Clustering

Existing selective laser melting (SLM) machine tools are not equipped with analytics tools. This paper describes an approach to analyze offline data, based on machine learning algorithms, to identify clusters. Normal states and error cases can be identified. The results can be used to develop condition monitoring systems that provide predictive maintenance for SLM machine tools.

In the BMBF-funded project “Provenance Analytics” research groups at the Bauhaus-Universität Weimar and the Hochschule Ostwestfalen-Lippe develop approaches for detecting anomalies in sensor data. In this short survey, we review the main methods for predicting failures in the production processes of manufacturing machines and give a brief overview of the activities planned in the project.