Prediction of the Wafer quality with respect to the production equipments data★

This paper deals with the prediction of wafers quality, according to the health indicators of manufacturing equipments in the semiconductor industry. The proposed approach is based on the pattern recognition principle by using a historical data of health indicators, associated to the reconstructed data of quality measurements of wafers. The aim is to construct clusters that represent the normal and the known faulty operations. Then, the Remaining Useful Life in terms of number of Wafers (RUW) is estimated by monitoring the trajectory and velocity of the degradation phenomenon.