NORMA eResearch @NCI Library

Data Mining for Enhancing Silicon Wafer Fabrication

Doke, Omkar (2020) Data Mining for Enhancing Silicon Wafer Fabrication. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (2MB) | Preview


Gordon E. Moore found that density of transistors doubled every two years on a microchip. However, now it is doubling in every 18 months1 thereby making semiconductor manufacturing one of the most complicated technological process. With increasing density, the transistor dimension is reducing thereby demanding rigorous physical and electrical testing to ensure high die yield quality which majorly depends on smooth functioning of equipment’s. In the past, various research projects were undertaken on wafer image data in semiconductor manufacturing field to improve the quality and productivity by reducing the impact of contaminants. This research aims at using machine learning techniques on numerical data obtained from sensors in equipment’s to predict wafer failure in manufacturing process thereby reducing equipment failure by providing timely maintenance (i.e. predictive maintenance) which in turn would enhance productivity and improve die yield quality. To achieve this, models like XGBoost, Decision Tree, Logistic Regression, Support Vector Machine, Random Forest, K-Nearest Neighbor and Neural Network are used for classification. Various case studies were conducted wherein these models were evaluated for their performance based on their accuracy and precision. Random Forest outperformed all other models with both accuracy and precision over 98% thereby confirming that machine learning techniques can be used to implement predictive maintenance in production line with an aim to improve the productivity by making optimum use of equipment’s. Keywords: Semiconductor Manufacturing, Die Yield Quality, Contaminants, Predictive Maintenance

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 20 Jan 2021 13:47
Last Modified: 20 Jan 2021 13:47

Actions (login required)

View Item View Item