Search research articles

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Wafer Defect Image Generation Method Based on Improved Styleganv3 Network.

Micromachines·2025

Same journal

Correction: Kang et al. Fluid Flow to Electricity: Capturing Flow-Induced Vibrations with Micro-Electromechanical-System-Based Piezoelectric Energy Harvester. <i>Micromachines</i> 2024, <i>15</i>, 581.

Micromachines·2026

Same journal

Femtosecond Laser Texturing of Wood Coatings with Bio-Based Epoxy and Wax Additives for Enhanced Hydrophobicity.

Micromachines·2026

Same journal

Engineering of Optoelectronic Devices for Renewable Energy Applications.

Micromachines·2026

Same journal

Phase Transformation and Electrochemical Behavior of Hexagonal TiO<sub>2</sub> Nanotubes Under Different Annealing Temperatures and Heating Rates.

Micromachines·2026

Same journal

Process Optimization and Predictive Modeling of Femtosecond Laser Precision Milling for Commercial PMMA Slices.

Micromachines·2026

Same journal

A Hybrid Preprocessing Multi-Objective Surrogate Model for Thermal MEMS Actuators.

Micromachines·2026

See all related articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 18, 2025

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Efficient Mixed-Type Wafer Defect Pattern Recognition Based on Light-Weight Neural Network.

Guangyuan Deng^1,2, Hongcheng Wang¹

¹School of Electrical Engineering and Intelligentization, Dongguan University of Technology, Dongguan 523808, China.

|July 27, 2024

Summary

This summary is machine-generated.

This study introduces a lightweight neural network for efficient mixed-type wafer defect recognition in semiconductor manufacturing. The model achieves high accuracy and speed, improving chip production processes.

Keywords:

attention mechanism defect pattern recognition large kernel convolution light-weight neural network wafer map

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

Related Experiment Videos

Last Updated: Jun 18, 2025

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

Area of Science:

Semiconductor Manufacturing
Artificial Intelligence
Computer Vision

Background:

Wafer defect pattern recognition is crucial for improving semiconductor chip production.
Recognizing mixed-type defects in large-scale semiconductor wafer production presents significant challenges requiring high accuracy and speed.

Purpose of the Study:

To propose a lightweight neural network model for efficient and accurate recognition of mixed-type wafer defects.
To enhance feature extraction and retain important information during downsampling for improved defect recognition.

Main Methods:

The proposed model utilizes inverted residual convolution blocks with attention mechanisms for fast inference and enhanced feature extraction.
Large kernel convolution downsampling layers are employed to preserve critical feature information.
The model was evaluated on the real-world Mixed-type WM38 dataset.

Main Results:

The lightweight neural network achieved a recognition accuracy of 98.69% with only 1.01 million parameters.
The model demonstrated superior performance in both accuracy and inference speed compared to existing popular models.
Deployment as a TensorRT engine enabled processing of over 1300 wafer maps per second.

Conclusions:

The proposed lightweight neural network model offers an effective solution for mixed-type wafer defect recognition in semiconductor manufacturing.
The model's efficiency and accuracy contribute to optimizing semiconductor production processes.
The TensorRT engine deployment highlights the model's practical applicability for high-throughput industrial scenarios.