Data-analytics-based factory operation strategies for die-casting quality enhancement

This paper proposes data-analytics-based factory operation strategies for the quality enhancement of die casting. We first define four main problems casting that result in lower quality: [P1] gaps between input and output parameter values, [P2] occurrence preheat shots, [P3] lateness defect distinction, [P4] worker-experience-based tuning. To address these problems, we derived seven tasks should be conducted during operation: [T1] implementation exploratory data analysis (EDA) investigating trends correlations data, [T2] deduction optimal values production fair-quality products, [T3] upper control limits input–output gap management, [T4] development a shot diagnosis algorithm, [T5] prediction [T6] cause [T7] tuning algorithm. The details proposed with regard to preprocessing, analytics method used, are presented discussed. Finally, case study die-casting South Korea has adopted is introduced.