Causation analysis model for ship traffic accidents based on C5.0 decision tree and application

doi:10.16265/j.cnki.issn1003-3033.2022.10.0483

Abstract

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.

Key words: C5.0 algorithms, decision tree, ship traffic accident, causation path, causation analysis, 24Model

HUANG Changhai, SHEN Jia, ZHU Ranchao, QI Xucun, ZHENG Fei, LU Hao. Causation analysis model for ship traffic accidents based on C5.0 decision tree and application[J]. China Safety Science Journal, 2022, 32(10): 90-99.

Figures/Tables 8

Fig.1

Fig.2

Tab.1

Fig.3

Tab.2

Classification rule set

序号	输出变量	分类规则集	样本量	置信度/%
1	碰撞	大风浪、港区泊位附近水域、船长不在驾驶台	7	86
2		大风浪、违规操作、航行、过往船或进出口船	9	100
3		大风浪、避让与操纵行为过失、航行或锚泊	18	94
4		大风浪、避让与操纵行为过失、船长在驾驶台、岛礁区或海上或闽中渔场	10	80
5		非大风浪、水上水下作业	17	77
6		非大风浪、航行、应急处理过失或通信合作过失或避让与操纵行为过失	170	94
7		非大风浪、航行、公务船	32	84
8		非大风浪、航行、货船、XM辖区或ND辖区或ZZ辖区或FZ辖区	27	70
9		非大风浪、航行、货船、QZ辖区、雾季	11	73
10		非大风浪、航行、自然条件	11	91
11		非大风浪、航行、航行操作过失、XM辖区、港区泊位附近水域	8	75
12		非大风浪、航行、航行操作过失、ZZ辖区或FZ辖区	7	86
13		非大风浪、航行、违规操作、公务船或客船	21	86
14		非大风浪、航行、违规操作、货船、海上、能见度不良或受限制	11	91
15		非大风浪、航行、违规操作、货船、港区泊位附近水域或锚地或闽中渔场	29	86
16		非大风浪、锚泊、港内作业船、港区泊位附近水域或锚地	15	87
17		非大风浪、锚泊、进出口船	26	89
18		通航环境、能见度不良、港区泊位附近水域或锚地	7	100
19		潜在缺陷、非大风浪、能见度不良或良好	6	83
20		设备缺陷、避让与操纵行为过失、非大风浪、海上或锚地	6	100
序号	输出变量	分类规则集	样本量	置信度/%
21	触礁	助航设施	5	80
22		可航水域、台风或寒潮	5	100
23		大风浪、航线计划过失、雾季	10	80
24		通航环境、能见度良好、自然条件	23	83
25		设备缺陷、避让与操纵行为过失、非大风浪、港区泊位附近水域	5	80
26		设备缺陷、航行操作过失	8	88
27	风灾	大风浪、应急处理过失、能见度不良	10	70
28		大风浪、海上、ND辖区或PT辖区	10	80
29		货物缺陷、自然条件、公司管理局限或船内外作业方	5	80
30	火灾爆炸	非大风浪、锚泊、公司管理局限、台风或雾季	5	80
31	自沉	设备缺陷、航行、海上、寒潮	5	80
32	自沉	超载、台风或雾季	6	100

Tab.2

Fig.4

Tab.3

Fig.5

References 14

[1]	蔡玉良, 于淳, 孙旭, 等. 我国沿海船舶事故特征及影响因素分析[J]. 中国航海, 2021, 44(2):45-52.
	CAI Yuliang, YU Chun, SUN Xu, et al. Characteristics of ship accidents in coastal waters of China and analysis on influencing factors[J]. Navigation of China, 2021, 44(2):45-52.
[2]	FU Shanshan, YAN Xinping, ZHANG Di, et al. Risk influencing factors analysis of Arctic maritime transportation systems: a Chinese perspective[J]. Maritime Policy and Management, 2018, 45(4):439-455. doi: 10.1080/03088839.2018.1448477
[3]	HUANG Changhai, HU Shenping. Factors correlation mining on maritime accidents database using association rule learning algorithm[J]. Cluster Computing, 2019, 22: 4551-4559. doi: 10.1007/s10586-018-2089-z
[4]	ÇAKIR E, FIŞKIN R, SEVGILI C. Investigation of tugboat accidents severity: an application of association rule mining algorithms[J]. Reliability Engineering and System Safety, 2021, 209:DOI:10.1016/j.ress.2021.107470. doi: 10.1016/j.ress.2021.107470
[5]	司东森, 张英俊, 郎坤. 基于改进BN的集装箱船舶碰撞事故致因分析[J]. 中国安全科学学报, 2019, 29(10):31-37. doi: 10.16265/j.cnki.issn1003-3033.2019.10.006
	SI Dongsen, ZHANG Yingjun, LANG Kun. Causation analysis of container ship collision accidents based on improved BN[J]. China Safety Science Journal, 2019, 29(10):31-37. doi: 10.16265/j.cnki.issn1003-3033.2019.10.006
[6]	DENG Jian, LIU Shaoyong, XIE Cheng, et al. Risk coupling characteristics of maritime accidents in Chinese inland and coastal waters based on N-K model[J]. Journal of Marine Science and Engineering, 2022, 10(1): DOI:10.3390/jmse10010004. doi: 10.3390/jmse10010004
[7]	付姗姗, 刘燕平, 席永涛, 等. 北极海冰环境下船舶事故严重程度影响因素分析[J]. 中国安全科学学报, 2019, 29(10):84-90. doi: 10.16265/j.cnki.issn1003-3033.2019.10.013
	FU Shanshan, LIU Yanping, XI Yongtao, et al. Analysis of influencing factors on severity of ship accidents in ice-covered Arctic waters[J]. China Safety Science Journal, 2019, 29(10):84-90. doi: 10.16265/j.cnki.issn1003-3033.2019.10.013
[8]	张丽丽. 水上交通事故致因问题研究[D]. 大连: 大连海事大学, 2017.
	ZHANG Lili. Analysis on waterway traffic accident cause[D]. Dalian: Dalian Maritime University, 2017.
[9]	ZHOU Q, WONG Y, LOH H, et al. A fuzzy and Bayesian network CREAM model for human reliability analysis:the case of tanker shipping[J]. Safety Science, 2018, 105: 149-157. doi: 10.1016/j.ssci.2018.02.011
[10]	AKYUZ E. A marine accident analysing model to evaluate potential operational causes in cargo ships[J]. Safety Science, 2017, 92: 17-25. doi: 10.1016/j.ssci.2016.09.010
[11]	ZHANG Su, WANG Jingui. Analysis of South Korea Sewol sunken ferry accident based on behavioral safety[J]. Journal of Coastal Research. 2015, 73: 611-613. doi: 10.2112/SI73-106.1
[12]	孙轶轩, 邵春福, 赵丹, 等. 交通事故严重程度C5.0决策树预测模型[J]. 长安大学学报:自然科学版, 2014, 34(5):109-116.
	SUN Yixuan, SHAO Chunfu, ZHAO Dan, et al. Traffic accident severity prediction model based on C5.0 decision tree[J]. Journal of Changan University:Natural Science Edition, 2014, 34(5):109-116.
[13]	傅贵, 陈奕燃, 许素睿, 等. 事故致因“2-4”模型的内涵解析及第6版的研究[J]. 中国安全科学学报, 2022, 32(1):12-19. doi: 10.16265/j.cnki.issn1003-3033.2022.01.002
	FU Gui, CHEN Yiran, XU Surui, et al. Detailed explanations of 24Model and development of its 6^th version[J]. China Safety Science Journal, 2022, 32(1):12-19. doi: 10.16265/j.cnki.issn1003-3033.2022.01.002
[14]	FU Gui, XIE Xuecai, JIA Qingsong, et al. The development history of accident causation models in the past 100 years: 24Model, a more modern accident causation model[J]. Process Safety and Environmental Protection, 2020, 134: 47-82. doi: 10.1016/j.psep.2019.11.027

序号	变量类别	输入变量	事故变量具体说明
1	事故属性	季节特征	寒潮、台风、雾季
2		地点类型	岛礁区、港区泊位附近水域、海上、锚地、闽中渔区
3		管辖水域	FZ辖区、ND辖区、PT辖区、QZ辖区、XM辖区、ZZ辖区
4		船舶种类	公务船、客船、货船、不明
5		航线	进出口船、过往船、港内作业船
6		船舶动态	并靠、航行、锚泊、水上水下作业
序号	变量类别	输入变量	事故变量具体说明
7	事故致因	引航员操作	是、否
8		船长在驾驶台	船长在驾驶台、船长不在驾驶台
9		其他人员	船内外作业方、拖轮作业方、公司管理局限、海事管理局限、无关
10		船员原因	违规操作、航行操作过失、航线计划过失、通信合作过失、应急处理过失、避让与操纵行为过失、无关
11		能见度	能见度不良、能见度良好、能见度受限制
12		风浪	大风浪、非大风浪
13		意外原因	自然条件、船舶条件、其他条件、无关
14		交通原因	泊位锚地、交通意外、通航秩序、无关
15		航道码头原因	渔区、助航设施、航道弯道、可航水域、通航环境、海图出版物、无关
16		船舶货物原因	超载、货物缺陷、潜在缺陷、结构缺陷、设备缺陷、无关

分区	训练集	测试集
样本量	715	179
分类正确率/%	91.05	93.85
置信度范围	0.402~1.000	0.352~1.000
平均正确性	0.813	0.825

[1]	FANG Ming, ZHANG Yi, TAN Yue. Safety system and management model of subway construction under multi-factor coupling failure mode [J]. China Safety Science Journal, 2024, 34(5): 82-90.
[2]	SUN Shimei, ZHANG Jiayan. Research on influencing factors of subway station fire evacuation based on 24Model-D-ISM [J]. China Safety Science Journal, 2024, 34(4): 153-159.
[3]	LI Xian, JIAO Yu, CHEN Wentao, SHI Danda, KANG Yutao. Feature mining and causative analysis of fire accidents in ship repair and building enterprises [J]. China Safety Science Journal, 2024, 34(3): 29-38.
[4]	JIANG Xin, ZHANG Tengfei, CHEN Jing, ZHAO Li, QIU Guokun, WANG Hui. Numerical study on safety cognition of cavern constructors from perspective of complex system [J]. China Safety Science Journal, 2024, 34(2): 22-30.
[5]	YUAN Chenhui, FU Gui, WU Zhirong, ZHAO Jinkun. Comparative study on definition of cause factors between 24Model and LCM [J]. China Safety Science Journal, 2024, 34(1): 27-34.
[6]	SONG Yinghua, JIANG Chen, LI Moxiao, QI Shi. Rockburst prediction model based on improved Smote-GBDT algorithm [J]. China Safety Science Journal, 2023, 33(9): 25-32.
[7]	TONG Ruipeng, WANG Biao, SUN Ninghao, HU Xiangyang, WANG Qian. Theoretical construction and application of accident-cause-training method [J]. China Safety Science Journal, 2023, 33(8): 24-29.
[8]	ZHAO Wei, LI Shuquan. Prediction model of safety competency of construction workers based on machine learning [J]. China Safety Science Journal, 2023, 33(7): 51-57.
[9]	SONG Wei, FU Gui. Comparative analysis study of STPA and 24Model [J]. China Safety Science Journal, 2023, 33(6): 1-10.
[10]	ZHANG Jiangshi, LI Yongtun, MAO Xiangning, HU Xinyue, WANG Ziyi. Study on classification of coal mine accident causes based on NLP [J]. China Safety Science Journal, 2023, 33(6): 20-26.
[11]	JIANG Yujie, WAN Zheng, CHEN Jihong. Causation analysis of ship accident severity based on ordered choice model [J]. China Safety Science Journal, 2023, 33(12): 131-139.
[12]	SUN Shimei, SUN Zuhang, FENG Ziyang, FU Gui. Behavioral causes analysis of construction accidents based on behavior-based accident causation 24Model theory [J]. China Safety Science Journal, 2023, 33(11): 30-37.
[13]	JING Fei. Research on human factors analysis of railway violations based on data analysis [J]. China Safety Science Journal, 2022, 32(S2): 54-59.
[14]	SHI Zhao, FU Gui, XIE Xuecai, TONG Wenqing, YUAN Chenhui, CHEN Yiran. Development and application of SCAP [J]. China Safety Science Journal, 2022, 32(8): 29-36.
[15]	DONG Longjun, ZHENG Rujian, DENG Sijia. Construction and application of "L-B" man-machine accident model [J]. China Safety Science Journal, 2022, 32(8): 1-8.