.png){kind=icon}
.png){kind=icon}
Return
Complex chain integration and normalization model-based risk prediction in multiplex networked industrial chains
.png){kind=icon}
PRE
AI
DOI：10.1016/j.compeleceng.2024.109097.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In recent years, the industrial chain structure has taken on new characteristics of multiplex networks due to the various types of links that connect enterprises within and outside the industrial chain. This has increased the occurrence of risk problems such as disruptions, shortages and unsold products. Consequently, this paper proposes a risk prediction method for multiplex networked industrial chains based on complex chain integration and normalization model (RPMNIC-CCINM). Firstly, we perform feature reconstruction on the original data to enhance its utility in risk prediction. Next, we devise a multi-chain cascade fusion method to enhance the adaptability of the risk prediction model to the structure of multiplex industrial chain networks. Lastly, we calculate risk values for the current industrial chain from different dimensions in a cascading manner, achieving risk prediction in multiplex industrial chains. Experimental results demonstrate that the proposed method effectively predicts the risks of interruption, shortage, and oversupply in multiplex networked industrial chains, providing stable and reliable risk warnings for the industry chains.
Keywords:
Multiplex networked industrial chains
Data reconstruction
Risk fusion computing
Risk prediction
Journal
C
IF:
4.9
Papers:
6.7K
Citations:
1.3W