TY - JOUR
T1 - Detection of interferences in an additive manufacturing process: an experimental study integrating methods of feature selection and machine learning
AU - Stanisavljevic, Darko
AU - Cemernek, David
AU - Gursch, Heimo
AU - Urak, Günter Christoph
AU - Lechner, Gernot Christian
PY - 2019/11/27
Y1 - 2019/11/27
N2 - Additive manufacturing becomes a more and more important technology for production, mainly driven by the ability to realise extremely complex structures using multiple materials but without assembly or excessive waste. Nevertheless, like any high-precision technology additive manufacturing responds to interferences during the manufacturing process. These interferences – like vibrations – might lead to deviations in product quality, becoming manifest for instance in a reduced lifetime of a product or application issues. This study targets the issue of detecting such interferences during a manufacturing process in an exemplary experimental setup. Collection of data using current sensor technology directly on a 3D-printer enables a quantitative detection of interferences. The evaluation provides insights into the effectiveness of the realised application-oriented setup, the effort required for equipping a manufacturing system with sensors, and the effort for acquisition and processing the data. These insights are of practical utility for organisations dealing with additive manufacturing: the chosen approach for detecting interferences shows promising results, reaching interference detection rates of up to 100% depending on the applied data processing configuration.
AB - Additive manufacturing becomes a more and more important technology for production, mainly driven by the ability to realise extremely complex structures using multiple materials but without assembly or excessive waste. Nevertheless, like any high-precision technology additive manufacturing responds to interferences during the manufacturing process. These interferences – like vibrations – might lead to deviations in product quality, becoming manifest for instance in a reduced lifetime of a product or application issues. This study targets the issue of detecting such interferences during a manufacturing process in an exemplary experimental setup. Collection of data using current sensor technology directly on a 3D-printer enables a quantitative detection of interferences. The evaluation provides insights into the effectiveness of the realised application-oriented setup, the effort required for equipping a manufacturing system with sensors, and the effort for acquisition and processing the data. These insights are of practical utility for organisations dealing with additive manufacturing: the chosen approach for detecting interferences shows promising results, reaching interference detection rates of up to 100% depending on the applied data processing configuration.
U2 - 10.1080/00207543.2019.1694719
DO - 10.1080/00207543.2019.1694719
M3 - Article
SN - 0020-7543
VL - 2019
JO - International Journal of Production Research
JF - International Journal of Production Research
IS - 57
ER -