Abstract
Ion Mill Etching (IME) is an advanced process technology that uses ion-beam sources to remove materials by atomic sandblasting in order to reveal a specific pattern on the substrate. The high-precision capability requires stringent process monitoring and control of the flowcool system which is critical to prevent thermal deformation for temperature sensitive materials from the heat generated from the ion beam irradiation. This study focuses on a multi-sensor data analytics to monitoring the IME process condition — enabling diagnostics and prediction of three main failure mechanisms of the IME flowcool system. A generalizable framework of engineering-based data-driven failure diagnostics and prediction is developed using random forest-based classification and a Deep Long Short-Term Memory (LSTM)-based failure prediction. The proposed framework and methods are demonstrated and validated in an ion mill etching process using multi-sensor data collected from multiple run-to-failure cycles. Three different failure modes related to the flowcool system are detected, identified in real time and the time to the next failure is accurately predicted. The proposed method provides a systematic and generalizable approach for process monitoring and early prediction of failures by using heterogeneous sensor measurements and operational data when under various operating conditions and settings.
