Citation

Huang C, Shen J, Zhu R, Qi X, Zheng F, Lu H. China Saf. Sci. J. 2022; 32(10): 90-99.

Copyright

(Copyright © 2022, China Occupational Safety and Health Association, Publisher Gai Xue bao)

DOI

10.16265/j.cnki.issn1003-3033.2022.10.0483

PMID

unavailable

Abstract

In order to reduce the occurrence of ship accidents, the causation of ship traffic accidents was analyzed. Firstly, a ship traffic accident causation path analysis model based on the C5. 0 algorithm was constructed. The model took accident type as the output variable and the ship traffic accident data as samples. Then, the evaluation indexes of validity for path analysis of accident causation were established. Furthermore, the 24Model was used to analyze the causal relationship of different types of accident paths. Finally, the prevention and control measures for ship traffic accidents were proposed by cutting off the potential causation path of accidents. Taking 894 ship traffic accidents as an example, the sample set was randomly divided into 80% training set and 20% test set, and the proposed model was used for analysis. The research results show that the proposed model can generate a set of classification rules for different types of accidents, the classification accuracy rate of the model is over 90%, and the model has a strong generalization ability. The causal chain of ship traffic accidents constructed in combination with the classification rule set provides a quantitative theoretical basis for the prevention of accidents. © 2022 China Safety Science Journal. All rights reserved.

Language: zh