18075216. SEMICONDUCTOR FILM THICKNESS PREDICTION USING MACHINE-LEARNING simplified abstract (Applied Materials, Inc.)
Contents
- 1 SEMICONDUCTOR FILM THICKNESS PREDICTION USING MACHINE-LEARNING
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 SEMICONDUCTOR FILM THICKNESS PREDICTION USING MACHINE-LEARNING - A simplified explanation of the abstract
- 1.4 Potential Applications
- 1.5 Problems Solved
- 1.6 Benefits
- 1.7 Commercial Applications
- 1.8 Prior Art
- 1.9 Frequently Updated Research
- 1.10 Questions about Film Thickness Estimation
- 1.11 Original Abstract Submitted
SEMICONDUCTOR FILM THICKNESS PREDICTION USING MACHINE-LEARNING
Organization Name
Inventor(s)
Nojan Motamedi of Sunnyvale CA (US)
Dominic J. Benvegnu of La Honda CA (US)
Kiran L. Shrestha of San Jose CA (US)
SEMICONDUCTOR FILM THICKNESS PREDICTION USING MACHINE-LEARNING - A simplified explanation of the abstract
This abstract first appeared for US patent application 18075216 titled 'SEMICONDUCTOR FILM THICKNESS PREDICTION USING MACHINE-LEARNING
The abstract describes a patent application for using a machine-learning model to estimate film thickness from spectral images captured during semiconductor substrate processing. Simulated images are generated for various predefined thickness profiles to train the model.
- Simulated training data is generated by simulating a light source reflecting off the film on a semiconductor substrate and capturing the spectral data with a camera.
- The captured spectral data is converted into images for wafers with different film thickness profiles, which are then labeled for training the machine-learning model.
Potential Applications
This technology could be applied in semiconductor manufacturing processes to accurately estimate film thickness without the need for physical measurements.
Problems Solved
This innovation addresses the challenge of accurately determining film thickness during semiconductor processing, which is crucial for ensuring product quality and performance.
Benefits
The use of simulated training data allows for the rapid generation of a wide variety of thickness profiles, improving the accuracy and efficiency of film thickness estimation.
Commercial Applications
This technology has potential commercial applications in the semiconductor industry, where precise control of film thickness is essential for the performance and reliability of electronic devices.
Prior Art
Researchers interested in this technology may explore prior art related to machine-learning models for estimating film thickness in semiconductor processing.
Frequently Updated Research
Stay informed about the latest research developments in machine-learning applications for semiconductor manufacturing processes to enhance the accuracy and efficiency of film thickness estimation.
Questions about Film Thickness Estimation
How does this technology improve the accuracy of film thickness estimation in semiconductor processing?
The use of simulated training data allows for a wide range of thickness profiles to be generated, enhancing the model's ability to estimate film thickness accurately.
What are the potential limitations of using machine-learning models for film thickness estimation in semiconductor processing?
One potential limitation could be the need for continuous updates and improvements to the model to account for variations in processing conditions and materials.
Original Abstract Submitted
A machine-learning model may be used to estimate a film thickness from a spectral image captured from a semiconductor substrate during processing. Instead of using actual measurements from physical substrates to train the model, simulated images may be generated for a wide variety of predefined thickness profiles. Simulated training data may be rapidly generated by receiving a film thickness profile representing a film on a semiconductor substrate design. A light source may be simulated being reflected off of the film on the semiconductor substrate and being captured by a camera. The spectral data captured by the camera may be converted into one or more images for a wafer with the film thickness profile. The images may then be labeled with thicknesses from the film thickness profile for training a machine-learning model.
