Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
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
查看所有相关文章

相关实验视频

Updated: Jun 18, 2025

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

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

Published on: January 5, 2024

1.0K

基于轻量级神经网络的高效混合型晶圆缺陷模式识别.

Guangyuan Deng1,2, Hongcheng Wang1

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

Micromachines
|July 27, 2024
PubMed
概括
此摘要是机器生成的。

本研究介绍了一种轻量级的神经网络,用于在半导体制造中高效地识别混合型晶圆缺陷. 该模型实现了高精度和速度,改善了芯片生产过程.

关键词:
注意力机制注意力机制缺陷模式识别 缺陷模式识别大型内核卷积卷积.轻质神经网络是一种轻质神经网络.晶圆地图 晶圆地图

更多相关视频

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

512
Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
11:34

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

11.1K

相关实验视频

Last Updated: Jun 18, 2025

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

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

Published on: January 5, 2024

1.0K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

512
Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
11:34

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

11.1K

科学领域:

  • 半导体制造业 半导体制造业
  • 人工智能的人工智能
  • 计算机视觉 计算机视觉

背景情况:

  • 晶圆缺陷模式识别对于改善半导体芯片生产至关重要.
  • 在大规模的半导体晶圆生产中识别混合类型的缺陷存在重大挑战,需要高精度和速度.

研究的目的:

  • 提出一个轻量级的神经网络模型,以高效准确地识别混合型晶圆缺陷.
  • 为了增强特征提取和保留重要的信息,在下方采样期间改善缺陷识别.

主要方法:

  • 拟议的模型使用反向剩余卷积块,并配有注意力机制,用于快速推断和增强特征提取.
  • 使用大型内核卷积下采样层来保存关键特征信息.
  • 该模型在现实世界混合型WM38数据集上进行了评估.

主要成果:

  • 这种轻量级的神经网络只用101万个参数实现了98.69%的识别精度.
  • 该模型在准确性和推断速度方面表现出优异的性能,与现有的流行的模型相比.
  • 作为TensorRT引擎的部署使得每秒能够处理超过1300个晶圆地图.

结论:

  • 拟议的轻量级神经网络模型为半导体制造中混合型晶圆缺陷识别提供了有效的解决方案.
  • 该模型的效率和准确性有助于优化半导体生产过程.
  • TensorRT引擎的部署突显了该模型在高通量工业场景中的实际应用性.