18070448. DETERMINING EQUIPMENT CONSTANT UPDATES BY MACHINE LEARNING simplified abstract (Applied Materials, Inc.)

DETERMINING EQUIPMENT CONSTANT UPDATES BY MACHINE LEARNING

Organization Name

Applied Materials, Inc.

Inventor(s)

Sidharth Bhatia of Santa Cruz CA (US)

Roger Lindley of Santa Clara CA (US)

Upendra Ummethala of Cupertino CA (US)

Thomas Li of Santa Clara CA (US)

Michael Howells of San Jose CA (US)

Steven Babayan of Los Altos CA (US)

Mimi-Diemmy Dao of Santa Clara CA (US)

DETERMINING EQUIPMENT CONSTANT UPDATES BY MACHINE LEARNING - A simplified explanation of the abstract

This abstract first appeared for US patent application 18070448 titled 'DETERMINING EQUIPMENT CONSTANT UPDATES BY MACHINE LEARNING

Simplified Explanation

The abstract of the patent application describes a method that involves using trace data and equipment constants as input to a machine learning model to recommend updates to equipment constants of a processing chamber.

• The method utilizes trace data and equipment constants associated with substrate processing procedures.
• The input also includes trace data and equipment constants specific to a processing chamber.
• The trained machine learning model provides recommendations for updating equipment constants.
• The method involves updating equipment constants based on the recommendations from the machine learning model.

Potential Applications

This technology could be applied in semiconductor manufacturing processes to optimize equipment settings and improve overall efficiency.

Problems Solved

This technology helps in identifying and implementing optimal equipment settings for substrate processing procedures, leading to enhanced productivity and quality in manufacturing processes.

Benefits

The use of machine learning models to recommend equipment constant updates can result in improved process control, reduced downtime, and increased yield in manufacturing operations.

Potential Commercial Applications

One potential commercial application of this technology could be in the semiconductor industry for optimizing equipment settings in processing chambers.

Possible Prior Art

Prior art in the field of semiconductor manufacturing may include traditional methods of equipment calibration and optimization, which may not be as efficient or accurate as the machine learning-based approach described in this patent application.

How does this technology compare to traditional methods of equipment optimization in terms of accuracy and efficiency?

This article does not provide a direct comparison between the machine learning-based approach and traditional methods of equipment optimization. It would be beneficial to understand the specific advantages and limitations of each method in different manufacturing scenarios.

What are the potential challenges in implementing this technology in a real-world manufacturing environment?

The article does not address the potential challenges that may arise when implementing this technology in actual manufacturing settings. It would be important to consider factors such as data integration, model accuracy, and scalability when deploying this solution in industrial applications.

Original Abstract Submitted

A method includes providing, as input to a first trained machine learning model, trace data associated with one or more substrate processing procedures. The input further includes equipment constants associated with the one or more substrate processing procedures. The input further includes trace data of a first processing chamber. The input further includes equipment constants of the first processing chamber. The method further includes obtaining, as output from the first trained machine learning model, a recommended update to a first equipment constant of the first processing chamber. The method further includes updated the first equipment constant of the first processing chamber responsive to obtaining the output from the first trained machine learning model.