新型建筑智能化平台节点拓扑匹配算法研究  

Research on node topology matching algorithm of new building intelligent platform

作　　者：杨亚龙[1,2,3] 洪德健 张睿 刘为[1,2,3] YANG Yalong;HONG Dejian;ZHAN GRui;LIU Wei(Anhui Province Key Laboratory of Intelligent Building and Building Energy Saving,Anhui Jianzhu University,Hefei 230022,China;School of Electronic and Information Engineering,Anhui Jianzhu University,Hefei 230061,China;Institute of Plasma Physics,Chinese Academy of Sciences,Hefei 230031,China)

机构地区：[1]安徽建筑大学智能建筑与建筑节能安徽省重点实验室,安徽合肥230022 [2]安徽建筑大学电子与信息工程学院,安徽合肥230061 [3]中国科学院等离子体物理研究所,安徽合肥230031

出　　处：《大连理工大学学报》2019年第3期310-315,共6页Journal of Dalian University of Technology

基　　金：国家重点研发计划资助项目(2017YFC0704100)

摘　　要：针对新型建筑智能化平台中空间拓扑与节点拓扑一致性问题,提出了一种拓扑匹配算法.在拓扑匹配过程中,通过提取AutoCAD建筑平面图的B-rep信息,将其表示为以空间单元为节点的属性邻接图.建筑平面图空间拓扑被表示为大图,平台中智能节点交互形成的拓扑被表示为小图,一致性问题被转化为大图中查询同构小图问题.该算法与传统的子图同构算法相比,首先利用顶点度优化匹配顺序,其次增加顶点的邻域信息作为剪枝条件,对候选集匹配项进行筛选,最后采用非递归-回溯思想对数据节点进行验证,并在真实的数据集上验证了算法的适用性与高效性.A topology matching algorithm is proposed to solve the consistency problem between spatial topology and node topology based on new building intelligent platform. In the process of topology matching, the B-rep information of AutoCAD building plans is extracted and represented as an attribute adjacent graph with spatial units as nodes. The spatial topology of the building plan is represented as a big graph, and the topology formed by the interaction of intelligent nodes in the platform is represented as a small graph, and the consistency problem is translated into querying isomorphic small graph in the big graph. Compared with the traditional subgraph isomorphism algorithm, firstly, node degree is used to optimize the matching order. Secondly, the neighborhood information of vertices is added as pruning condition to filter the matching items of candidate sets. Finally, non-recursive backtracking is used to verify the data nodes, and the applicability and efficiency of the algorithm are verified on the real data sets.

关 键 词：新型建筑智能化平台 AUTOCAD 子图同构 非递归 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]