Data-driven model for process evaluation in wire EDM

To digitalize the wire EDM process, data-driven models are necessary for evaluating its performance. This presents a challenge due to the high volume of data and the stochastic nature of the process. In this paper, electrical parameters are measured and processed by an FPGA (field programmable gate array) system to recognize and characterize temporally and spatially resolved single discharges as either normal or abnormal. Supervised machine learning methods such as artificial neural networks (ANN) are used and models are trained with different data sets to predict the machined geometrical accuracy and cutting speed based on recorded process data.