View source for 18530692. METHOD AND APPARATUS WITH OPERATIONAL CONTROL DEPENDENT ON MULTIPLE PROCESSES simplified abstract (Samsung Electronics Co., Ltd.)

=METHOD AND APPARATUS WITH OPERATIONAL CONTROL DEPENDENT ON MULTIPLE PROCESSES=


==Organization Name==

[[:Category:Samsung Electronics Co., Ltd.|Samsung Electronics Co., Ltd.]]


[[Category:Samsung Electronics Co., Ltd.]]

==Inventor(s)==

[[:Category:Dong Jin Ji of Suwon-si (KR)|Dong Jin Ji of Suwon-si (KR)]][[Category:Dong Jin Ji of Suwon-si (KR)]]

[[:Category:Kaeweon You of Suwon-si (KR)|Kaeweon You of Suwon-si (KR)]][[Category:Kaeweon You of Suwon-si (KR)]]

[[:Category:Jiung Lee of Suwon-si (KR)|Jiung Lee of Suwon-si (KR)]][[Category:Jiung Lee of Suwon-si (KR)]]

[[:Category:Seok Hyun Hong of Suwon-si (KR)|Seok Hyun Hong of Suwon-si (KR)]][[Category:Seok Hyun Hong of Suwon-si (KR)]]

==METHOD AND APPARATUS WITH OPERATIONAL CONTROL DEPENDENT ON MULTIPLE PROCESSES - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18530692 titled 'METHOD AND APPARATUS WITH OPERATIONAL CONTROL DEPENDENT ON MULTIPLE PROCESSES

The patent application describes a method for optimizing semiconductor fabrication processes using neural networks.

* The method involves generating sequence data based on measured values of process factors for each process of a semiconductor fabrication process.
* A temporary quality index of the wafer is generated using a second neural network connected to a first neural network that receives the sequence data.
* The first and second neural networks are trained based on the difference between the temporary quality index and the actual quality index of the wafer.
* A control process is selected from the processes using the trained neural networks, and a control factor is selected using the trained second neural network.

Potential Applications:
- This technology can be applied in semiconductor manufacturing to improve the quality and efficiency of wafer production.
- It can also be used in other industries that require precise control and optimization of processes.

Problems Solved:
- The method addresses the challenge of optimizing multiple processes in semiconductor fabrication to achieve desired quality standards.
- It helps in automating the selection of control processes and factors, reducing human error and improving overall efficiency.

Benefits:
- Enhanced quality control in semiconductor fabrication processes.
- Increased productivity and cost savings through optimized process control.
- Improved accuracy and consistency in wafer production.

Commercial Applications:
Title: "Neural Network Optimization for Semiconductor Fabrication Processes"
This technology can be utilized by semiconductor manufacturers to streamline production processes, reduce defects, and enhance overall product quality. It can also be licensed to companies in other industries that require precision manufacturing processes.

Questions about Neural Network Optimization for Semiconductor Fabrication Processes:
1. How does this method improve the efficiency of semiconductor fabrication processes?
- The method optimizes process control by using neural networks to analyze data and make decisions, leading to improved quality and productivity.
2. What are the potential cost savings associated with implementing this technology?
- By automating process control and optimizing factors, companies can reduce waste, rework, and production costs, resulting in significant savings over time.


==Original Abstract Submitted==

A method including generating sequence data based on measured values of respective one or more process factors of each of a plurality of processes of a semiconductor fabrication process for a wafer within the semiconductor fabrication process, generating a temporary quality index of the wafer using a second neural network connected to a first neural network that is provided the sequence data, training the first neural network and the second neural network based on a loss between the temporary quality index and a set actual quality index of the wafer, selecting a control process from among the plurality of processes using at least one of the trained first neural network and/or the trained second neural network, and selecting a control factor from among multiple process factors of the selected process using the trained second neural network.



[[Category:G05B19/418]]
[[Category:CPC_G05B19/41865]]