Kaixian Gao

Kaixian Gao


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
ZLZhuang LI
Zhuang LI
ZXZhu Xiaoming
Zhu Xiaoming
SLShiguan Liao
Shiguan Liao
JYJianchuan Yin
Jianchuan Yin
KGKaixian Gao
Kaixian Gao
XLXinliang Liu
Xinliang Liu
Ship collision accidents have a greatly adverse impact on the development of the shipping industry. Due to the uncertainty relating to these accidents, maritime risk is often difficult to accurately quantify. This study innovatively proposes a comprehensive method combining qualitative and quantitative methods to predict the risk of ship collision accidents. First, in view of the uncertain impact of risk factors, the Bayesian network analysis method was used to characterize the correlations between risk factors, and a collision accident risk assessment network model was established. Secondly, in view of the uncertainty relating to the information about risk factors, a subjective data quantification method based on the cloud model was adopted, and the quantitative reasoning of collision accident risk was determined based on multi-source data fusion. The proposed method was applied to the spatiotemporal analysis of ship collision accident risk in China’s coastal port waters. The results show that there is a higher risk of collision accidents in Guangzhou Port and Ningbo Port in China, the potential for ship collision accidents in southern China is greater, and the occurrence of ship collision accidents is most affected by the environment and operations of operators. Combining the Bayesian network and cloud model and integrating multi-source data information to conduct an accident risk assessment, this innovative analysis method has significance for improving the prevention of and response to risks of ship navigation operations in China’s coastal ports.