Feature Selection Based on Visual Analytics for Quality Prediction in Aluminium Die Casting

摘要: Digital transformation is regarded as a key enabler for quality management in the modern casting industry. By uncovering parameters that affect part quality, continuous process improvement could be enabled. In particular, focus laid on explicability of identified dependencies due to acceptance data-driven decisions by workers well initiate tailored measures. For this purpose, paper two visual analytics approaches are discussed quality-affecting with claim high degree – one hand method-feature-heatmap visualizes multiple backward feature elimination and other graph-based visualization class association rules. An automotive industry use case demonstrates context gravity die aluminium knuckles.