Abstract
To minimize wafer yield losses by misprocessing during semiconductor manufacturing, faster and more accurate fault detection during the plasma process are desired to increase production yields. Process faults can be caused by abnormal equipment conditions, and the performance drifts of the parts or components of complicated semiconductor fabrication equipment are some of the most unnoticed factors that eventually change the plasma conditions. In this work, we propose improved stability and accuracy of process fault detection using optical emission spectroscopy (OES) data. Under a controlled experimental setup of arbitrarily induced fault scenarios, the extended isolation forest (EIF) approach was used to detect anomalies in OES data compared with the conventional isolation forest method in terms of accuracy and speed. We also used the OES data to generate features related to electron temperature and found that using the electron temperature features together with equipment status variable identification data (SVID) and OES data improved the prediction accuracy of process/equipment fault detection by a maximum of 0.84%.
Highlights
A new perspective is suggested for the density metric of semiconductor technology as semiconductor sizes are continuously shrinking [1]
The first is equipment status variable identification data (SVID) comprising more than a thousand parameters, including the operational set values and current values of various components related to radio frequency (RF) power, pressure, gas flow, and electrostatic chuck
We used our domain knowledge of the plasma etch equipment and selected a few tens of equipment parameters related to the mass flow controller (MFC) miscalibration scenarios; the distributions of the selected parameters were investigated to compare the sensitivity to changes in the gas flow rate of SF6 between the normal and abnormal processes
Summary
A new perspective is suggested for the density metric of semiconductor technology as semiconductor sizes are continuously shrinking [1]. This indicates that small changes in the semiconductor process parameters have considerable influence on the semiconductor production yields [2]. Even if high-dimensional data with multiple features are used, the algorithm performs well for abnormality diagnosis. To understand the IF anomaly diagnosis algorithm, we assumed that data were collected from two sensors for 25 s each at 1 s intervals. To diagnose the abnormality of the given data, the IF anomaly diagnosis algorithm employs a similar principle
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
