Applied Materials, Inc.

Amazon Technologies, Inc.

Yi Wang

Wolfgang R Aderhold

Abhilash J Mayur

Jiangtao Zhang

Embodiments disclosed herein include a method of setting a target profile. In an embodiment, the method comprises obtaining a first gain curve for one or more temperature sensor offsets, and obtaining a second gain curve for one or more zone multipliers. In an embodiment, the method further comprises combining the first gain curve and the second gain curve into a thermal model. In an embodiment, the method further comprises obtaining a reference data set, and using the thermal model to generate temperature sensor offsets and/or zone multipliers to apply to the reference data set in order to generate the target profile.

Auto fine-tuner for desired temperature profile

Embodiments disclosed herein include a method of processing a substrate. In an embodiment, the method comprises detecting one or more substrate parameters of a substrate in a processing chamber, and heating the substrate to a first temperature with an open loop tuning (OLT) heating process based on the one or more substrate parameters. In an embodiment, the method may further comprise placing the substrate on an edge ring, and heating the substrate to a second temperature with a low temperature closed loop controller. In an embodiment, the method further comprises heating the substrate to a third temperature with a high temperature closed loop controller.

RTP substrate temperature one for all control algorithm

Aspects of the present disclosure relation to systems, methods, and apparatus for correcting thermal processing of substrates. In one aspect, a corrective absorption factor curve having a plurality of corrective absorption factors is generated.

Systems, methods, and apparatus for correcting thermal processing of substrates

Techniques for creating an aggregated machine learning (ML) model from a plurality of candidate ML models are described. According to some embodiments, a machine learning service generates an aggregated machine learning model from a first machine learning model and a second machine learning model, selects the first machine learning model, the second machine learning model, or the aggregated machine learning model for usage, and performs an inference with the selected machine learning model. Additionally, a user may select the candidate models to be trained.

Growing community of inventors

Sunnyvale, CA, United States of America

Yi Wang