采用设计结构矩阵的突发事件扩散预测及建模方法

发布时间：2018-12-11 06:55

【摘要】：针对现代供应链系统中突发事件扩散路径的控制问题,提出了对突发事件扩散路径进行预测分析的算法,并建立预测结果存储模型。根据基本供应链网络是由供应商、制造商以及分销商组成的特点,首先利用图论的思想结合设计结构矩阵(DSM)对供应链网络系统各组成部分之间的关联关系进行描述,然后利用设计的聚类算法对DSM聚类分析,预测系统中的所有突发事件扩散路径和影响范围。在分析结果的基础上,建立了扩散路径的可扩展性标记语言存储模型,提高了系统对突发事件的反应速度,缩短了反应时间,当突发事件引起成员发生变化时,系统能得到快速响应。最后以某供应链网络为例,使用所提出的算法对其中28个成员的扩散路径进行分析,利用存储模型得到扩散路径的3种类型。试验结果表明,通过提出的优化的聚类算法,缩短了迭代次数,提高了计算效率,并为所提算法与模型对控制供应链系统突发事件的扩散路径分析提供了实际意义。
[Abstract]:Aiming at the control of emergency diffusion path in modern supply chain system, an algorithm is proposed to predict and analyze the critical incident diffusion path, and a prediction result storage model is established. According to the characteristic that the basic supply chain network is composed of suppliers, manufacturers and distributors, the relationship between the components of the supply chain network system is described by using the idea of graph theory and the design structure matrix (DSM). Then we use the designed clustering algorithm to analyze the DSM cluster and predict the diffusion path and influence range of all sudden events in the system. Based on the analysis of the results, the extensible markup language storage model of diffusion path is established, which improves the response speed of the system and shortens the reaction time. The system can get quick response. Finally, taking a supply chain network as an example, the proposed algorithm is used to analyze the diffusion paths of 28 members, and three types of diffusion paths are obtained by using the storage model. The experimental results show that the proposed optimal clustering algorithm shortens the number of iterations and improves the computational efficiency. The proposed algorithm and model provide practical significance for the analysis of the diffusion path of the unexpected events in the supply chain system.
【作者单位】：西安工业大学机电工程学院;
【基金】：中国制造2025数字出版知识挖掘与服务创新平台及产业化项目(2230201) 陕西省特种加工重点实验室资助项目(15JS041)
【分类号】：F274;O151.21

【相似文献】