This paper discusses the application of a generalized regression neural network (GRNN) in the risk assessment of dangerous goods transportation by sea. As a type of neural network that is based on a radial basis function, the GRNN is suitable for processing small sample data with nonlinear characteristics. In this study, a sample dataset containing seven risk factors was constructed, and the SPREAD values were adjusted to optimize the performance of the model. The experimental results show that when the SPREAD value is 0.3, the GRNN model has high prediction accuracy and good generalizability for both the training and test samples. Therefore, the GRNN model is applicable and reliable for assessing the risk level of dangerous goods accidents, which provides a new assessment tool for risk management of dangerous goods transportation by sea.
MullaiA. A risk analysis framework for maritime transport of packaged dangerous goods: a validating demonstration. PhD Thesis, Lund University, Sweden, 2007.
European Maritime Safety Agency. Annual overview of marine casualties and incidents 2019. EMSA, 2019.
4.
WanCYanXZhangD, et al. An advanced fuzzy Bayesian-based FMEA approach for assessing maritime supply chain risks. Transp Res E Logist Transp Rev2019; 125: 222–240.
5.
AriciSSAkyuzEArslanO. Application of fuzzy bow-tie risk analysis to maritime transportation: the case of ship collision during the STS operation. Ocean Eng2020; 217(1): 107960.
6.
RenniEBascòABusiniV, et al. Awareness and mitigation of natech accidents: toward a methodology for risk assessment. Chem Eng Trans2010; 19: 383–388.
7.
DoHTTLyTTBDoTT. Combining semiquantitative risk assessment, composite indicator and fuzzy logic for evaluation of hazardous chemical accidents. Sci Rep2020; 10: 18544.
8.
AkyuzEArslanOTuranO. Application of fuzzy logic to fault tree and event tree analysis of the risk for cargo liquefaction on board ship. Appl Ocean Res2020; 101: 102238.
9.
LeggettDJ. Lab-HIRA: hazard identification and risk analysis for the chemical research laboratory. Part 2. Risk analysis of laboratory operations. J Chem Health Saf2012; 19: 25–36.
10.
MaLMaXLanH, et al. A methodology to assess the interrelationships between contributory factors to maritime transport accidents of dangerous goods in China. Ocean Eng2022; 266(Part 3): 112769.
11.
JuLVassalosDWangQ, et al. Numerical investigation of solid bulk cargo liquefaction. Ocean Eng2018; 159: 333–347.
12.
ShuifenZ. Research on simulation and risk assessment technology of spill accidents in the inland transportation of hazardous chemicals. PhD Thesis, Lanzhou Jiaotong University, 2020.
13.
LiHZhouKZhangC, et al. Dynamic evolution of maritime accidents: comparative analysis through data-driven Bayesian networks. Ocean Eng2024; 303: 117736.
14.
ZhaoXYuanHYuQ. Autonomous vessels in the Yangtze river: a study on the maritime accidents using data-driven Bayesian networks. Sustainability2021; 13(17): 9985.
15.
BarkahRFauziahRAlayyannurP, et al. Hazard identification, risk assessment, and determining control (HIRADC) method in a university laboratory in Surabaya, Indonesia. Indian J Forensic Med Toxicol2020; 14(1): 380–385.
16.
ChangLLiuQYanJ, et al. Risk field model construction and risk classification of hazardous chemical transportation. Math Probl Eng2022; 2022: 1–13.
17.
PrzywartyMGucmaLMarcjanK, et al. Risk analysis of collision between passenger ferry and chemical tanker in the western zone of the Baltic sea. Pol Marit Res2015; 22: 3–8.
18.
HeZWengW. A dynamic and simulation-based method for quantitative risk assessment of the domino accident in chemical industry. Process Saf Environ Prot2020; 144: 79–92.
19.
AydinMCamliyurtGAkyuzE, et al. Analyzing human error contributions to maritime environmental risk in oil/chemical tanker ship. Hum Ecol Risk Assess2021; 27(7): 1838–1859.
20.
LiSChenGMenJ, et al. A dynamic and simulation-based method for quantitative risk assessment of domino accidents in chemical warehouses using improved support vector machines. J Loss Prev Process Ind2021; 71: 104372.
21.
LiuZTianWCuiZ, et al. An intelligent quantitative risk assessment method for ammonia synthesis process. Chem Eng J2021; 420: 417.
22.
ZhuXWangHLiY, et al. Environmental risk assessment and mapping of oil spill pollution in coastal areas of China using AIS data. J Environ Manag2022; 305: 114302.
23.
SpechtDF. A general regression neural network. IEEE Trans Neural Netw1991; 2(6): 568–576.
24.
BiJChengHZhangW, et al. Artificial Intelligence in ship trajectory prediction. J Mar Sci Eng2024; 12(5): 769.
25.
Prpić-OršićJValčićMČarijaZ. A hybrid wind load estimation method for container ship based on computational fluid dynamics and neural networks. J Mar Sci Eng2020; 8(7): 539.
26.
ZhangZ. Prediction of ship plate forming springback using an improved whale optimization algorithm optimized GRNN model. J Mar Sci Eng2023; 11(8): 1484.
27.
YangJH. Optimization of ship components using GRNN to improve energy efficiency design index (EEDI). J Ship Res2022; 66(3): 233–243.
28.
WuM. Port dangerous goods container logistics operation risk evaluation and intelligent control. China Harbor Eng2021; 2(1): 1–8.
29.
XueHShaoZPanJ, et al. Vessel traffic flow prediction based on CFA-GRNN algorithm. J Shanghai Jiaotong Univ2020; 54(4): 421–429.
30.
PuSChengGYuT. A ship trajectory analysis method based on the GRNN algorithm. Ship Sci Technol2021; 43(9): 117–121.
31.
SiyuanSZhaoxiaHHuX, et al. Prediction of NOx emissions from four-stroke marine diesel engine based on general regression neural network. J Jimei Univ2017; 22(1): 35–40.
32.
ZhangJX, et al. Comparative study on safety assessment methods for dangerous goods transportation by water based on GRNN and BP neural networks. J Transp Inf Saf2020; 38(3): 123–130.
33.
WangD. Research on the prediction process of modern ship safety incidents based on artificial intelligence. J Dalian Maritime Univ2021; 47(3): 1–10.
