流程工厂设计中的规则挖掘与智能预测  

Rule Mining and Intelligent Prediction in Process Plant Design

作　　者：温蕊 唐卫清[1,2] 苏智勇[3] 

机构地区：[1]南京理工大学计算机科学与工程学院,南京210094 [2]中国科学院计算技术研究所,北京100190 [3]南京理工大学自动化学院,南京210094

出　　处：《计算机辅助设计与图形学学报》2015年第5期930-939,共10页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(61300160)

摘　　要：流程工厂设计涉及不同的工程应用背景及专业知识,大量隐含的设计规则尚未提炼,因此建模过程存在效率低、模型质量不高等问题.结合流程工厂模型的领域特性,提出一种用于挖掘工厂设计规则的频繁类型树模型.该模型以大量实例工厂模型中各构件的属性及拓扑连接关系为依据构造频繁类型树;在后续模型的构建过程中,通过对该树的查询为当前工厂设计提供实时的智能预测.实验结果表明,文中模型能够挖掘到不同工程应用背景下的隐含建模知识,在未来模型的构建过程中,利用这些知识所提供的智能预测可以大幅缩小构件选择范围,有效地提升流程工厂模型的构建效率及设计质量.Process plant design involves a variety of engineering backgrounds and specialized knowledge. With abundant latent design rules not being extracted, the existing modeling methods present the disadvan-tages of low efficiency and deficient model quality. In that sense, a Frequent-Type-Tree model for mining process plant design rules is proposed. The model constructs a Frequent Type Tree by analyzing component attributes and topological correlations in plant models and provides real-time intelligent predictions by que-rying the tree for future design. Experimental results show that the proposed model can mine valuable latent modeling knowledge in various application backgrounds. The mined knowledge is then used to shrink ranges of component selection by a large margin while future modeling efficiency and design quality is improved significantly.

关 键 词：流程工厂建模 结构分析 关联挖掘 构件预测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]