Coupling analysis of crane accident risks based on Bayesian network and the N-K model

• Published in: Scientific reports Vol. 14; no. 1; p. 1133
• Main Authors: Wu, Bang-Jie, Jin, Liang-Hai, Zheng, Xia-Zhong, Chen, Shu
• Format: Journal Article
• Language: English
• Published: England Nature Publishing Group 11.01.2024; Nature Portfolio
• Subjects: Accident prevention; Bayesian analysis; Construction accidents & safety; Data mining; Environmental risk; Risk factors; Sensitivity analysis
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-51425-9

Crane usage is pervasive on construction sites, however, it is associated with a notably high accident rate. The analyzing of crane accident risks is essential for accident prevention, control, and ensuring the safety of lifting operations. Hence, significant emphasis should be placed on understanding the interaction among various risk factors. This paper proposes a quantitative coupling method for human, machine, management, and environmental risk factors in crane accidents, leveraging Bayesian networks (BN) and the N-K model. Firstly, text mining technology and fault tree analysis are employed to analyze the causes of crane accidents and categorize the associate risk factors. Secondly, the types of risk coupling resulting from human, machine, management, and environmental risk factors are defined. Thirdly, the BN model is developed based on the analysis of crane accident risksand its N-K model. Fourthly, the parameters of the risk coupling nodes in the developed BN are determined based on the calculation results of the N-K model. Finally, for the risk coupling types with high coupling values and the first-level node and second-level node, the failure probability is analyzed through posterior probability and sensitivity analysis. The results indicate that factors related to man and management significantly impact crane accidents and warrant enhanced attention. The interplay among multiple risk factors significantly influences the probability of crane accidents, necessitating careful attention.