Negative collaboration risk analysis and control in manufacturing service collaboration based on complex network evolutionary game

被引:0
|
作者
Sun, Hanlin [1 ]
Zhang, Yongping [2 ]
Liu, Bo [2 ]
Sheng, Guojun [3 ]
Cheng, Ying [2 ]
Zuo, Ying [2 ]
Tao, Fei [2 ,4 ]
机构
[1] Beihang Univ, Sino French Engineer Sch, Beijing 100191, Peoples R China
[2] Beihang Univ, Sch Automat Sci & Elect Engn, Beijing 100191, Peoples R China
[3] COSMO Ind Intelligence Res Inst Co Ltd, Qingdao 266426, Peoples R China
[4] Beihang Univ, Int Res Inst Multidisciplinary Sci, Digital Twin Int Res Ctr, Beijing 100191, Peoples R China
基金
中国国家自然科学基金;
关键词
Manufacturing service collaboration; Collaboration behavior; Negative collaboration risk; Risk control;
D O I
10.1016/j.eswa.2024.125545
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In the era of the digital economy, manufacturing service collaboration (MSC) effectively addresses user personalization and customization through networked collaboration among service providers. However, opportunistic negative collaboration behaviors within the network can lead to risk generation, risk propagation and potential dysfunction of the entire collaboration network. Traditional risk control strategies are often based on experience and lack predictive validation. To improve the efficiency of risk control strategy formulation and validate the effectiveness of risk control, the article proposes a negative collaboration risk control optimal strategy exploration method. This method can realize effective optimal decision-making for risk control and effectiveness validation by combining the complex network evolutionary game and Q-learning. The experiment results show that this method is able to formulate situation-specific risk control strategies and keep negative collaboration providers below 10%, effectively controlling MSC risk.
引用
收藏
页数:13
相关论文
共 50 条
  • [21] Research on the Collaboration of Express Service Network Based on Resource Integration
    Wang, Qianying
    Zhang, Keming
    Mu, Dong
    2016 INTERNATIONAL CONFERENCE ON LOGISTICS, INFORMATICS AND SERVICE SCIENCES (LISS' 2016), 2016,
  • [22] Service composition method based on collaboration network and task circumstance
    Peng, Y.-B. (pyb2010@126.com), 1600, Shanghai Jiaotong University (48):
  • [23] Evolutionary Analysis of Developer Collaboration Network in Cloud Foundry OSS Community
    Zhang, Pengchen
    Liu, Peng
    Wang, Nianxin
    KNOWLEDGE AND SYSTEMS SCIENCES, KSS 2019, 2019, 1103 : 87 - 105
  • [24] Evolutionary analysis of international collaboration network of Chinese scholars in management research
    Li Zhai
    Xiangbin Yan
    Joshana Shibchurn
    Xiaohong Song
    Scientometrics, 2014, 98 : 1435 - 1454
  • [25] Evolutionary analysis of international collaboration network of Chinese scholars in management research
    Zhai, Li
    Yan, Xiangbin
    Shibchurn, Joshana
    Song, Xiaohong
    SCIENTOMETRICS, 2014, 98 (02) : 1435 - 1454
  • [26] Contract-collaboration network method for modeling manufacturing resource control workflows
    Kim, CO
    Jun, J
    Kim, SS
    Baek, JK
    JOURNAL OF INTELLIGENT MANUFACTURING, 2002, 13 (06) : 463 - 475
  • [27] Contract-collaboration network method for modeling manufacturing resource control workflows
    Chang-Ouk Kim
    Jin Jun
    Sung-Shick Kim
    Jong Kwan Baek
    Journal of Intelligent Manufacturing, 2002, 13 : 463 - 475
  • [28] Dynamic Model of Collaboration in Multi-Agent System Based on Evolutionary Game Theory
    Gou, Zhuozhuo
    Deng, Yansong
    GAMES, 2021, 12 (04):
  • [29] Research on Service Discovery of Manufacturing Supply Chain Intelligent Collaboration Based on SOA
    Deng, Shan
    Wu, Zeshu
    PROCEEDINGS OF THE FOURTH INTERNATIONAL CONFERENCE ON OPERATIONS AND SUPPLY CHAIN MANAGEMENT (ICOSCM 2010), 2010, 4 : 133 - 135
  • [30] Graph-based operational robustness analysis of industrial Internet of things platform for manufacturing service collaboration
    Cheng, Ying
    Gao, Yanshan
    Wang, Lei
    Tao, Fei
    Wang, Qing-Guo
    INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH, 2023, 61 (13) : 4237 - 4264