The demonstrator uses machine learning to predict product parameters of inertial sensors, which are determined by the 3-dimensional shape and dimensions of the MEMS device. Data is collected from several process sources, including product measurements in various process steps and processing machine conditions. This data is linked with the measured electromechanical characteristics in wafer probing after completing processing. This data is used to build a machine learning model capable of predicting a semi-processed wafer's critical parameter. If prediction indicates that the process is drifting, the process recipes are adjusted to prevent scrap material from being produced.
Beyond state-of-the-art developments and impacts
The use of neural networks demonstrated to control the MEMS processes effectively.