Publication detail

Classification of materials for selective laser melting by laser-induced breakdown spectroscopy

VRÁBEL, J. POŘÍZKA, P. KLUS, J. PROCHAZKA, D. NOVOTNÝ, J. KOUTNÝ, D. PALOUŠEK, D. KAISER, J.

Original Title

Classification of materials for selective laser melting by laser-induced breakdown spectroscopy

English Title

Classification of materials for selective laser melting by laser-induced breakdown spectroscopy

Type

journal article in Web of Science

Language

en

Original Abstract

In the present work, we introduce a possibility to improve the rapid prototyping process of selective laser melting (SLM) using laser-induced breakdown spectroscopy (LIBS) which provides a material analysis. SLM uses many disparate materials for manufacturing of parts. The elemental composition of raw materials and constructed parts is obtained from a characteristic spectrum, which is a result of LIBS measurement. We compared a high-end LIBS instrumentation with a low-cost one; the latter could be easily implemented to a SLM device. The measured data were processed using multivariate data analysis algorithms. First, the principal component analysis was employed for a visualization and dimensionality reduction. Second, the reduced data set was classified using support vector machines. Moreover, we have suggested a procedure for an automatized classification of materials and parts during the SLM process without any supervision of a spectroscopy-specialist.

English abstract

In the present work, we introduce a possibility to improve the rapid prototyping process of selective laser melting (SLM) using laser-induced breakdown spectroscopy (LIBS) which provides a material analysis. SLM uses many disparate materials for manufacturing of parts. The elemental composition of raw materials and constructed parts is obtained from a characteristic spectrum, which is a result of LIBS measurement. We compared a high-end LIBS instrumentation with a low-cost one; the latter could be easily implemented to a SLM device. The measured data were processed using multivariate data analysis algorithms. First, the principal component analysis was employed for a visualization and dimensionality reduction. Second, the reduced data set was classified using support vector machines. Moreover, we have suggested a procedure for an automatized classification of materials and parts during the SLM process without any supervision of a spectroscopy-specialist.

Keywords

LIBS, SLM, Chemometrics, Classification, Multivariate-data analysis

Released

01.12.2019

Publisher

Springer International

Pages from

2897

Pages to

2905

Pages count

9

URL

BibTex


@article{BUT150346,
  author="Jakub {Vrábel} and Pavel {Pořízka} and Jakub {Klus} and David {Prochazka} and Jan {Novotný} and Daniel {Koutný} and David {Paloušek} and Jozef {Kaiser}",
  title="Classification of materials for selective laser melting by laser-induced breakdown spectroscopy",
  annote="In the present work, we introduce a possibility to improve the rapid prototyping process of selective laser melting (SLM) using laser-induced breakdown spectroscopy (LIBS) which provides a material analysis. SLM uses many disparate materials for manufacturing of parts. The elemental composition of raw materials and constructed parts is obtained from a characteristic spectrum, which is a result of LIBS measurement. We compared a high-end LIBS instrumentation with a low-cost one; the latter could be easily implemented to a SLM device. The measured data were processed using multivariate data analysis algorithms. First, the principal component analysis was employed for a visualization and dimensionality reduction. Second, the reduced data set was classified using support vector machines. Moreover, we have suggested a procedure for an automatized classification of materials and parts during the SLM process without any supervision of a spectroscopy-specialist.",
  address="Springer International",
  chapter="150346",
  doi="10.1007/s11696-018-0609-1",
  howpublished="online",
  institution="Springer International",
  number="10",
  volume="1",
  year="2019",
  month="december",
  pages="2897--2905",
  publisher="Springer International",
  type="journal article in Web of Science"
}