Semiconductor Wafer

Semiconductor wafer manufacturing relies on precise control and defect detection to maximize yield. Current research focuses on applying advanced machine learning techniques, such as generative adversarial networks (GANs) for data augmentation and various deep learning architectures (including convolutional neural networks and transformers) for defect pattern recognition and prediction of electrical performance from metrology data. These methods aim to improve automated visual inspection, enabling faster and more accurate identification of defects, ultimately optimizing production efficiency and enhancing the quality of integrated circuits. The development of efficient, low-memory models is crucial for deployment in real-time fabrication environments.

Papers

July 24, 2024

Utilizing Generative Adversarial Networks for Image Data Augmentation and Classification of Semiconductor Wafer Dicing Induced Defects
Zhining Hu, Tobias Schlosser, Michael Friedrich, André Luiz Vieira e Silva, Frederik Beuth, Danny Kowerko
Generative Adversarial Network Classification Code GAN Algorithm Defect Pattern Image Data Augmentation Semiconductor Wafer

November 20, 2023

Applying Machine Learning Models on Metrology Data for Predicting Device Electrical Performance
Bappaditya Dey, Anh Tuan Ngo, Sara Sacchi, Victor Blanco, Philippe Leray, Sandip Halder
Machine Learning Model Smart Device Semiconductor Manufacturing Capacitive Sensing Extreme Ultraviolet Lithography Model Metrology Semiconductor Wafer

March 24, 2023

August 30, 2022

Deep Open-Set Recognition for Silicon Wafer Production Monitoring
Luca Frittoli, Diego Carrera, Beatrice Rossi, Pasqualina Fragneto, Giacomo Boracchi
Outlier Detection Open Set Recognition Wafer Defect Semiconductor Wafer Silicon Wafer Production Monitoring

November 5, 2021

Defect Detection on Semiconductor Wafers by Distribution Analysis
Thomas Olschewski
Defect Detection Classification Algorithm Detection Performance Distributional Assumption Object Classification Semiconductor Wafer Silicon Wafer Production Monitoring

Semiconductor Wafer

Papers

Utilizing Generative Adversarial Networks for Image Data Augmentation and Classification of Semiconductor Wafer Dicing Induced Defects

Applying Machine Learning Models on Metrology Data for Predicting Device Electrical Performance

Mixed-Type Wafer Classification For Low Memory Devices Using Knowledge Distillation

Efficient Mixed-Type Wafer Defect Pattern Recognition Using Compact Deformable Convolutional Transformers

Deep Open-Set Recognition for Silicon Wafer Production Monitoring

Defect Detection on Semiconductor Wafers by Distribution Analysis