4.7 Article

Distributed representation learning and intelligent retrieval of knowledge concepts for conceptual design

期刊

ADVANCED ENGINEERING INFORMATICS
卷 53, 期 -, 页码 -

出版社

ELSEVIER SCI LTD
DOI: 10.1016/j.aei.2022.101649

关键词

Data-driven conceptual design; Knowledge representation; Engineering semantic network; Pathfinding algorithm

资金

  1. National Key Research and Devel-opment Project of China [2018YFB1700702]
  2. Science & Technology Ministry Innovation Method Program of China [2020IM020400]
  3. National Natural Science Foundation of China [52175241]

向作者/读者索取更多资源

Data-driven conceptual design is an effective approach to generate novel and meaningful ideas by utilizing external knowledge, especially in the early design phase. However, the majority of engineering knowledge exists in unstructured and heterogeneous texts, posing challenges in capturing complex knowledge relationships and efficiently retrieving valuable implicit associations. In this work, we propose a new data-driven conceptual design approach that represents and retrieves cross-domain knowledge concepts through information-dense word embeddings and a semantic network. The validation results and case studies demonstrate the effectiveness and practicality of our proposed approach in enhancing engineering conceptual design.
Data-driven conceptual design is rapidly emerging as a powerful approach to generate novel and meaningful ideas by leveraging external knowledge especially in the early design phase. Currently, most existing studies focus on the identification and exploration of design knowledge by either using common-sense or building specific-domain ontology databases and semantic networks. However, the overwhelming majority of engineering knowledge is published as highly unstructured and heterogeneous texts, which presents two main challenges for modern conceptual design: (a) how to capture the highly contextual and complex knowledge relationships, (b) how to efficiently retrieve of meaningful and valuable implicit knowledge associations. To this end, in this work, we propose a new data-driven conceptual design approach to represent and retrieve cross-domain knowledge concepts for enhancing design ideation. Specifically, this methodology is divided into three parts. Firstly, engineering design knowledge from the massive body of scientific literature is efficiently learned as informationdense word embeddings, which can encode complex and diverse engineering knowledge concepts into a common distributed vector space. Secondly, we develop a novel semantic association metric to effectively quantify the strength of both explicit and implicit knowledge associations, which further guides the construction of a novel large-scale design knowledge semantic network (DKSN). The resulting DKSN can structure cross-domain engineering knowledge concepts into a weighted directed graph with interconnected nodes. Thirdly, to automatically explore both explicit and implicit knowledge associations of design queries, we further establish an intelligent retrieval framework by applying pathfinding algorithms on the DKSN. Next, the validation results on three benchmarks MTURK-771, TTR and MDEH demonstrate that our constructed DKSN can represent and associate engineering knowledge concepts better than existing state-of-the-art semantic networks. Eventually, two case studies show the effectiveness and practicality of our proposed approach in the real-world engineering conceptual design.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据