20240046096. PREDICTIVE MODELING OF A MANUFACTURING PROCESS USING A SET OF TRAINED INVERTED MODELS simplified abstract (Applied Materials, Inc.)
PREDICTIVE MODELING OF A MANUFACTURING PROCESS USING A SET OF TRAINED INVERTED MODELS
Organization Name
Inventor(s)
Sidharth Bhatia of Santa Cruz CA (US)
Dermot Cantwell of Sunnyvale CA (US)
Serghei Malkov of Hayward CA (US)
PREDICTIVE MODELING OF A MANUFACTURING PROCESS USING A SET OF TRAINED INVERTED MODELS - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240046096 titled 'PREDICTIVE MODELING OF A MANUFACTURING PROCESS USING A SET OF TRAINED INVERTED MODELS
Simplified Explanation
The disclosed technology involves performing predictive modeling to identify inputs for a manufacturing process, specifically for semiconductor devices. The method includes receiving expected output data that defines an attribute of a semiconductor device manufactured by a semiconductor device manufacturing process. This expected output data corresponds to an unexplored portion of a process space associated with the manufacturing process. The technology then identifies expected input data by using the expected output data as input to a plurality of homogeneous inverted machine learning models. Each inverted machine learning model is trained to determine a respective set of input data for configuring the semiconductor device manufacturing process based on linear extrapolation using the expected output data.
- The technology performs predictive modeling to identify inputs for a semiconductor device manufacturing process.
- Expected output data, which defines an attribute of a semiconductor device, is received.
- The expected output data corresponds to an unexplored portion of the process space.
- Expected input data is identified using inverted machine learning models.
- Each inverted machine learning model is trained to determine a set of input data for configuring the manufacturing process based on linear extrapolation using the expected output data.
Potential applications of this technology:
- Optimization of semiconductor device manufacturing processes.
- Identification of optimal input parameters for semiconductor device manufacturing.
- Improving the efficiency and quality of semiconductor device production.
Problems solved by this technology:
- Difficulty in identifying the optimal inputs for semiconductor device manufacturing processes.
- Lack of efficient methods for exploring unexplored portions of the process space.
- Inability to accurately determine the input parameters based on expected output data.
Benefits of this technology:
- Increased efficiency in semiconductor device manufacturing.
- Improved quality control in the production of semiconductor devices.
- Reduction in manufacturing errors and defects.
- Cost savings through optimized manufacturing processes.
Original Abstract Submitted
disclosed herein is technology for performing predictive modeling to identify inputs for a manufacturing process. an example method may include receiving expected output data defining an attribute of a semiconductor device manufactured by at least one semiconductor device manufacturing process performed within at least one processing chamber, wherein the expected output data corresponds to an unexplored portion of a process space associated with the at least one semiconductor device manufacturing process, and identifying expected input data by using the expected output data as input to a plurality of homogeneous inverted machine learning models, wherein each inverted machine learning model of the plurality of homogeneous inverted machine learning models is trained to determine, by performing linear extrapolation based on the expected output data, a respective set of input data of a plurality of sets of input data for configuring the semiconductor device manufacturing process to manufacture the semiconductor device.
