.png){kind=icon}
返回
Behavior-environment interaction aware manufacturing service collaboration optimization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.jmsy.2024.03.011.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Manufacturing enterprises participate in platform-based collaboration by encapsulating their manufacturing resources/capabilities as manufacturing services (MSs). In platform-based manufacturing service collaboration (MSC), the mutually influential between behaviors of MS providers and the collaborative environment will have an important impact on the MSs supply ability and the MSC scheme planning. Therefore, this paper proposes a behavior-environment interaction aware MSC optimization method. Firstly, the behavior-environment interaction mechanism considering the proactive/ passive behaviors of MS providers (i.e., join/exit platform behavior, accept/reject task behavior, cooperate/non-cooperate behavior) and the collaborative environment is built. Then, the collaborative environment is described by the BBV complex network, taking into account the inherent attributes of the providers and the collaborative relationship based on the priority attachment characteristics. Finally, the behaviour-environment interaction mechanism is combined with the Dueling DQN algorithm to address the MSC optimization problem. The proposed method can effectively solve the MSC optimization problem, ensuring a balanced consideration of the interests of consumers, MS providers and the platform. According to the experiment, the arrival of new MS providers will enhance the global efficiency of the platform. And the higher the willingness of MS providers to participate in MSC, the higher their income and the global efficiency of the platform.
Keyword:
Manufacturing service collaboration
Deep reinforcement learning
BBV complex network
Behavior-environment interaction
期刊
IF:
14.2
论文数:
2.7K
被引数:
1.6W
机构
引用论文
Viral and immunological factors associated with breast milk transmission of SIV in rhesus macaques
OAAI
.png){kind=icon}
OAAI分享收藏Long/Short-Term Utility Aware Optimal Selection of Manufacturing Service Composition Toward Industrial Internet Platforms面向工业互联网平台的制造服务组合长短期效用感知最优选择
OAAI
OAAI分享收藏Dynamic production scheduling towards self-organizing mass personalization: A multi-agent dueling deep reinforcement learning approach面向自组织大规模个性化的动态生产调度: 一种多智能体对决深度强化学习方法
PREAI
分享收藏Manufacturing service composition model based on synergy effect: A social network analysis approach
PREAI
分享收藏Multi-attribute negotiation mechanism for manufacturing service allocation in smart manufacturing
PREAI
分享收藏Platform-Based Manufacturing Service Collaboration: A Supply-Demand Aware Adaptive Scheduling Mechanism基于平台的制造服务协作: 一种供需感知的自适应调度机制
PREAI
分享收藏Manufacturing Services Scheduling With Supply-Demand Dual Dynamic Uncertainties Toward Industrial Internet Platforms面向工业互联网平台的供需双动态不确定性制造服务调度
PREAI
分享收藏
查看更多内容