Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

Layer-specific facial soft-tissue thickness in 1174 Chinese adults: Implications for finite-element headforms and ergonomic design.

Ergonomics·2026
Same author

Independent and joint effects of ambient temperature and relative humidity on fetal distress: effect modification by air pollutants.

International journal of biometeorology·2026
Same author

Permeability prediction of 3D complex fracture networks in deep underground based on fractal analysis of trace maps.

Scientific reports·2026
Same author

Therapeutic leukapheresis with severe pertussis: evaluating efficacy, feasibility, and safety.

BMC pediatrics·2026
Same author

Assessing Executive Function in Patients With Temporal Lobe Epilepsy Through a Game-Based Assessment Task.

Behavioural neurology·2026
Same author

In Vivo Calcium Imaging with a Miniaturized Microscope in the Hypothalamus for Understanding Social Behaviors in Mice.

Journal of visualized experiments : JoVE·2026

Related Experiment Video

Updated: Jul 23, 2025

Comprehensive Characterization of Extended Defects in Semiconductor Materials by a Scanning Electron Microscope
11:14

Comprehensive Characterization of Extended Defects in Semiconductor Materials by a Scanning Electron Microscope

Published on: May 28, 2016

13.9K

Node-Loss Detection Methods for CZ Silicon Single Crystal Based on Multimodal Data Fusion.

Lei Jiang1,2, Rui Xue1, Ding Liu1,2

  • 1School of Automation and Information Engineering, Xi'an University of Technology, Xi'an 710048, China.

Sensors (Basel, Switzerland)
|July 14, 2023
PubMed
Summary

This study introduces a new method using multimodal data fusion to detect node loss during monocrystalline silicon growth. The approach accurately identifies defects, enhancing quality control in semiconductor manufacturing.

Keywords:
CZ silicon single crystalattention mechanismcontinuous wavelet transformconvolutional neural networkmultimodal data fusionnode-loss detection

More Related Videos

Synchrotron X-ray Microdiffraction and Fluorescence Imaging of Mineral and Rock Samples
10:12

Synchrotron X-ray Microdiffraction and Fluorescence Imaging of Mineral and Rock Samples

Published on: June 19, 2018

9.1K
Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles
11:54

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

9.3K

Related Experiment Videos

Last Updated: Jul 23, 2025

Comprehensive Characterization of Extended Defects in Semiconductor Materials by a Scanning Electron Microscope
11:14

Comprehensive Characterization of Extended Defects in Semiconductor Materials by a Scanning Electron Microscope

Published on: May 28, 2016

13.9K
Synchrotron X-ray Microdiffraction and Fluorescence Imaging of Mineral and Rock Samples
10:12

Synchrotron X-ray Microdiffraction and Fluorescence Imaging of Mineral and Rock Samples

Published on: June 19, 2018

9.1K
Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles
11:54

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

9.3K

Area of Science:

  • Materials Science
  • Semiconductor Manufacturing
  • Artificial Intelligence

Background:

  • Monocrystalline silicon is crucial for semiconductor and photovoltaic industries.
  • The Czochralski (CZ) method for silicon growth is susceptible to node loss, causing crystal failure.
  • Current industrial methods lack efficient detection for node loss during silicon growth.

Purpose of the Study:

  • To develop an efficient, data-driven method for detecting node loss in monocrystalline silicon growth.
  • To explore the application of multimodal data fusion in analyzing silicon crystal growth.
  • To improve the accuracy and reliability of defect detection in the CZ method.

Main Methods:

  • Collected multimodal data including diameter, temperature, pulling speed, and meniscus images.
  • Applied continuous wavelet transform for one-dimensional signal preprocessing.
  • Utilized improved channel attention mechanism convolutional neural networks (ICAM-CNN) and multimodal fusion networks (MMFN) for data analysis and defect recognition.

Main Results:

  • The proposed ICAM-CNN and MMFN methods accurately detected node-loss defects in CZ silicon single-crystal growth.
  • Achieved high accuracy, robustness, and real-time performance in defect detection.
  • Demonstrated the effectiveness of multimodal data fusion for monitoring silicon crystal growth.

Conclusions:

  • The developed multimodal data fusion method offers an effective solution for real-time node-loss detection.
  • This approach can significantly enhance efficiency and quality control in industrial monocrystalline silicon production.
  • The data-driven techniques provide valuable technical support for the semiconductor and photovoltaic sectors.