Lam Research Corporation

Kapil Umesh Sawlani

Michal Danek

Joshua Collins

Hanna Bamnolker

Atashi Basu

David M Fried

Siew Neo

Anand Chandrashekar

Richard Alan Gottscho

Kaihan Abidi Ashtiani

Ronald Allan Powell

Gary B Lind

Keith J Hansen

Keith B Wells

Dongyao Li

Michael Rumer

Michael Bowes

Emily Ann Alden

Methods, systems, and computer programs are presented for determining the recipe for manufacturing a semiconductor with the use of machine learning (ML) to accelerate the definition of recipes. One general aspect includes a method that includes an operation for performing experiments for processing a component, each experiment controlled by a recipe, from a set of recipes, that identifies parameters for manufacturing equipment. The method further includes an operation for performing virtual simulations for processing the component, each simulation controlled by one recipe from the set of recipes. An ML model is obtained by training an ML algorithm using experiment results and virtual results from the virtual simulations. The method further includes operations for receiving specifications for a desired processing of the component, and creating, by the ML model, a new recipe for processing the component based on the specifications.

Determination of recipes for manufacturing semiconductor devices

Defects on a substrate comprising electronic components can be classified with a computational defect analysis system that may be implemented in multiple stages. For example, a first stage classification engine may process metrology data to produce an initial classification of defects. A second stage classification engine may use the initial classification, along with manufacturing information and/or prior defect knowledge to output probabilities that the defects are caused by one or more potential sources.

Defect classification and source analysis for semiconductor equipment

A method for depositing tungsten includes arranging a substrate including a titanium nitride layer in a substrate processing chamber and performing multi-stage atomic layer deposition of tungsten on the substrate using a precursor gas includes tungsten chloride (WCIx) gas, wherein x is an integer. The performing includes depositing the tungsten during a first ALD stage using a first dose intensity of the precursor gas, and depositing the tungsten during a second ALD stage using a second dose intensity of the precursor gas. The first dose intensity is based on a first dose concentration and a first dose period. The second dose intensity is based on a second dose concentration and a second dose period. The second dose intensity is 1.5 to 10 times the first dose intensity.

Atomic layer deposition of tungsten for enhanced fill and reduced substrate attack

Provided herein are systems and methods for optimizing feature fill processes. The feature fill optimization systems and methods may be used to optimize feature fill from a small number of patterned wafer tests. The systems and methods may be used for optimizing enhanced feature fill processes including those that include inhibition and/or etch operations along with deposition operations. Results from experiments may be used to calibrate a feature scale behavioral model. Once calibrated, parameter space may be iteratively explored to optimize the process.

Fill process optimization using feature scale modeling

A system includes a camera mounted external to and adjacent to a window of a processing chamber configured to process semiconductor substrates. The window allows the camera to view a component in the processing chamber. The camera is configured to generate a video signal indicative of a status of the component during a process being performed in the processing chamber. The system further includes a controller coupled to the processing chamber. The controller is configured to control the camera, process the video signal from the camera, determine the status of the component based on the processing of the video signal, and determine whether to terminate the process based on the status of the component.

In-situ chamber clean end point detection systems and methods using computer vision systems

A method for depositing tungsten includes arranging a substrate including a titanium nitride layer in a substrate processing chamber and performing multi-stage atomic layer deposition of tungsten on the substrate using a precursor gas includes tungsten chloride (WClx) gas, wherein x is an integer. The performing includes depositing the tungsten during a first ALD stage using a first dose intensity of the precursor gas, and depositing the tungsten during a second ALD stage using a second dose intensity of the precursor gas. The first dose intensity is based on a first dose concentration and a first dose period. The second dose intensity is based on a second dose concentration and a second dose period. The second dose intensity is 1.5 to 10 times the first dose intensity.

Growing community of inventors

Sunnyvale, CA, United States of America

Kapil Umesh Sawlani