Time Series Clustering for Knowledge Discovery on Metal Additive ManufacturingShow others and affiliations
2020 (English)In: 21th International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2020, Springer Science and Business Media Deutschland GmbH , 2020, p. 447-455Conference paper, Published paper (Refereed)
Abstract [en]
This work meets Metal Additive Manufacturing and Time Series Processing. It presents a four-step analytical procedure addressed to support the discovery of defect causes in 3D metal printing. The method has a phase of data space transformation, where the features space is firstly reduced and secondly exploited in a higher dimensional space. Later, a procedure for knowledge discovery is applied. Finally, by analyzing the results, it is concluded the most probable causes of the high rate of defects in the production phase. This procedure is proved with data obtained from a SLM machine, and the results are convincing.
Place, publisher, year, edition, pages
Springer Science and Business Media Deutschland GmbH , 2020. p. 447-455
Keywords [en]
Clustering, Fault detection, Metal Additive Manufacturing, Single layer melting, Time series, Additives, Defects, Metadata, Analytical procedure, Data space, High rate, Higher-dimensional, Metal additives, Production phase, Time series clustering, Time series processing, 3D printers
National Category
Natural Sciences
Identifiers
URN: urn:nbn:se:ri:diva-51209DOI: 10.1007/978-3-030-62365-4_42Scopus ID: 2-s2.0-85097125886ISBN: 9783030623647 (print)OAI: oai:DiVA.org:ri-51209DiVA, id: diva2:1516040
Conference
IDEAL 2020: Intelligent Data Engineering and Automated Learning – IDEAL 2020 pp 447-455. 4 November 2020 through 6 November 2020
Note
Funding details: European Institute of Innovation and Technology, EIT; Funding details: EIT Manufacturing; Funding details: European Commission***Delivered and deleted from Elsevier end because this record is to be no longer updated or in business with Elsevier on Date 10-03-2020***, EC, 20122; Funding text 1: Acknowledgments. Data collection and curation have been accomplished within the DIGI-QUAM Project, which has received funding from the EIT Manufacturing, and is supported by the EIT, a body of the European Union under grant agreement nº 20122. Time Series Analysis part has been founded by the project KK-2019/00095 (Departamento de Desarrollo Economico e Infraestructuras del Govierno Vasco. Programa ELKARTEK 2019.
2021-01-112021-01-112021-06-17Bibliographically approved