Quality in Color: Using Knowledge Graphs for Enhanced Quality Control in an Automotive Paintshop

Abstract

Sensors and their derived data have reshaped manufacturing by enabling real-time monitoring, improved quality control and enhanced safety, particularly in automotive processes. Despite these benefits, challenges arise within the realm of data discovery when they have to align all this data, originating from different systems and built by different manufacturers using different technologies. This paper shows our solution to resolve these challenges within the Volvo Cars paintshop. By organizing sensor metadata, link them with the originating devices and the place where the data will be stored in a knowledge graph, our approach facilitates seamless data integration for multiple paintshop applications. We show how the resulting knowledge graph helps with dashboard techniques, machine learning, and semantic reasoning to provide insights for the paintshop operators. The obtained findings clearly show the potential of knowledge graphs in production lines, paving the way for future advancements in automotive manufacturing.