摘要
为满足产品敏捷定制设计过程对知识的快速获取、组织和重用的要求,提出基于设计仓库的知识管理体系。设计仓库负责从不同数据源获取已有知识,并构建面向主题的多维设计知识模型;用户和设计人员通过基于事例推理系统输入查询请求,由在线分析处理系统采用钻取、切片、切块等操作完成相似实例的匹配,通过知识约简技术对在线分析处理输出的相似实例及其属性进行简化,然后基于事例推理系统在约简的基础上完成产品定制设计,机器学习则对新实例知识进行获取。最后阐述了知识管理体系对捆钞机定制设计过程的支持。
To satisfy the requirements for quick acquisition, organization and reuse of product knowledge in agile product customized design, the method of product knowledge management based on design repository was proposed. Design repository was responsible for organizing various kinds of knowledge from different data sources and setting up a subject-oriented multi-dimensional design knowledge model. Users and designers could input inquiries into Case-Based Reasoning (CBR) systems. Then On-Line Analysis and Processing (OLAP) drilled down and found the similar cases. Knowledge reduction techniques were adopted to reduce the retrieved similar cases output from OLAP, which improved CBR. Machine Learning could capture the cases adaptation knowledge to complement design repository. Finally, the proposed approach was demonstrated by a real application of tied bill machine.
出处
《计算机集成制造系统》
EI
CSCD
北大核心
2005年第6期831-835,共5页
Computer Integrated Manufacturing Systems
基金
国家863/CIMS主题资助项目(2002AA411410)
国家自然科学基金资助项目(50175008)。~~
关键词
知识管理
设计仓库
基于实例的推理
知识约简
knowledge management
design repository
case-based reasoning
knowledge reduction