工程进度计划中的知识挖掘与应用

发布时间：2019-05-06 17:23

【摘要】：建设企业在工程实践中积累着大量历史项目的进度计划及管理文档资料,其中蕴含有丰富的工程经验和知识。受制于技术手段的不足,这些知识无法得到有效的识别和利用。该文基于图挖掘的理论,提出了一种能够从进度计划的网络图和Gantt图中识别出具有固定组合模式且频繁出现的工序集合的算法。试验测试和应用的结果表明,算法具有良好的可行性和有效性。算法的提出有助于项目管理人员从已有的进度计划中识别出有价值的信息和知识,为当前工程项目的计划制定和进度控制提供决策依据,以及为研究和开发工程进度管理和决策支持系统提供技术基础。
[Abstract]:Construction enterprises have accumulated a large number of historical project schedule and management documents in the engineering practice, which contains rich engineering experience and knowledge. Constrained by the lack of technical means, these knowledge can not be effectively identified and utilized. In this paper, based on the theory of graph mining, an algorithm is proposed to identify the set of processes with fixed combination pattern and frequent occurrence from the network graph and Gantt graph of schedule plan. The results of test and application show that the algorithm is feasible and effective. The proposed algorithm is helpful for project managers to identify valuable information and knowledge from the existing schedule, and to provide decision-making basis for current project planning and schedule control. And provide technical basis for research and development of project schedule management and decision support system.
【作者单位】：清华大学土木工程系清华大学土木工程系
【基金】：国家自然科学基金资助项目(50478015)
【分类号】：TU722

【参考文献】