基于功能分解结构模型的工程知识自动提取与组织方法

Engineering Knowledge Acquisition Method Based on Functional Decomposition Structure Model

知识的提取与重用对提高工程设计效率、减少设计活动中的重复工作有着重要意义,针对工程领域知识形式的多样化、结构化等特点,提出一种基于功能分解结构模型的半自动化知识提取方法。通过功能分解完成结构模板的构建;采用命名实体识别技术从工程文本中提取设计相关关键信息;进一步基于隐含狄利克雷分布模型完成文本主题聚类,在此基础上实现关键信息与功能分解结构的关联;在提出该方法与流程的基础上,完成原型系统的设计与开发,并以自动武器概念设计以及闭锁机构的设计为例展示了完整的功能分解以及知识提取过程。研究结果表明:半自动知识提取方法能有效地减少知识提取过程中的人为工作;知识重用适应工程领域的设计思路,可向设计者提供相关的领域知识。

The acquisition and reuse of knowledge are of great significance for improving the efficiency of engineering design and reducing the duplication of work in design activities.A semi-automated knowledge acquisition method based on functional decomposition structure model is proposed for the diversified and structured knowledge forms in the engineering field.The construction of the structure template is completed based on functional decomposition,the named entity recognition technology is used to extract the key information related to the design from engineering texts,and then the topic clustering is realized based on the latent Dirichlet allocation model,based on which the key information and the functional decomposition structure are correlated.In accordance with the proposed method and procedure,the design of the prototype system is accomplished,and the complete functional decomposition and knowledge acquisition process are illustrated by the design of an automatic weapon and its breech locking mechanism.The result shows that the proposed method can be used effectively to reduce the human-involved work in the knowledge acquisition process.Knowledge reuse based on this can adapt to designers’thinking and provide the knowledge of related fields for designers.