Version 1
: Received: 2 October 2023 / Approved: 2 October 2023 / Online: 2 October 2023 (09:13:34 CEST)
Version 2
: Received: 7 October 2023 / Approved: 7 October 2023 / Online: 7 October 2023 (09:53:09 CEST)
How to cite:
Chowdhury, H. Semiconductor Manufacturing Process Improvement Using Data-Driven Methodologies. Preprints2023, 2023100056. https://doi.org/10.20944/preprints202310.0056.v2
Chowdhury, H. Semiconductor Manufacturing Process Improvement Using Data-Driven Methodologies. Preprints 2023, 2023100056. https://doi.org/10.20944/preprints202310.0056.v2
Chowdhury, H. Semiconductor Manufacturing Process Improvement Using Data-Driven Methodologies. Preprints2023, 2023100056. https://doi.org/10.20944/preprints202310.0056.v2
APA Style
Chowdhury, H. (2023). Semiconductor Manufacturing Process Improvement Using Data-Driven Methodologies. Preprints. https://doi.org/10.20944/preprints202310.0056.v2
Chicago/Turabian Style
Chowdhury, H. 2023 "Semiconductor Manufacturing Process Improvement Using Data-Driven Methodologies" Preprints. https://doi.org/10.20944/preprints202310.0056.v2
Abstract
The paper investigates into the intricacies of semiconductor manufacturing, a highly complex process entailing a wide array of subprocesses and diverse equipment. Semiconductors are miniaturized integrated circuits comprising numerous components. The semiconductor manufacturing process begins with the thin disc-shaped silicon wafers. On each wafer, up to thousands of identical chips can be prepared depending upon the diameter of the wafer to build up the circuits layer by layer in a wafer fab. The size of the semiconductors requires a high number of units to be produced, thus necessitating a large amount of data to control for improving the semiconductor manufacturing process. Therefore, the collection and analysis of the equipment data, process data, and machine history data throughout the manufacturing process are required to diagnose faults, monitor the process, and manage the manufacturing process effectively. This research is focused on improving the semiconductor manufacturing process through a rigorous analysis of collected manufacturing process data, employing statistical process control (SPC), data mining techniques, and data-driven decision models. The project's primary objective is to increase the manufacturing process stability and productivity by utilizing the latest data-driven technologies in the scientific community. A structured review was undertaken, exploring contemporary data-driven methodologies in semiconductor manufacturing process improvement, specifically pertaining to process capability, product yield rate, and process stability. This review accentuates a comprehensive evaluation of data-driven methodologies applicable to conventional semiconductor manufacturing facilities, aiming to drive substantial process improvements. It features a detailed demonstration facilitating the selection of optimal semiconductor manufacturing processes to enhance overall operational performance. This study of process improvement in the semiconductor manufacturing steps through the application of data-driven methodologies will be effective in delivering advanced, real-time, and proactive control decisions throughout the manufacturing facilities. This endeavor is expected to promptly provide critical insights for enterprise manufacturing decision-makers to reduce manufacturing cycle time, improve the product yield rate, and increase the overall efficiency of the manufacturing process.
Keywords
semiconductor manufacturing; statistical process control (SPC); data mining techniques; data-driven decision models; process improvement; product yield rate; process stability
Subject
Engineering, Industrial and Manufacturing Engineering
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Commenter: Hribhu Chowdhury
Commenter's Conflict of Interests: Author