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

Response Surface Methodology01:16

Response Surface Methodology

147
Response Surface Methodology (RSM) is a collection of statistical and mathematical techniques used to develop, improve, and optimize processes. It is particularly valuable when many input variables or factors potentially influence a response variable.
The process of RSM involves several key steps:
147

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

Reproducibility and validity of an FFQ developed for adults in Nanjing, China.

The British journal of nutrition·2016
Same author

[Chemical Constituents from Leaves of Hibiscus syriacus and Their α-Glucosidase Inhibitory Activities].

Zhong yao cai = Zhongyaocai = Journal of Chinese medicinal materials·2016
Same author

Quantifying Different Tactile Sensations Evoked by Cutaneous Electrical Stimulation Using Electroencephalography Features.

International journal of neural systems·2016
Same author

A Highly Sensitive Immunosorbent Assay Based on Biotinylated Graphene Oxide and the Quartz Crystal Microbalance.

ACS applied materials & interfaces·2016
Same author

Identification of Thyroid Hormones and Functional Characterization of Thyroid Hormone Receptor in the Pacific Oyster Crassostrea gigas Provide Insight into Evolution of the Thyroid Hormone System.

PloS one·2015
Same author

Decreased functional connectivity density in pain-related brain regions of female migraine patients without aura.

Brain research·2015

相关实验视频

Updated: Jul 12, 2025

Surrogate Model Development for Digital Experiments in Welding
09:17

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

962

软感应回归模型:从传感器到晶圆计量预测

Angzhi Fan1, Yu Huang2, Fei Xu3

  • 1Department of Statistics, University of Chicago, Chicago, IL 60637, USA.

Sensors (Basel, Switzerland)
|October 28, 2023
PubMed
概括

本研究介绍了一种机器学习模型,用于使用传感器数据预测半导体检测测量. 长期短期记忆网络有效预测质量指标,改善半导体制造工艺.

关键词:
人工智能的人工智能是人工智能.处理数据的数据处理.晶圆制造 晶圆制造 晶圆制造

更多相关视频

Environmental Dynamic Mechanical Analysis to Predict the Softening Behavior of Neural Implants
06:59

Environmental Dynamic Mechanical Analysis to Predict the Softening Behavior of Neural Implants

Published on: March 1, 2019

7.8K
A Coupled Experiment-finite Element Modeling Methodology for Assessing High Strain Rate Mechanical Response of Soft Biomaterials
11:28

A Coupled Experiment-finite Element Modeling Methodology for Assessing High Strain Rate Mechanical Response of Soft Biomaterials

Published on: May 18, 2015

12.5K

相关实验视频

Last Updated: Jul 12, 2025

Surrogate Model Development for Digital Experiments in Welding
09:17

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

962
Environmental Dynamic Mechanical Analysis to Predict the Softening Behavior of Neural Implants
06:59

Environmental Dynamic Mechanical Analysis to Predict the Softening Behavior of Neural Implants

Published on: March 1, 2019

7.8K
A Coupled Experiment-finite Element Modeling Methodology for Assessing High Strain Rate Mechanical Response of Soft Biomaterials
11:28

A Coupled Experiment-finite Element Modeling Methodology for Assessing High Strain Rate Mechanical Response of Soft Biomaterials

Published on: May 18, 2015

12.5K

科学领域:

  • 半导体制造业 半导体制造业
  • 机器学习 机器学习
  • 计量系统 计量系统

背景情况:

  • 半导体行业要求先进的检测和计量,以降低产量,质量和成本.
  • 通过制造设备中的传感器进行实时监控,使机器学习应用成为可能.
  • 预测计量学的软传感对于流程优化至关重要.

研究的目的:

  • 为了解决测量系统中的软感应回归问题.
  • 使用过程中的传感器数据预测即将进行的检查测量.
  • 为半导体制造开发一个准确和早期预测模型.

主要方法:

  • 提出了一个基于网络的长期短期记忆 (LSTM) 回归器.
  • 开发了两个不同的损失函数用于模型训练.
  • 引入了一种用于准确性评估的新型分片评估指标.

主要成果:

  • 对于各种检查类型,LSTM模型实现了准确和早期的预测.
  • 实验结果证明了该模型在复杂的制造过程中的有效性.
  • 拟议的评估指标提供了一个数学方法来评估预测准确性.

结论:

  • 开发的软感应回归模型增强了半导体计量学中的预测能力.
  • LSTM网络为制造业实时质量预测提供了一个强大的工具.
  • 这种方法促进了主动调整,提高了半导体生产的整体效率.