Integrated modeling for retired mechanical product genes in remanufacturing: A knowledge graph-based approach

Guo, Yuyao, Wang, Lei, Zhang, Zelin, Cao, Jianhua, Xia, Xuhui and Liu, Ying ORCID: https://orcid.org/0000-0001-9319-5940 2024. Integrated modeling for retired mechanical product genes in remanufacturing: A knowledge graph-based approach. Advanced Engineering Informatics 59 , 102254. 10.1016/j.aei.2023.102254

Preview

PDF - Accepted Post-Print Version Download (872kB) | Preview

Abstract

Retired mechanical product genes refer to a collection of information that describes the structure, status, and related characteristics of retired mechanical products. Leveraging this information, along with its implicit knowledge, is a key approach to enhance the intelligence and efficiency of the remanufacturing process. This study aims to automatically obtain and integrate multi-source, heterogeneous, multilayer, and multidimensional retired mechanical product information and its implicit knowledge through a knowledge graph to form a gene bank, providing data basis for the remanufacturing process. First, the conceptual model of retired mechanical product genes and overall modeling framework based on knowledge graph are established. Next, according to the gene characteristics on different product layers, appropriate modeling methods were designed for part genes, product function and structure genes, product performance and failure genes respectively. For implicit rules and knowledge that pose challenges for direct representation, we express them in the IF-THEN form and convert them into triples. Then, an information fusion method is employed to integrate genes information on various layers into a gene graph. Finally, the proposed integrated modeling approach was evaluated in a scenario of remanufacturing an eleven-roll straightening machine. The results indicate that it can automatically obtain part genes information quickly and effectively. Additionally, it was confirmed that the constructed gene graph exhibits good accuracy and completeness, demonstrating the promising application prospects of the proposed method in remanufacturing.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Engineering
Publisher:	Elsevier
ISSN:	1474-0346
Date of First Compliant Deposit:	28 November 2023
Date of Acceptance:	6 November 2023
Last Modified:	27 Nov 2024 02:45
URI:	https://orca.cardiff.ac.uk/id/eprint/164430

Actions (repository staff only)

Edit Item