A Data-Based Tool Failure Prevention Approach in Progressive Die Stamping

The research on methods for monitoring sheet metal stamping is benefiting from the increased availability of enabling technologies such as sensors, data mining software, cloud computing, and artificial intelligence. The predictive maintenance policies of tools (punches and dies) can be targeted at monitoring progressive wear or at the detection of sudden failures or anomalies. Early detection of tool failure is the method preferred by the recent literature on data management in sheet metal stamping. However, the stamping of small parts poses challenges due to multiple tools and signals and limited visibility of die wear, requiring management of multiple sensors and data sources. This paper proposes a failure prevention approach for progressive die stamping using global and local force sensors with upper bounds for maximum values to indicate unhealthy conditions. The methodology was tested on millions of small washers made of carbon steel. The stamping process was implemented using a servo-press with a high rate. The press was equipped with eight in-process sensors, including strain gauges, thin foil force sensors, and acoustic sensors. The data of material properties, maintenance reports, statistical process control data, and in-process sensors were collected and stored in a data lake. By combining the in-process sensor acquisition with the corresponding log events and maintenance data in the same time span, it is possible to look for correlations among the variables and build an effective tool health prevention policy.