Artificial Intelligence in Thin Film Manufacturing

This course, originally recorded on August 18, 2020, describes how machine learning and AI-based approaches to research, development, and production brings advantages to cleanroom processes.  AI-based identification of time-varying equipment performance, and the effects of the previous recipe used on the outcome of the current desired methods, are just some of the ways AI can be used to reduce the process variability.

Cornell University has applied AI approaches to optimize lithography and etching processes involved in the development of an RF wake-up NEMS (Nano ElectroMechnical system) switch that needs a well-controlled gap between a moving shuttle and a contact. This presentation highlights that, as well as a decision tree based AI model for predicting lithography outcomes.

The AI work used as the basis for the course has been applied to plasma etching and the combined prediction of lithography and thin-film etching, using CD-SEM imagery for feature extraction and modeling process variables. Additional approaches to train process-modeling CAD tools to result in better process development experience have been developed.

The course provides a useful basis upon which to formulate AI strategies for all thin film manufacturing sites.