Relating wear stages in sheet metal forming based on short- and long-term force signal variations

Abstract Monitoring systems in sheet metal forming cannot rely on direct measurements of the physical condition interest because space between die component and material is inaccessible. Therefore, order to gain further insight into or stamping process, sensors must be used detect auxiliary quantities such as acoustic emission force that relate interest. While it known changes data are related parameters process material, lubricant used, geometry, over large stroke series their relationship wear subject this paper. Previously, from different conditions (artificially introduced system not occurring an industry-like environment) were input for clustering classifying high low data. This paper contributes fill current research gap by isolating structural properties indicators growth quantify evolution during ongoing production scenarios. The selected methods represent either established analysis, dimensionality reduction local structure separation generic feature extraction. study conducted a set four experiments with each containing about 3000 strokes.