Applied Materials, Inc.

Thomas Ho Fai Li

Christopher Heung-Gyun Lee

Zhaozhao Zhu

Erik S Rondum

Jie Diao

Bum Jick Kim

Jeong Jin Hong

Sejune Cheon

Sang Hong Kim

Mihyun Jang

Tianyu Yang

Anders Andelman Nottrott

A method includes receiving spectral data of a substrate and metrology data corresponding to the spectral data of the substrate. The method further includes determining a plurality of feature model configurations for each of a plurality of feature models, each of the plurality of feature model configurations including one or more feature model conditions. The method further includes determining a plurality of feature model combinations, where each feature model combination of the plurality of feature model combinations includes a subset of the plurality of feature model configurations. The method further includes generating a plurality of input datasets, where each input dataset of the plurality of input datasets is generated based on application of the spectral data to a respective feature model combination of the plurality of feature model combinations. The method further includes training a plurality of machine learning models, where each machine learning model is trained to generate an output using an input dataset of the plurality of input datasets and the metrology data. The method further includes selecting a trained machine learning model from the plurality of trained machine learning models satisfying one or more selection criteria.

Machine learning model training

An apparatus and method for to monitoring slurry buildup is disclosed. A substrate polishing apparatus includes a surface coated at least in part with a fluorescent material, a light source configured to illuminate the surface, an image sensor configured to image the surface, and a processor coupled to the image sensor and configured to monitor slurry buildup on the surface using data supplied from the image sensor.

Chemical mechanical polishing slurry buildup monitoring

Polishing pad cleaning systems and related methods are disclosed. A rotatable platen comprising a polishing pad in combination with a fluid, such as a polishing fluid, contacts a substrate to planarize material at the surface thereof and resultantly creates debris. A cleaning system introduces a spray system to remove debris from the polishing pad to prevent substrate damage and improve efficiency, a waste removal system for removing used spray, used polishing fluid, and debris from the polishing pad, and a polishing fluid delivery system for providing fresh polishing fluid to the polishing pad, such that the substrate only receives fresh polishing fluid upon each complete rotation of the platen. In this manner, within die performance is enhanced, the range of certain CMP processes is improved, scratches and contamination are avoided for each polished substrate and for later-polished substrates, and platen temperatures are reduced.

System and process for in situ byproduct removal and platen cooling during CMP

In one embodiment, a method for cleaning a surface of a polishing pad includes conditioning the polishing pad surface and rotating the conditioned polishing pad surface. The method also includes spraying the polishing pad surface to lift debris from the conditioned polishing pad surface. The method further includes vacuuming the debris from the polishing pad surface downstream from where the condition occurs, wherein downstream is defined by a rotational direction of the polishing pad. In another embodiment, a processing station including a rotatable platen, a substrate carrier head, a polishing fluid delivery system, a conditioner, a spray nozzle, and a vacuum system is provided. The conditioner is disposed between the substrate carrier head and the spray nozzle. The vacuum system is configured to vacuum the polishing pad surface. The vacuum system is downstream from the conditioner, defined by a rotation of the platen.

Polishing pad cleaning with vacuum apparatus

Growing community of inventors

San Jose, CA, United States of America

Thomas Ho Fai Li