemJE, et al. On the use of the hybrid causal logic method in offshore risk analysis. Reliab Eng Syst Saf2009; 94(2): 445–455.
37.
McKenziePFDuveneckMJMorrealeLL, et al. Local and global parameter sensitivity within an ecophysiologically based forest landscape model. Environ Model Softw2019; 117: 1–13.
38.
Standardization Administration of China. Classification and code for the hazardous and harmful factors in process: GB/T 13861-2022. China Standards Press, 2022.
