Advanced die sinking EDM process monitoring based on anomaly detection for online identification of improper process conditions

Abstract Die sinking EDM processes are widely employed in advanced aerospace applications where part quality and machining time are main concerns. The aim of this research work is to develop an advanced EDM process monitoring procedure in the perspective of Zero Defect Manufacturing based on the identification of correlations between die sinking EDM process parameters and improper process conditions that could increase machining time and cause unacceptable part quality. To this purpose, the Real Time Acquisition (RTAQ) module installed on a AgieCharmilles FORM P 600 sinker spark erosion machine tool is utilized to monitor and acquire online data related to 8 selected process parameters with 32 ms sampling interval. An anomaly detection methodology is then applied to timely identify improper process conditions based on relevant features extracted from the EDM process parameters.