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 Experiment Video

Updated: Jan 18, 2026

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

1.0K

Heat Source Parameter Identification Based on Attention-Enhanced Residual Convolutional Neural Network.

Hao Jiang1, Xinyu Liu1, Zhenfei Guo2

  • 1College of Mechanical and Electrical Engineering, Northeast Forestry University, Harbin 150040, China.

Materials (Basel, Switzerland)
|September 13, 2025
PubMed
Summary

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

Harnessing the Versatility of SAM-Dependent Enzymes: From Mechanism to Application.

Chembiochem : a European journal of chemical biology·2026
Same author

Mobile health apps for home care support of children with congenital heart disease: A scoping review based on persuasive system design models.

Digital health·2026
Same author

Evaluation of computational tools for the prediction of CRISPR/SpCas9 gRNA activity in plants.

Plant cell reports·2026
Same author

Dietary supplementation with allicin enhances growth performance and antioxidant capacity, and reduces gut pathogens and antibiotic resistance genes in Trachidermus fasciatus.

Fish physiology and biochemistry·2026
Same author

Molecular characterization of a novel hadakavirus from Pestalotiopsis mangiferae.

Archives of virology·2026
Same author

Cross-cultural adaptation and psychometric testing of the Evidence-Based Practice Mentoring Scale in Chinese nurses.

BMJ open·2026
This summary is machine-generated.

Accurate heat source parameter identification is crucial for reliable welding simulations. This study introduces HSPINet, a novel deep learning model, for efficient and precise identification of these critical welding parameters.

Area of Science:

  • Materials Science and Engineering
  • Computational Mechanics
  • Artificial Intelligence in Manufacturing

Background:

  • Welding thermal analysis accuracy relies heavily on heat source parameters.
  • Inaccurate parameters compromise predictions of temperature distribution, distortion, and residual stress.
  • Existing identification methods struggle with complex industrial environments.

Purpose of the Study:

  • To develop an intelligent model for accurate heat source parameter identification.
  • To enhance the reliability of welding thermal simulations for safety-critical structures.
  • To provide an adaptable tool for complex industrial welding applications.

Main Methods:

  • Proposed the Heat Source Parameter Identification Network (HSPINet) model.
Keywords:
heat source parametersparameter inversionresidual convolutional neural networkwelding simulation

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.3K

Related Experiment Videos

Last Updated: Jan 18, 2026

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

1.0K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.3K
  • Utilized a residual convolutional neural network (ResNet) architecture.
  • Incorporated an attention mechanism for feature extraction from T-joint weld morphology.

    • Main Results:

    • HSPINet efficiently and accurately identifies heat source parameters.
    • The model effectively extracts key features considering process parameters and joint dimensions.
    • Demonstrated improved intelligence in heat source parameter identification.

    Conclusions:

    • HSPINet offers a practical, intelligent solution for welding simulation.
    • The model enhances thermal field evaluation accuracy in industrial settings.
    • Shows significant theoretical value and broad applicability in laser processing and manufacturing.