Time Series Clustering for Knowledge Discovery on Metal Additive Manufacturing

• Marta Aramburu-Zabala ^[1] ; Simona Masurtschak ^[1] ; Ramón Moreno ^[1] ; Jeremy Jean-Jean ^[2] ; Angela Veiga ^[1]
  1. [1] Basque Research and Technology Alliance

     Basque Research and Technology Alliance

     Mendaro, España

     
  2. [2] RISE IVF, Material and Production Division, Argongatan 30 (431 53 Mölndal, Sweden)
• Localización: Intelligent Data Engineering and Automated Learning – IDEAL 2020. 21st International Conference: Guimarães, Portugal; November 4–6, 2020. Proceedings / Cesar Analide (ed. lit.), Paulo Novais (ed. lit.), David Camacho Fernández (ed. lit.), Hujun Yin (ed. lit.), Vol. 2, 2020 (Part II), ISBN 978-3-030-62365-4, págs. 447-455
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • 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.