Machine and deep learning method for spectrum-based metrology and process control

• Main Authors: TAL, NOAM, YOGOV SHAY, STREICH, BOAZ, BRANOWICZ, BAREK, COHEN, ODED, YAACOBI RAHN
• Format: Patent
• Language: Chinese; English
• Published: 02.12.2022
• Subjects: BASIC ELECTRIC ELEMENTS; ELECTRIC SOLID STATE DEVICES NOT OTHERWISE PROVIDED FOR; ELECTRICITY; INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIRCHEMICAL OR PHYSICAL PROPERTIES; MEASURING; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS; MEASURING LENGTH, THICKNESS OR SIMILAR LINEARDIMENSIONS; PHYSICS; SEMICONDUCTOR DEVICES; TESTING

Systems and methods for advanced process control (APC) in semiconductor manufacturing include, for each wafer station of a plurality of wafer stations, receiving a pre-processing set of scatterometry training data measured prior to performing a processing step, receiving a respective post-processing set of scatterometry training data measured after performing the processing step, and transmitting the received pre-processing set to the plurality of wafer stations. And receiving a set of process control knob training data indicative of process control knob settings applied during implementation of the processing step; and generating a machine learning model that associates the pre-processed set of scatterometry training data with the changes in the corresponding process control knob training data and the corresponding post-processed set of scatterometry training data to train the machine learning model to recommend changes to the process control knob settings, changes in the pre-processed scatterometry data are