wbk Institute of Production Science

Lukas Weiser, M.Sc.

  • 76131 Karlsruhe
    Kaiserstraße 12

Lukas Weiser, M.Sc.

Area of Research:

  • Quality assurance in additive manufacturing
  • Process-integrated measurement technology
  • Sensor development for LPBF process monitoring
  • Machine Learning / Artificial Intelligence
  • MES development
  • Leightweight construction: hybrid fibre composites


General Tasks:

  • Coordination of lecture Production & Operations Management (POM)
  • Coordinator Learning Factory Module 3 – Six Sigma
  • Core Team Learning Factory - Software


Curriculum Vitae:

since 11/2018 Research Associate at the Institute of Production Science (wbk) at Karlsruhe Institute of Technology (KIT)  
10/2012 - 10/2018 Study of mechanical engineering at Karlsruhe Institute of Technology (KIT)  
14/07/1993 Born in Bühl  



[ 1 ] Eschner, N.; Weiser, L.; Häfner, B. & Lanza, G. (2018), "Development of an Acoustic Process Monitoring System for the Selective Laser Melting (SLM)". Solid Freeform Symposium - Proceedings, eds. SFF Symposium, pp. 2097-2117.
The current selective laser melting (SLM) process lacks both process quality and reproducibility. Recent research focuses on the integration of optical measuring technology, but acoustic sensors also seem promising. Initial results on acoustic methods show their suitability. The further processing of the data still shows difficulties, mostly due to the high sample rate. In this work a concept for an acoustic process monitoring system is developed and integrated into the process. First results show its capability to distinguish different process qualities. For this purpose, various configurations for in-process integration of acoustic measurement techniques are discussed and evaluated. The most promising structure-borne sound concept is integrated and tested in a test bed. In a Design of Experiments for specific parameter selection, cubes with different process qualities are produced, and the acoustic signatures are evaluated. For a first prove of concepts a Neuronal Network is trained to classify three different laser classes. Therefore, different NN topologies were tested and the best-found solution had a precision of more than 90%.

[ 2 ] Eschner, N.; Weiser, L.; Häfner, B. & Lanza, G. (2019), "Akustische Prozessüberwachung für das Laserstrahlschmelzen (LBM) mit neuronalen Netzen: Eine Potentialbewertung", tm - Technisches Messen, no. 11, pp. 661-672. 10.1515/teme-2019-0070
Das selektive Laserstrahlschmelzen (LBM) steht aktuell an der Schwelle zum Einsatz für Kleinserien. Ein wesentlicher Nachteil des Verfahrens ist aktuell noch die geringe Reproduzierbarkeit der Prozessqualität. Einige aktuelle Forschungsarbeiten konzentrieren sich deshalb auf die Integration optischer Messtechnik zur Prozessüberwachung. Neben den optischen Verfahren zeigen erste Untersuchungen, dass auch akustische Sensoren zur Prozessüberwachung ein vielversprechender Ansatz sind. Eine große Herausforderung bei den akustischen Daten stellt die Datenverarbeitung dar, da das akustische Rohsignal nur schwer zu interpretieren ist. In dieser Arbeit wird ein neues Konzept für ein akustisches Prozessüberwachungssystem vorgestellt und in eine Versuchsumgebung integriert. Zum Aufzeichnen akustischer Signale werden in einem Design of Experiments Prozessparameter gezielt variiert und Testkörper verschiedener Bauteilqualität aufgebaut. Für einen ersten Nachweis der Eignung des Messsystems zur Überwachung des Prozesses wird ein künstliches neuronales Netz trainiert, um die verwendeten Prozessparameter (drei Laserleistungen) zu bewerten. Damit kann gezeigt werden, dass diese Messtechnik das Potential hat, den Prozess zu überwachen.

[ 3 ] Eschner, N.; Weiser, L. & Lanza, G. (2020), "Classification of specimen density in Laser Powder Bed Fusion (L-PBF) using in-process structure-borne acoustic process emissions", Additive Manufacturing, vol. 34, 10.1016/j.addma.2020.101324 [30.11.-1].
Currently, the laser powder bed fusion (L-PBF) process cannot offer a reproducible and predefined quality of the processed parts. Recent research on process monitoring focuses strongly on integrated optical measurement technology. Besides optical sensors, acoustic sensors also seem promising. Previous studies have shown the potential of analyzing structure-borne and air-borne acoustic emissions in laser welding. Only a few works evaluate the potential that lies in the usage during the L-PBF process. This work shows how the approach to structure-borne acoustic process monitoring can be elaborated by correlating acoustic signals to statistical values indicating part quality. Density measurements according to Archimedes? principle are used to label the layer-based acoustic data and to measure the quality. The data set is then treated as a classification problem while investigating the applicability of existing artificial neural network algorithms to match acoustic data with density measurements. Furthermore, this work investigates the transferability of the approach to more complex specimens.