LAUSR

Abstract Due to increased digitalization in the production environment, data, information, and sustainable management approaches should be developed in order to enable production machines for data acquisition, data exchange and data analysis. Especially for additive manufacturing technologies, those approaches are extremely important to detect and avoid failures in the manufacturing process. A critical failure during the manufacturing process could lead to a defective workpiece, wasting resources. Within this context, this work addresses the concept of sustainable data for a selective laser melting machine tool. The selective laser melting process is one of the additive manufacturing technologies that is capable of producing lighter and more complex functional workpieces in comparison to conventional manufacturing technologies. Beyond the use of the machine tool system internal data (e.g. process data, internal sensors), additional information such as energy consumption and data provided using external sensors are required to detect the current condition of production process. In order to observe if the considered data sources are capable of identifying abnormal conditions of the machine tool, failures from five subsystems were inserted during a manufacturing process of a reference workpiece. Four of the five data sources detect failures that influenced the layer quality while they are occurring. Thus, the results could be used to allow the operator to take measures to save energy and resources.