期刊文献+

基于复杂网络的化工过程层次符号有向图模型建立及关键节点识别 被引量:12

AHP-SDG model establishment and key node identification of chemical process system based on complex network
下载PDF
导出
摘要 针对定性符号有向图(signed directed graph,SDG)在化工过程系统中建模复杂度高、故障分辨率低、容易忽略部分变量等问题,提出一种基于复杂网络理论构建层次SDG网络模型并识别关键节点的方法。首先利用层次分析法对化工过程系统划分递阶层次结构,建立基于子系统的系统SDG网络模型,选取度中心性、接近中心性等多个节点重要性评价指标,采用主成分分析法确定各指标权重并利用逼近理想排序法(technique for order preference by similarity to an ideal solution,TOPSIS)多属性决策方法得到节点重要性的综合评价值,初步识别关键节点所在的子系统;然后建立子系统的SDG模型并细化为有向网络,采用Leader Rank算法对节点重要性进行排序,进而在子系统网络模型中确定关键节点的位置。案例计算结果表明该方法可以有效地降低建模的复杂性,提高关键节点识别的全面性和准确性,从而改善化工过程系统的安全稳定性。 A method of establishing AHP(analytic hierarchy process)-SDG(signed directed graph)model and identifying key nodes was proposed based on complex network. Considering high complexity,poor resolution and some variables neglected in the modeling of chemical process system. Firstly,system SDG model was established and transformed into undirected network after dividing hierarchy structure of chemical process. According to the multi-attribute decision-making method,the subsystems,which contain the key node,were identified by selecting multiple node importance indices,such as degree centrality,closeness centrality,flow betweenness centrality,eigenvector centrality and structural holes. The weight of each index was calculated by principal component analysis. Secondly,the subsystem SDG model was transformed into directed network. Key nodes were found further through Leader Rank algorithm. Experimental results showed that this method can not only reduce the complexity of modeling,but also can improve the comprehensive and accuracy of identification. Thereby,it can improve the security and stability of chemical process.
出处 《化工进展》 EI CAS CSCD 北大核心 2018年第2期444-451,共8页 Chemical Industry and Engineering Progress
基金 国家自然科学基金项目(21136003 41101570)
关键词 化工过程 层次符号有向图 复杂网络 主成分分析法 逼近理想排序法 LeaderRank算法 关键节点 chemical processes AHP-SDG model complex networks principal component analysis TOPSIS LeaderRank algorithm key node
  • 相关文献

参考文献12

二级参考文献154

共引文献441

同被引文献121

引证文献12

二级引证文献34

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部