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

Predicting Molecular Geometry02:27

Predicting Molecular Geometry

VSEPR Theory for Determination of Electron Pair Geometries
Metallic Solids02:37

Metallic Solids

Metallic solids such as crystals of copper, aluminum, and iron are formed by metal atoms. The structure of metallic crystals is often described as a uniform distribution of atomic nuclei within a “sea” of delocalized electrons. The atoms within such a metallic solid are held together by a unique force known as metallic bonding that gives rise to many useful and varied bulk properties.
All metallic solids exhibit high thermal and electrical conductivity, metallic luster, and malleability. Many...
Metal-Ligand Bonds02:51

Metal-Ligand Bonds

The hemoglobin in the blood, the chlorophyll in green plants, vitamin B-12, and the catalyst used in the manufacture of polyethylene all contain coordination compounds. Ions of the metals, especially the transition metals, are likely to form complexes.
In these complexes, transition metals form coordinate covalent bonds, a kind of Lewis acid-base interaction in which both of the electrons in the bond are contributed by a donor (Lewis base) to an electron acceptor (Lewis acid). The Lewis acid in...
Valence Bond Theory02:42

Valence Bond Theory

Coordination compounds and complexes exhibit different colors, geometries, and magnetic behavior, depending on the metal atom/ion and ligands from which they are composed. In an attempt to explain the bonding and structure of coordination complexes, Linus Pauling proposed the valence bond theory, or VBT, using the concepts of hybridization and the overlapping of the atomic orbitals. According to VBT, the central metal atom or ion (Lewis acid) hybridizes to provide empty orbitals of suitable...
Metal-Semiconductor Junctions01:24

Metal-Semiconductor Junctions

The contact of metal and semiconductor can lead to the formation of a junction with either Schottky or Ohmic behavior.
Schottky Barriers
Schottky barriers arise when a metal with a work function (Φm) contacts a semiconductor with a different work function (Φs). Initially, electrons transfer until the Fermi levels of the metal and semiconductor align at equilibrium. For instance, if Φm > Φs, the semiconductor Fermi level is higher than the metal's before contact. The semiconductor's...

You might also read

Related Articles

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

Sort by
Same author

Development of a Deep Learning-Based Decision Framework for Optimal Process Parameter Selection in Metal Additive Manufacturing.

Sensors (Basel, Switzerland)·2026
Same author

Sudden Fall Detection of Human Body Using Transformer Model.

Sensors (Basel, Switzerland)·2025
Same author

Prediction of Metal Additively Manufactured Surface Roughness Using Deep Neural Network.

Sensors (Basel, Switzerland)·2022
See all related articles

Related Experiment Video

Updated: Jun 28, 2026

Interfacing 3D Engineered Neuronal Cultures to Micro-Electrode Arrays: An Innovative In Vitro Experimental Model
09:47

Interfacing 3D Engineered Neuronal Cultures to Micro-Electrode Arrays: An Innovative In Vitro Experimental Model

Published on: October 18, 2015

10.0K

Prediction of Metal Additively Manufactured Bead Geometry Using Deep Neural Network.

Min Seop So1, Mohammad Mahruf Mahdi2, Duck Bong Kim3

  • 1Department of Industrial Engineering, Chosun University, Gwangju 61452, Republic of Korea.

Sensors (Basel, Switzerland)
|October 16, 2024
PubMed
Summary

A Deep Neural Network (DNN) accurately predicts bead geometry in Wire Arc Additive Manufacturing (WAAM), enhancing structural integrity for large metal parts. This advanced machine learning approach improves precision in the aerospace sector.

Keywords:
bead geometrydeep neural network (DNN)gas metal arc welding (GMAW)wire arc additive manufacturing (WAAM)

More Related Videos

A Paired Bead and Magnet Array for Molding Microwells with Variable Concave Geometries
11:42

A Paired Bead and Magnet Array for Molding Microwells with Variable Concave Geometries

Published on: January 28, 2018

8.7K
Surrogate Model Development for Digital Experiments in Welding
09:17

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

712

Related Experiment Videos

Last Updated: Jun 28, 2026

Interfacing 3D Engineered Neuronal Cultures to Micro-Electrode Arrays: An Innovative In Vitro Experimental Model
09:47

Interfacing 3D Engineered Neuronal Cultures to Micro-Electrode Arrays: An Innovative In Vitro Experimental Model

Published on: October 18, 2015

10.0K
A Paired Bead and Magnet Array for Molding Microwells with Variable Concave Geometries
11:42

A Paired Bead and Magnet Array for Molding Microwells with Variable Concave Geometries

Published on: January 28, 2018

8.7K
Surrogate Model Development for Digital Experiments in Welding
09:17

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

712

Area of Science:

  • Manufacturing Engineering
  • Materials Science
  • Artificial Intelligence

Background:

  • Additive Manufacturing (AM), specifically Wire Arc Additive Manufacturing (WAAM), enables large metal component production, crucial for aerospace.
  • Precise control over bead geometry (width and height) is vital for WAAM part integrity.
  • Existing methods struggle with the complex, nonlinear relationships governing WAAM bead formation.

Purpose of the Study:

  • To develop and validate a Deep Neural Network (DNN) model for accurate prediction of bead geometry in Gas Metal Arc Welding-Cold Metal Transfer (GMAW-CMT) WAAM.
  • To compare the predictive performance of the DNN against traditional regression and machine learning models.
  • To demonstrate the potential of deep learning for enhancing WAAM process control and efficiency.

Main Methods:

  • Collected precise process parameter data (wire speed, feed rate) and bead dimensions using a Coordinate Measuring Machine (CMM).
  • Trained and validated multiple regression models, including Linear Regression, Ridge, Polynomial, Random Forest, and a custom DNN.
  • Designed a DNN with multiple hidden layers, trained via backpropagation, and optimized with the Adam optimizer.

Main Results:

  • The DNN model demonstrated superior accuracy in predicting bead width and height compared to all other tested models.
  • Achieved very low error metrics: 0.014% MAPE for width, 0.012% MAPE for height, 0.122 RMSE for width, and 0.153 RMSE for height.
  • Random Forest also showed effectiveness, but the DNN excelled due to its ability to capture complex nonlinearities.

Conclusions:

  • Deep Neural Networks offer a highly accurate and robust method for forecasting bead geometry in WAAM processes.
  • The developed DNN model can significantly improve the precision and reliability of WAAM-manufactured components.
  • This research highlights the transformative potential of AI and deep learning in advancing additive manufacturing technologies.