基于模糊DBN的生鲜冷链物流风险评估方法

马颖; 隽雯露; 王诗颖

doi:10.3963/j.jssn.1674-4861.2025.04.016

基于模糊DBN的生鲜冷链物流风险评估方法

doi: 10.3963/j.jssn.1674-4861.2025.04.016

武汉理工大学管理学院武汉 430070

基金项目:

国家重点研发计划项目 2023YFE0208300

武汉市科技局、武汉市交通运输局联合项目 2023-2-5

详细信息

通讯作者:
马颖(1975—)，博士，教授. 研究方向：风险与预警管理. E-mail：mying331@163.com

中图分类号: TP18
计量
- 文章访问数: 2
- HTML全文浏览量: 2
- PDF下载量: 0
- 被引次数: 0
出版历程
- 收稿日期: 2025-03-31

Risk Assessment of Fresh Cold Chain Logistics Based on Fuzzy DBN

School of Management, Wuhan University of Technology, Wuhan 430070, China

摘要

摘要: 针对生鲜冷链物流风险因素多、风险状态随时间变化等问题，为提升生鲜冷链物流风险动态评估效能，精准识别其关键风险诱因，基于模糊动态贝叶斯网络开展生鲜冷链物流风险评估方法研究。基于全流程-多维度融合视角，采用分解分析法解构生鲜冷链物流运作全流程，运用熵权-TOPSIS法深度筛选核心指标，构建了全流程多维度生鲜冷链物流风险评估指标体系。并结合模糊理论，纳入生鲜特性参数，以确定动态贝叶斯网络的条件概率分布，从而建立生鲜冷链物流的DBN风险评估模型。以武汉市某生鲜冷链物流企业为例开展实证分析，利用GeNIe软件建立DBN风险评估模型，对生鲜冷链物流的风险因素概率评估。结果表明：生鲜冷链物流风险的发生概率随着时间的转移从0.24增加到0.31；其中，运输环节呈现出最高的风险发生概率，构成生鲜冷链物流系统的关键风险变量，且随着时间流逝，存储环节因堆放方式不当、存储温度不适等原因，存储风险易转移至运输环节，导致运输风险增加约10%，对生鲜冷链物流风险影响最大。与BN相比，模糊DBN风险评估的精准性提高19.73%。
- 供应链风险管理 /
- 生鲜冷链物流 /
- 风险评估 /
- 模糊动态贝叶斯网络
Abstract: To address problems such as numerous risk factors and time-varying risk states in fresh cold chain logis-tics, a risk assessment method for fresh cold chain logistics is studied based on the fuzzy dynamic Bayesian network (DBN). To improve the efficiency of dynamic risk assessment for fresh cold chain logistics and accurately identify key risk triggers. From the perspective of full-process and multi-dimensional integration, the entire operation pro-cess of fresh cold chain logistics is deconstructed using the decomposition analysis method. Core indicators are screened in depth by combining the EWM and TOPSIS. Through these steps, a full-process and multi-dimensional risk assessment indicator system for fresh cold chain logistics is constructed. Meanwhile, fuzzy theory is integrated, and fresh product characteristic parameters are incorporated to determine the conditional probability distribution of the DBN. Thus, a DBN risk assessment model for fresh cold chain logistics is established. An empirical analysis is conducted with a fresh cold chain logistics enterprise in Wuhan as the research object. The DBN risk assessment model is built using GeNIe software, and the probabilities of risk factors in fresh cold chain logistics are evaluated. Results show that the occurrence probability of fresh cold chain logistics risks increases from 0.24 to 0.31 over time. Among all links, the transportation link exhibits the highest risk occurrence probability and constitutes a key risk variable in the fresh cold chain logistics system. Storage risks are prone to transfer to the transportation link due to improper stacking methods and unsuitable storage temperatures as time passes. This transfer leads to an approxi-mately 10% increase in transportation risks, which exerts the greatest impact on fresh cold chain logistics risks. Compared with the static BN, the accuracy of the fuzzy DBN risk assessment is improved by 19.73%.
- Supply chain risk management /
- fresh cold chain logistics /
- risk assessment /
- fuzzy dynamic Bayesian network

HTML全文

图 1 生鲜产品冷链物流典型运作流程

Figure 1. Typical operation process of cold chain logistics of fresh products

下载: 全尺寸图片幻灯片

图 2 生鲜冷链物流风险评估指标体系

Figure 2. Risk assessment index system of fresh cold chain logistics

下载: 全尺寸图片幻灯片

图 3 先验网络

Figure 3. Prior network

下载: 全尺寸图片幻灯片

图 4 转移网络

Figure 4. Transfer Network

下载: 全尺寸图片幻灯片

图 5 DBN风险评估模型推理结果

Figure 5. Reasoning results of DBN risk assessment model

下载: 全尺寸图片幻灯片

图 6 节点概率变化图

Figure 6. diagram of node probability change

下载: 全尺寸图片幻灯片

图 7 模型评价指标比较

Figure 7. Comparison of model evaluation metrics

下载: 全尺寸图片幻灯片

表 1 风险评估指标

Table 1. Risk indicator system

一级指标	二级指标	风险致因
加工风险	加工设备	加工设备突然故障，未使用专用仪器设备检验等
	产品自身	生鲜产品未加工前已经腐烂
	加工车间环境	加工车间环境是否干净，符合国家标准
	预冷技术	由于预冷技术不合格导致加工过程中的生鲜腐烂
	产品分类	生鲜产品是否根据品类进行分类
包装风险	包装材料	包装材料劣质
	包装规格	包装规格不当
	包装密封程度	包装密封性差导致产品变质
	包装安全	包装内进入异物
储存风险	存储温控设备	存储温度的失控导致变质、腐烂
	冷库设计	冷库的区域布局、最优库存设置是否合理
	堆放方式	堆放方式的不合理导致产品和包装的破损
	低温分拣操作	冷库是否设置安全过渡区进行分拣
	人员管理	仓储人员的管理失误造成的风险问题
运输风险	运送车辆	运送车辆的故障，是否按时更新检测
	运输设备	运输过程中温控设备的失衡造成的生鲜变质
	监控技术	运输过程是否有定位监控技术
	装卸过程	装卸过程的不合规范导致产品以及包装的破损
	装卸效率	人工装卸过慢导致生鲜产品配送延迟
	交通堵塞	交通堵塞造成的配送延迟

下载: 导出CSV

表 2 风险因素评价属性权重

Table 2. Attribute weights for risk factor evaluation

评价属性	风险发生概率	风险损失程度
信息熵E_j	0.915 9	0.893 6
信息冗余度d_j	0.084 1	0.106 4
权重ω_j	0.441 5	0.558 5

下载: 导出CSV

表 3 风险因素贴近度

Table 3. Proximity to risk factors

风险类别	风险因素	贴近度C_i	排序
加工风险	加工设备	0.703 2	4
	产品自身	0.558 4	11
	加工车间环境	0.075 2	20
	预冷技术	1.000 0	1
	产品分类	0.166 9	17
包装风险	包装材料	0.625 6	8
	包装规格	0.658 0	6
	包装密封程度	0.649 1	7
	包装安全	0.465 9	13
	存储温控设备	0.924 8	2
	冷库设计	0.210 0	16
储存风险	堆放方式	0.625 6	9
	低温分拣操作	0.237 4	15
	人员管理	0.439 3	14
	运送车辆	0.519 0	12
	运输设备	0.824 9	3
运输风险	监控技术	0.116 6	19
	装卸过程	0.660 9	5
	装卸效率	0.145 3	18
	交通堵塞	0.599 8	10

下载: 导出CSV

表 4 三角模糊数形式和λ截集

Table 4. Triangular fuzzy number form and λ cut sets

专家判断语言	三角模糊数形式	λ截集
非常低(VL)	f_VL =(0，0，0.15)	[0, 0.15-0.15λ]
偏低(FL)	f_FL =(0.1，0.25，0.4)	[0.1 + 0.15λ, 0.4-0.15λ]
中等(M)	f_M=(0.3，0.5，0.7)	[0.3 + 0.2λ, 0.7-0.2λ]
偏高(FH)	f_FH =(0.6，0.75，0.9)	[0.6 + 0.15λ, 0.9-0.15λ]
非常高(VH)	f_VH =(0.85，1，1)	[0.85 + 0.15λ, 1]

下载: 导出CSV

表 5 先验概率

Table 5. Prior Probability

节点名称	先验概率/%
节点名称	State0	State1
加工设备故障	0.754	0.246
加工腐烂食品	0.935	0.065
预冷不合格	0.414	0.586
包装规格不符	0.500	0.500
包装密封性差	0.708	0.292
杂物进入包装	0.844	0.156
装卸不合规范	0.586	0.414
运送车辆故障	0.713	0.287
运输设备故障	0.542	0.458
交通堵塞	0.287	0.713
存储温度失控	0.419	0.581
堆放方式错误	0.457	0.543
人员管理失误	0.667	0.333

下载: 导出CSV

表 6 总结点及风险型节点转移概率

Table 6. Transfer probabilities of summary points and risk-type nodes

节点	t+1	t
节点	t+1	State0	State1
总结点	State0	0.5	0.2
总结点	State1	0.5	0.8
加工风险	State0	0.5	0.1
加工风险	State1	0.5	0.9
包装风险	State0	0.5	0.1
包装风险	State1	0.5	0.9
储存风险	State0	0.5	0.1
储存风险	State1	0.5	0.9
运输风险	State0	0.5	0.1
运输风险	State1	0.5	0.9

下载: 导出CSV

表 7 BN模型总结点与风险型节点推理结果

Table 7. Summary Points of BN Model and Reasoning Results of Risk Nodes

节点名称	State0	State1
生鲜冷链物流失效	0.76	0.24
加工风险	0.83	0.17
包装风险	0.72	0.28
储存风险	0.71	0.29
运输风险	0.63	0.37

下载: 导出CSV

参考文献(20)

[1]	GIBSON E K, ALMEIDA G, JONES L S, et al. Inactivation of bacteria on fresh produce by batch wash ozone sanita-tion[J]. Food Control, 2019, 106: 106747. doi: 10.1016/j.foodcont.2019.106747
[2]	NAKANDALA D, LAU H, ZHAO L. Development of a hy-brid fresh food supply chain risk assessment model[J]. Inter-national Journal of Production Research, 2016, 55(14): 4180-4195.
[3]	江雨燕, 尹莉, 王付宇. 多配送中心半开放式冷链物流配送路径优化[J]. 复杂系统与复杂性科学, 2024, 21(2): 137-146. JIANG Y Y, YIN L, WANG F Y. Optimization of distribution path for semi-open cold chain logistics with multiple distribu-tion centers[J]. Complex Systems and Complexity Science, 2024, 21(2): 137-146. (in Chinese)
[4]	张芳, 武杰, 杨悦. 风险规避的冷链物流服务供应链减排协调决策[J]. 计算机工程与应用, 2021, 57(24): 259-267. ZHANG F, WU J, YANG Y. Emission reduction coordination decision of cold chain logistics service supply chain with risk aversion[J]. Computer Engineering and Applications, 2021, 57(24): 259-267. (in Chinese)
[5]	杨扬, 杨小佳, 喻庆芳. 基于系统动力学的生鲜农产品国际冷链物流运作风险控制研究—以云南省生鲜蔬菜国际冷链物流为例[J]. 北京交通大学学报(社会科学版), 2017, 16 (3): 119-128. YANG Y, YANG X J, YU Q F. Research on operation risk control of international cold chain logistics for fresh agricul-tural products based on system dynamics — a case study of international cold chain logistics for fresh vegetables in Yun-nan Province[J]. Journal of Beijing Jiaotong University(So-cial Sciences Edition), 2017, 16(3): 119-128. (in Chinese)
[6]	杨扬, 袁媛, 李杰梅. 基于HACCP的生鲜农产品国际冷链物流质量控制体系研究—以云南省蔬菜出口泰国为例[J]. 北京交通大学学报(社会科学版), 2016, 15(2): 103-108. YANG Y, YUAN Y, LI J M. Research on quality control sys-tem of international cold chain logistics for fresh agricultural products based on HACCP — a case study of vegetable ex-port from Yunnan province to Thailand[J]. Journal of Beijing Jiaotong University(Social Sciences Edition), 2016, 15(2): 103-108. (in Chinese)
[7]	申笑宇, 赵悦. 生鲜电商前置仓冷链物流断链风险影响因素研究[J]. 安全与环境工程, 2023, 30(1): 9-18. SHEN X Y, ZHAO Y. Study on influencing factors of cold chain logistics chain breakage risk in front warehouse of fresh e-commerce[J]. Safety and Environmental Engineer-ing, 2023, 30(1): 9-18. (in Chinese)
[8]	彭本红, 武柏宇, 周叶. 冷链物流断链风险的熵权可拓评价研究[J]. 北京交通大学学报(社会科学版), 2017, 16(1): 110-119. PENG B H, WU B Y, ZHOU Y. Study on the extension evalu-ation of the risk of cold chain logistics breaking[J]. Journal of Beijing Jiaotong University (Social Sciences Edi-tion), 2017, 16(1): 110-119. (in Chinese)
[9]	CHEN H, ZHANG Q, LUO J, et al. Interruption risk assess-ment and transmission of fresh cold chain network based on a fuzzy Bayesian network[J]. Discrete Dynamics in Nature and Society, 2021(1): 9922569.
[10]	潘文栋, 孙作轩, 徐惠彬, 等. 桥梁拆除施工安全总体风险评估指标体系研究[J]. 公路交通科技, 2023, 40(增刊2): 174-180. PAN W D, SUN Z X, XU H B, et al. Study on overall risk as-sessment index system for bridge demolition construction safety[J]. Journal of Highway and Transportation Research and Development, 2023, 40(S2): 174-180. (in Chinese)
[11]	谢露强, 徐靖, 王海燕. 基于RS-RBFNN的邮轮建造物资物流集配风险预警[J]. 中国安全科学学报, 2023, 33(6): 114-121. XIE L Q, XU J, WANG H Y. Risk early warning of logistics distribution of cruise construction materials based on RS-RB-FNN[J]. China Safety Science Journal, 2023, 33(6): 114-121. (in Chinese)
[12]	熊懿. 生鲜农产品冷链物流销售环节风险评价与防范研究[J]. 价格理论与实践, 2022, (11): 189-192, 212. XIONG Y. Study on risk assessment and prevention of cold chain logistics sales of fresh agricultural products[J]. Price: Theory & Practice, 2022(11): 189-192, 212. (in Chinese)
[13]	万君, 刘勋勋. 基于动态贝叶斯网络的冷链物流风险评价[J]. 公路交通科技, 2023, 40(10): 248-256. WAN J, LIU X X. Risk assessment of cold chain logistics based on dynamic Bayesian network[J]. Journal of Highway and Transportation Research and Development, 2023, 40(10): 248-256. (in Chinese)
[14]	SHARMA S, PAI S S. Analysis of operating effectiveness of a cold chain model using Bayesian networks[J]. Business Process Management Journal, 2015, 21(4): 722-742. doi: 10.1108/BPMJ-10-2014-0105
[15]	陈伟炯, 范雯, 朱小林, 等. 乳制品冷链物流风险评估的DBN方法研究[J]. 系统仿真学报, 2019, 31(5): 936-945. CHEN W J, FAN W, ZHU X L, et al. Research on DBN method for risk assessment of dairy cold chain logistics[J]. Journal of System Simulation, 2019, 31(5): 936-945. (in Chinese)
[16]	邸鸿喜, 魏玖长, 张亚, 等. 重大疫情下疫苗冷链物流在物联网环境中的风险评估[J]. 中国安全生产科学技术, 2022, 18 (4): 54-60. DI H X, WEI J C, ZHANG Y, et al. Risk assessment of vac-cine cold chain logistics in Internet of Things environment under major epidemics[J]. Journal of Safety Science and Technology, 2022, 18(4): 54-60. (in Chinese)
[17]	付焯, 严余松, 郭茜, 等. 生鲜农产品供应链物流风险传递机理及控制[J]. 西南交通大学学报, 2018, 53(3): 654-660. FU Z, YAN Y S, GUO Q, et al. Risk transmission mecha-nism and control of fresh agricultural product supply chain logistics[J]. Journal of Southwest Jiaotong Universi-ty, 2018, 53(3): 654-660. (in Chinese)
[18]	WANG S X. Study on cold chain logistics operation and risk control of fresh e-commerce products[J]. Advances in Multi-media, 2022, 7272370, 11.
[19]	WANG Y, WANG X, GENG X. Analysis of key risks in fresh products supply chain logistics based on the N-K/SNA model[J]. IEEE Access, 2022, 10: 1. doi: 10.1109/ACCESS.2021.3137641
[20]	赵浩威, 钟鸣, 李林锋, 等. 基于改进组合赋权的港口自洽能源系统规划方案综合评价方法[J]. 交通信息与安全, 2024, 42 (5): 148-162. doi: 10.3963/j.jssn.1674-4861.2024.05.014 ZHAO H W, ZHONG M, LI L F, et al. Comprehensive eval-uation method for port self-consistent energy system plan-ning scheme based on improved combination weighting[J]. Journal of Transport Information and Safety, 2024, 42(5): 148-162. (in Chinese) doi: 10.3963/j.jssn.1674-4861.2024.05.014