Machine learning and knowledge graph based design rule construction for additive manufacturing

Ko, Hyunwoong; Witherell, Paul; Lu, Yan; Kim, Samyeon; Rosen, David W.

doi:10.1016/j.addma.2020.101620

Cited by 83 publications

(41 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An ontology is a formal, explicit specification of a representational vocabulary for a shared domain of discourse (Gruber, 1993) that can be used to enhance the usage of CKM. Ontologies are often used to share a common understanding of the knowledge and to enable the reuse of domain knowledge among people or software agents (Noy & McGuiness, 2001).In addition, an ontology enables automated reasoning to infer implicit knowledge and detect inconsistencies in a knowledge base (Keet, 2018).In AM applications, ontologies have been proposed (1) to promote the modeling and reuse of knowledge towards the assistance of design (Kim et al, 2019;Ko et al,2021) and process planning (Liang, 2018) and (2) to be reused across computer systems to support knowledge and data management in an interoperable manner (Sanfilippo et al, 2019). Ontologies have been demonstrated as suitable to build a knowledge base for CKM (Abecker & van Elst, 2009).…”

Section: Ontology-based Collaborative Knowledge Managementmentioning

confidence: 99%

Collaborative knowledge management to identify data analytics opportunities in additive manufacturing

Park

Lee

et al. 2021

J Intell Manuf

Self Cite

View full text Add to dashboard Cite

Additive Manufacturing (AM) is becoming data-intensive. The ability to identify Data Analytics (DA) opportunities for effective use of AM data becomes a critical factor in the success of AM. To successfully identify high-potential DA opportunities in AM requires a set of distinctive interdisciplinary knowledge. This paper proposes a methodology that enables collaborative knowledge management for identifying and prioritizing DA opportunities in AM. The framework of the proposed methodology has three components: a team of experts, a DA Opportunity Knowledge Base (DOKB), and a prioritization tool. The team of experts provides diverse knowledge that can be used to identify and prioritize DA opportunities. The DOKB, developed by using the Web Ontology Language (OWL), captures diverse knowledge from the experts to identify DA opportunities. The prioritization tool ranks the identified DA opportunities by using the Fuzzy integrated Technique of Order Preference Similarity to the Ideal Solution (Fuzzy-TOPSIS). A case study, in which National Institute of Standards and Technology (NIST) researchers participated, demonstrates our methodology. As a result, 264 DA opportunities for AM's Laser-Powder Bed Fusion (L-PBF) process are identified and prioritized. The prioritized DA opportunities help set a DA direction for L-PBF AM. Our methodology keeps knowledge sharable, reusable, revisable, and extendable. Thus, this methodology can continue to facilitate collaboration within the AM community to identify high potential and high impact DA opportunities in AM.

show abstract

Section: Ontology-based Collaborative Knowledge Managementmentioning

confidence: 99%

Collaborative knowledge management to identify data analytics opportunities in additive manufacturing

Park

Lee

et al. 2021

J Intell Manuf

Self Cite

View full text Add to dashboard Cite

show abstract

“…Liang proposed an ontology-oriented knowledge methodology for the generation of a novel knowledge in the AM production design process based on a novel ontology (AM-OntoProc) and the informal model [31]. Ko et al presented an approach for automated and autonomous knowledge-driven AM design rule construction, that combines AM data, machine learning, and an ontology with knowledge graphs [32]. There are also some other approaches, which employ ontologies in the field of AM [26], [33], but not yet in combination with software that automatically checks production guidelines.…”

Section: B Additive Manufacturing Ontologiesmentioning

confidence: 99%

Knowledge-Driven Manufacturability Analysis for Additive Manufacturing

Mayerhofer¹,

Lepuschitz²,

Hoebert³

et al. 2021

IEEE Open J. Ind. Electron. Soc.

View full text Add to dashboard Cite

Additive Manufacturing (AM) evolved recently from a rapid prototyping process to a standard manufacturing tool. Nevertheless, it is still not a widely used method due to different process-related challenges. In recent years printer technologies and possible printable materials emerged but there are still challenging demands on the printing process. Hence, it is of vital importance to inspect the manufacturability of the designed parts. This work focuses on the not yet widely researched ceramic printing with the Lithography-based Ceramic Manufacturing (LCM) processes. It presents a knowledge-driven framework able to automatically examine geometric properties of a part and compare it to AM guidelines. As a knowledge base, an ontology is used which contains information about the capabilities of AM processes, printers and materials. The manufacturability system uses triangle-based mesh processing algorithms to recognize features and check the guidelines necessary for LCM. The evaluation shows the feasibility of manufacturability analysis with the developed framework and its limitations. INDEX TERMSAdditive manufacturing, computer-aided design, manufacturability analysis, knowledge representation, ontology.

show abstract

“…More and more data can be found on the subject of incremental manufacturing, which allow to better understand the influence of the principles of this process on the quality of manufactured elements [12,13]. Thanks to the development of areas such as Rapid Manufacturing or Rapid Prototyping, the time of developing new products and their improvement has been shortened [14][15][16].…”

Section: Wpływ Skręcania Na Strukturę Elementów Maszyn Wytworzonych Z Materiałów Polimerowych Metodą Druku 3dmentioning

confidence: 99%

Influence of torsion on the structure of machine elements made of polymeric materials by 3D printing

Dębski¹,

Magniszewski²,

Bernaczek³

et al. 2021

View full text Add to dashboard Cite

In this work, on the example of a spline connection, the effect of 3D printing on the structure of machine elements made of polymeric materials after a torsion test was investigated. A clear influence of the type of polymer and the printing direction in the applied incremental technology [FFF (Fused Filament Fabrication) also known as FDM (Fused Deposition Modeling)] on the structure of the obtained elements was observed.

show abstract

Machine learning and knowledge graph based design rule construction for additive manufacturing

Cited by 83 publications

References 38 publications

Collaborative knowledge management to identify data analytics opportunities in additive manufacturing

Collaborative knowledge management to identify data analytics opportunities in additive manufacturing

Knowledge-Driven Manufacturability Analysis for Additive Manufacturing

Influence of torsion on the structure of machine elements made of polymeric materials by 3D printing

Contact Info

Product

Resources

About