Semantic Networks for Engineering Design: A Survey

Abstract

There have been growing uses of semantic networks in the past decade, such as leveraging large-scale pre-trained graph knowledge databases for various natural language processing (NLP) tasks in engineering design research. Therefore, the paper provides a survey of the research that has employed semantic networks in the engineering design research community. The survey reveals that engineering design researchers have primarily relied on WordNet, ConceptNet, and other common-sense semantic network databases trained on non-engineering data sources to develop methods or tools for engineering design. Meanwhile, there are emerging efforts to mine large scale technical publication and patent databases to construct engineering-contextualized semantic network databases, e.g., B-Link and TechNet, to support NLP in engineering design. On this basis, we recommend future research directions for the construction and applications of engineering-related semantic networks in engineering design research and practice.

A twin data-driven approach for user-experience based design innovation

“…Compared with the former two representations, graph-based representations are widely studied as they can show concepts or entities and their complex relations. Their typical applications include semantic networks, ontology, concept maps, and knowledge graphs (Han et al, 2021). Some studies use graphical modelling tools to capture design knowledge while this process usually requires significant human involvement.…”

Establishing Product Appearance Specifications with the Identification of User Aesthetic Needs in Product Conceptual Design

“…The principles of aesthetic design can be defined as universally recognised compositional strategies for visual appearance. In addition to constituting and arranging the elements of visual design, they contribute to the aesthetics of the process [19]. Based on contrast, rhythm, balance, and proportion (CRBP), Stebbing enumerated the basic principles of aesthetic design on visual composition [54].…”

Engineering Knowledge Graph From Patent Database

“…For such inferences to be enabled, a supporting ontology (e.g., Mao and Sen [51]) must be built. Such an ontology should include classes (e.g., entity classification in Google Knowledge Graph 14 ) and attributes that characterize each entity and relationship, e.g., attributes of an analog-digital converter. The ontology plays a crucial role in building Q/A, query, and recommendation systems (e.g., Microsoft Academic Graph) that require named entity recognition and relation linking.…”

“…To meet the growing demands for engineering knowledge retrieval, representation, and concept generation-cum-evaluation, scholars have resorted to large scale, cross-domain, and commonsense knowledge graphs like ConceptNet and FreeBase [9]- [13] that may not provide facts that are technically dominant or relevant. Meanwhile, there is a lack of engineering-contextualized knowledge graph at the scale of ConceptNet and alike [14]. Our work aims to depart from the reliance on common-sense knowledge graphs by developing an engineering knowledge graph.…”