基于关联规则挖掘的船员不安全行为致因网络分析

马晓雪; 张瑞文; 乔卫亮; 韩冰; 杨杰

doi:10.3963/j.jssn.1674-4861.2025.02.001

基于关联规则挖掘的船员不安全行为致因网络分析

doi: 10.3963/j.jssn.1674-4861.2025.02.001

马晓雪^{1, 2,},
张瑞文¹,
乔卫亮^3, ,,
韩冰⁴,
杨杰³

1.
大连海事大学航运经济与管理学院辽宁大连 116026
2.
大连海事大学公共管理与人文艺术学院辽宁大连 116026
3.
大连海事大学轮机工程学院辽宁大连 116026
4.
上海船舶运输科学研究所有限公司上海 200135

基金项目:

中央高校基本科研业务费项目 3132024627

详细信息

作者简介:
马晓雪（1974—），博士，教授. 研究方向：交通运输公共安全管理. E-mail：xiaoqiao_fang@dlmu.edu.cn

通讯作者:
乔卫亮（1986—），博士，副教授. 研究方向：水上交通运输安全风险管控技术. E-mail：maxx1020@dlmu.edu.cn

中图分类号: X928.03
计量
- 文章访问数: 41
- HTML全文浏览量: 14
- PDF下载量: 13
- 被引次数: 0
出版历程
- 收稿日期: 2024-09-02

An Analysis of the Seafarers' Unsafe Actions Causality Network Based on Association Rule Mining

MA Xiaoxue^{1, 2
,},
ZHANG Ruiwen¹,
QIAO Weiliang^{3
, ,},
HAN Bing⁴,
YANG Jie³

1.
School of Maritime Economics and Management, Dalian Maritime University, Dalian 116026, Liaoning, China
2.
Public Administration and Humanities College, Dalian Maritime University, Dalian 116026, Liaoning, China
3.
Marine Engineering College, Dalian Maritime University, Dalian 116026, Liaoning, China
4.
Shanghai Ship and Shipping Research Institute Co., Ltd., Shanghai 200135, China

摘要

摘要: 船员不安全行为是水上交通事故频发的关键诱因，但现有研究多集中于单一因素分析，缺乏对其多因素耦合致因机制的挖掘剖析。基于886份水上交通事故调查报告，运用扎根理论对事故调查报告的文本内容进行处理，归纳提炼得出船员不安全行为及其致因；依据人为因素分析分类模型，建立起包含5个层面、76个因素的船员不安全行为及其致因分析框架；采用关联规则挖掘算法，探究船员不安全行为及其致因间的耦合关系，揭示其如何协同作用于船员不安全行为的发生机制；运用复杂网络理论，将关联规则挖掘的结果映射到有向加权网络中，建立船员不安全行为致因网络模型，通过对模型的拓扑特征进行深入分析，识别出在事故过程中发挥关键作用的节点。结果表明：船员不安全行为致因网络呈现出典型的小世界网络特性，平均聚类系数为0.63，平均路径长度为2.095 2，表明影响因素间关联紧密，易引发连锁反应；置信度大于0.5的关联规则中，“值班船员严重瞭望疏忽”有55%的概率与其他因素协同作用引发其他船员不安全行为，致因网络中其介数中心性值约为0.262 7，在致因路径发展中发挥关键中介作用；“未采取安全航速”与“未充分、正确利用导助航设施，或导助航设施不可用”在搁浅事故中存在高度关联关系，与其他因素耦合时的相互诱发概率达70%。此外，“未能及早发现并采取有效的风险化解措施”“船长应急处置能力差”等在多个事故类型的关联规则中频繁出现，表明这些不安全行为在船员应对风险过程中属于重要环节。
- 水上交通事故 /
- 船员不安全行为 /
- 致因分析 /
- 关联规则 /
- 复杂网络
Abstract: Seafarers' unsafe actions are pivotal contributors to the frequent occurrence of waterborne traffic accidents. However, the majority of existing research tends to concentrate on the analysis of single factors, with insufficient exploration of the underlying mechanisms involving the interplay of multiple factors. Based on 886 waterborne traffic accident investigation reports, unsafe actions and its causal factors are extracted by utilizing Grounded Theory. According to the framework of human factor analysis and classification system (HFACS), an analytical framework for the unsafe actions and causal factors is established, encompassing five levels and 76 factors. association rule mining (ARM) algorithm is utilized for the exploration of the coupling relationship and interaction between the seafarers' unsafe actions. It reveals how various causal factors synergistically contribute to the occurrence of seafarers' unsafe actions. By employing complex network theory, the results of association rule analysis are mapped onto a directed weighted network, constructing a causal network model for seafarers' unsafe actions. The key nodes influencing seafarers' unsafe actions are identified by analyzing the topological characteristics of the network. It is highlighted that the causation network of seafarers' unsafe actions exhibits typical small-world network characteristics, with an average clustering coefficient of 0.63 and an average path length of 2.095 2. This indicates that the influencing factors are closely interconnected, making it susceptible to triggering chain reactions. Among the strong association rules, "severe lookout negligence by watchkeeping seafarers" has a 55% probability of interacting with other factors to trigger other seafarers' unsafe actions. The betweenness centrality value of it is approximately 0.262 7, playing a crucial intermediary role in the development of causation pathways. "Failure to adopt a safe speed" and "inadequate use of navigational aids" exhibit a highly correlated relationship in grounding accidents, with a mutual inducement probability of 70% when interacting with other factors. Unsafe actions such as "failure to detect and implement effective risk mitigation measures in a timely manner" and "poor emergency response capabilities of the captain" frequently emerge in the association rules across multiple accident types. It indicates that these unsafe actions occupy a pivotal position in the process of seafarers' risk management.
- waterborne traffic accident /
- seafarers' unsafe actions /
- causation analysis /
- association rule mining /
- complex network

HTML全文

图 1 关联规则映射到有向加权网络示意图

Figure 1. Schematic diagram of associating rules to a directed weighted network

下载: 全尺寸图片幻灯片

图 2 致因到不安全行为关联规则散点图

Figure 2. Scatter plot of association rules from causal factors to unsafe actions

下载: 全尺寸图片幻灯片

图 3 致因与不安全行为间关联规则分组矩阵图

Figure 3. Grouping matrix plot of association rules between causal factors and unsafe actions

下载: 全尺寸图片幻灯片

图 4 船员不安全行为致因复杂网络模型

Figure 4. Complex network model of the causal factors of seafarers' unsafe actions

下载: 全尺寸图片幻灯片

图 5 节点的度

Figure 5. Degree of nodes

下载: 全尺寸图片幻灯片

图 6 节点的加权聚类系数

Figure 6. Weighted clustering coefficient of nodes

下载: 全尺寸图片幻灯片

图 7 节点的介数中心性

Figure 7. Betweeness centrality of nodes

下载: 全尺寸图片幻灯片

表 1 改进的HFACS模型

Table 1. Improved HFACS model

类别	编码	描述	类别	编码	描述
船员不安全行为	U1	值班船员严重瞭望疏忽、未保持正规瞭望	不安全行为前提	P1	沟通交流与通信不畅
	U2	未能充分估计可能存在的碰撞、搁浅、沉没等危险		P2	船舶离港航行前未制订相关工作计划或工作计划存在风险
	U3	未遵守船上航行或相关作业操作规程		P3	船上部分结构不符合规范、改装存在安全隐患
	U4	未采取安全航速		P4	船舶未配备，或配备不足救生设备
	U5	对环境影响估计不足，风险管控决策失误		P5	酒后驾驶
	U6	引航员未谨慎引航		P6	船舶技术状态不良、维护保养不到位
	U7	船员操作不当		P7	渔船违规作业、违法经营
	U8	船长的应急处置能力差，应急处置措施不当		P8	渔业生产设施、渔排非法布设
	U9	对环境风险估计不足，冒险离港航行		P9	大风浪天气，海况恶劣
	U10	航行途中未谨慎驾驶，保持应有的戒备		P10	航行（通航）环境复杂
	U11	船舶装卸货操作不当，货物重心不平衡		P11	能见度不良
	U12	未能运用良好的船艺操纵船舶		P12	缺少对不熟悉水域（能见度不良水域）应有的谨慎
	U13	违反船舶航行相关规则、法规		P13	船舶机械设备问题未及时修复、机械设备故障
	U14	未做好船舶离港航行前的货舱及货物相关准备工作		P14	潮流流速较大
	U15	值班船员责任心不强		P15	船舶载货超重，或有超重嫌疑
	U16	船员违规操作、船员习惯性违规		P16	船员不适任
	U17	未能及早发现、并采取有效的风险化解措施		P17	对通航环境不熟悉，未掌握通航环境信息
	U18	未充分、正确利用导助航设施，或导助航设施不可用		P18	船员疲劳
	U19	值班船员未掌握并严格执行计划航线		P19	船舶动力或电气故障，甚至失去动力
	U20	船长选择锚位、抢滩位置不当		P20	未及时掌握准确的气象水文信息
	U21	临近碍航物、岸边、他船，未保持足够的安全距离	不安全监督	S1	船上管理松散，船长未严格落实日常管理制度
	U22	未遵守避碰规则		S2	船长日常船舶管理风险意识较差
	U23	未核实风险应对措施的有效性（避让）		S3	船舶违法、违规营运，船舶证书、资质存在问题
	U24	船员应急操作不熟练、应急行为不当、未采取应急行动		S4	公司未能配备足够、适任的船员
	U25	未按规定进行交接班		S5	公司实际营运人指挥船舶违章运输
	U26	船舶发生险情、事故后未向海事机关报告		S6	船舶故意关闭AIS，使用虚假AIS、AIS故障
	U27	船上特殊作业人员不具备资质或相关技能		S7	船长的船上指挥权受限
	U28	值班船员数量不足、或没人值班		S8	公司未办理船舶进出港手续等，逃避监管
	U29	船员不熟悉船上相关设备的操作		S9	公司未能掌握船舶航行动态及技术状态
	U30	离港航行前货物适运性未核实，或者不适运	组织因素	O1	公司未有效落实安全管理责任
	U31	船舶载货航行期间，货物管理不善		O2	公司船舶所有人、经营人疏于安全管理
外部因素	E1	涉海施工单位雇佣三无船舶参与施工活动		O3	公司未提供有效、充分的岸基支持
	E2	码头非法经营，不具备安全靠泊条件		O4	公司未制订或未严格落实教育培训计划
	E3	装卸货码头安全生产作业条件较差		O5	公司安全管理体系文件内容不完善
	E4	导助航基础设施不足		O6	公司未给船舶配备足够的纸质海图资料
	E5	码头安全管理制度缺失，或未严格落实规章制度		O7	公司管理人员不具备相关资质，未能正确履职
	E6	货物托运人谎报、瞒报货物		O8	公司长时间未组织应急演练演习
	E7	非法铺设海底管道、海底光缆保护措施不当		O9	公司对船员安全意识和责任感强调不到位

下载: 导出CSV

表 2 提升度排名前3位的关联规则

Table 2. Top three association rules ranked by lift value

事故类型	序号	关联规则	支持度	置信度	提升度
	1	{P12，U1} →{U28}	0.07	0.67	6
触礁事故	2	{P2，U1，U2} →{U17}	0.07	0.33	2.25
	3	{P2，U1，U19}→{U15}	0.04	0.4	2.4
	1	{S3，U1}→{U17}	0.04	1	8.67
触碰事故	2	{P16，S3，U1} →{U17}	0.04	1	8.67
	3	{E3，U9，U12}→{U12}	0.07	1	6.5
	1	{O3，U5}→{U8}	0.12	0.57	2.69
风灾事故	2	{O3，P9，U5}→{U8}	0.12	0.57	2.69
	3	{O3，P2，P9，U8}→{U5}	0.12	1	1.65
	1	{E4，U4}→{U18}	0.12	1	8.5
搁浅事故	2	{O4，U4}→{U18}	0.12	1	8.5
	3	{O5，U4}→{U18}	0.12	1	8.5
	1	{S1，U3} →{U27}	0.08	0.38	3.47
火灾/爆炸事故	2	{P6，U3}→{U17}	0.05	0.25	2.31
	3	{E3，E5，O2，P6，U17}→{U3}	0.05	1	1.85
	1	{P1，U13}→{U4}	0.04	0.72	1.85
碰撞事故	2	{S4，U1}→{U17}	0.06	0.53	1.79
	3	{P11，U1}→{U4}	0.07	0.68	1.73
	1	{P9，P16，S3，U8}→{U9}	0.03	0.43	2.74
自沉事故	2	{P9，U14}→{U5}	0.02	0.27	2.02
	3	{P9，U9}→{U8}	0.03	0.28	1.79

下载: 导出CSV

参考文献(21)

[1]	席永涛, 胡甚平, 陈伟炯, 等. 船舶驾驶员操作可靠性量化的CREAM改进模型[J]. 中国安全科学学报, 2015, 25(11): 3-9. XI Y T, HU S P, CHEN W J, et al. Improved CREAM model for operational reliability verification of marine pilots[J]. China Safety Science Journal, 2015, 25(11): 3-9. (in Chinese)
[2]	HUANG C H, HU S P. Factors correlation mining on maritime accidents database using association rule learning algorithm[J]. Cluster Computing, 2019, 22(S2): S4551-S4559.
[3]	GRAZIANO A, TEIXEIRA A P, GUEDES S C. Classification of human errors in grounding and collision accidents using the TRACEr taxonomy[J]. Safety Science, 2016, 86(2): 245-257.
[4]	WANG H X, LIU Z J, WANG X J, et al. An analysis of factors affecting the severity of marine accidents[J]. Reliability Engineering and System Safety, 2021, 210(3): 107513.
[5]	杨柏丞, 马建斌, 王哲凯, 等. 海事事故的聚类与关联规则[J]. 中国航海, 2018, 41(3): 63-67. YANG B C, MA J B, WANG Z K, et al. Clustering and assosiaction rule on marine accidents[J]. Navigation of China, 2018, 41(3): 63-67. (in Chinese)
[6]	FENG Y W, WANG H X, XIA G Q, et al. A machine learning-based data-driven method for risk analysis of marine accidents[J]. Journal of Marine Engineering and Technology, 2024, 24(2): 147-158
[7]	LIAO S G, WENG J X, ZHANG Z M, et al. Probabilistic modeling of maritime accident scenarios leveraging bayesian network techniques[J]. Journal of Marine Science and Engineering, 2023, 11(8): 1513.
[8]	范中洲, 王宁飞. 基于SEM的船员不安全行为研究[J]. 安全与环境学报, 2021, 21(2): 682-687. FAN Z Z, WANG Y F. On the unsafe or reckless behaviors of the seafarer based on the structural equation model (SEM)[J]. Journal of Safety and Environment, 2021, 21(2): 682-687. (in Chinese)
[9]	LI H H, REN X J, YANG Z L. Data-driven bayesian network for risk analysis of global maritime accidents[J]. Reliability & System Safety, 2023, 230: 108938.
[10]	ASLAN B, SAHIN B, YAZIR D. A comprehensive analysis for collision and grounding accidents by using a hybrid FTA-FUCOM-ETA method[J]. International Journal of Shipping and Transport Logistics, 2024, 18(4): 449-490.
[11]	LAN H, MA X X, MA L H, et al. Pattern investigation of total loss maritime accidents based on association rule mining[J]. Reliability Engineering & System Safety, 2023, 229: 108893.
[12]	冯胤伟, 刘正江, 蒋子怡, 等. 基于关联规则挖掘和复杂网络理论的船舶碰撞事故影响因素分析[J]. 大连海事大学学报, 2023, 49(3): 31-44. FENG Y W, LIU Z J, JIANG Z Y, et al. Analysis of factors affecting ship collision based on association rule mining and complex network theory[J]. Journal of Dalian Maritime University, 2023, 49(3): 31-44. (in Chinese)
[13]	SAETREVIK B, HYSTAD S W. Situation awareness as a determinant for unsafe actions and subjective risk assessment on offshore attendant vessels[J]. Safety Science, 2017, 93: 214-221.
[14]	许未, 何世伟, 刘朝辉, 等. 基于关联规则的铁路事故致因网络构建与分析[J]. 铁道运输与经济, 2020, 42(11): 72-79. XU W, HE S W, LIU Z H, et al. Construction and analysis of railway accident causation network based on association rules[J]. Railway Transport and Economy, 2020, 42(11): 72-79. (in Chinese)
[15]	程明, 梅傲然. 基于关联规则的跑道着陆事件演化网络构建研究[J]. 中国安全生产科学技术, 2022, 18(12): 203-208. CHENG M, MEI A R. Research on construction of evolution network for runway landing event based on association rules[J]. Journal of Safety Science and Technology, 2022, 18(12): 203-208. (in Chinese)
[16]	LAN H, MA X X, QIAO W L, et al. On the causation of seafarers' unsafe acts using grounded theory and association rule[J]. Reliability Engineering & System Safety, 2022, 223: 108498.
[17]	LAN H, MA X X. Risk evolution analysis of seafarers' unsafe acts in maritime accidents based on directed weighted CN[J]. Applied Sciences, 2024, 14(6): 2595.
[18]	纪文璐, 王海龙, 苏贵斌, 等. 基于关联规则算法的推荐方法研究综述[J]. 计算机工程与应用, 2020, 56(22): 33-41. JI W L, WANG H L, SU G B, et al. Review of recommendation methods based on association rules algorithm[J]. Computer Engineering and Applications, 2020, 56(22): 33-41. (in Chinese)
[19]	胡松, 杨贝, 翁剑成, 等. 基于关联规则的居民公共交通依赖性致因分析[J]. 交通信息与安全, 2023, 41(3): 147-156. doi: 10.3963/j.jssn.1674-4861.2023.03.016 HU S, YANG B, WENG J C, et al. A cause analysis of residents' dependence on public transportation based on association rules[J]. Journal of Transport Information and Safety, 2023, 41(3): 147-156. (in Chinese) doi: 10.3963/j.jssn.1674-4861.2023.03.016
[20]	QIAO W L, GUO H T Y, DENG W Y, et al. Complex network-based risk analysis for maritime heavy casualties in China during 2012—2021[J]. Ocean Engineering, 2024, 308: 118258.
[21]	LAN H, MA X X, QIAO W L, et al. Determining the critical risk factors for predicting the severity of ship collision accidents using a data-driven approach[J]. Reliability Engineering & System Safety, 2023, 230: 108934.