Aic: an industrial knowledge graph with Abstraction-Instance-Capability reasoning abilities for personalized customization

Kai Zhang (), Zhiying Tu (), Dianhui Chu (), Xiaoping Lu () and Lucheng Chen ()
Additional contact information
Kai Zhang: Harbin Institute of Technology (Weihai)
Zhiying Tu: Harbin Institute of Technology (Weihai)
Dianhui Chu: Harbin Institute of Technology (Weihai)
Xiaoping Lu: State Key Laboratory of Massive Personalized Customization System and Technology
Lucheng Chen: State Key Laboratory of Massive Personalized Customization System and Technology

Journal of Intelligent Manufacturing, 2024, vol. 35, issue 7, No 22, 3419-3440

Abstract: Abstract In the era of the internet, people are increasingly interested in highly personalized customization, which has been leading the global industry to transform from “Enterprise centered Mass Manufacturing” to “User centered Mass Customization”. In recent decades, ontology-based semantic models have been used for semantic association description and syntax consistency alignment of product structures. However, the description of industrial terminology and general concepts has difficulty achieving accurate end-to-end matching of personalized user customization requirements and manufacturing capabilities. This requires detailed descriptions of process standards, component/assembly/part specifications, etc. Therefore, we propose the Abstraction-Instance-Capability (AIC) model based on a knowledge graph, which is a multigrained and multiview industrial knowledge model. By modeling industrial knowledge at a deeper level from various perspectives and by considering the expression of the relationships between knowledge, an industrial knowledge graph was constructed to support personalized customization. This graph can be used for personalized customization plan generation and other related operations, such as Design BOM (Bill of Materials) modification and verification. First, a meta-object facility (MOF)-based meta-model is defined for AIC model design. Second, the proposed model is used to define a multiview structure for modeling knowledge from various perspectives. Such a design realizes efficient industrial knowledge retrieval from various aspects, such as manufacturing resource retrieval, and production capacity analysis. Finally, in this paper we validate operability and introduce two case studies to demonstrate that the model has good performance in the recommendation of components (BOM modification) and the verification of personalized customization schemes (BOM verification).

Keywords: Personalized customization; Knowledge graph; Industrial knowledge modeling; Multiview; Bill of materials (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10845-023-02216-y Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joinma:v:35:y:2024:i:7:d:10.1007_s10845-023-02216-y

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10845

DOI: 10.1007/s10845-023-02216-y

Access Statistics for this article

Journal of Intelligent Manufacturing is currently edited by Andrew Kusiak

More articles in Journal of Intelligent Manufacturing from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().