Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Steel Manufacturing

Steel Manufacturing

Steel manufacturing is a multi-stage process that begins by smelting iron ore into cast iron in a blast furnace. This initial stage involves layering iron ore with coke, a type of fuel, and crushed limestone within the furnace. The coke is ignited with a high volume of air, leading to the creation of carbon monoxide, which acts to reduce the iron ore to pure iron.
During this smelting process, limestone plays a crucial role by forming slag. Slag captures impurities within the molten iron, such...

Methods of Medium Optimization

Methods of Medium Optimization

Optimizing growth media enhances microbial proliferation and maximizes product yield. Statistical experimental design methodologies provide structured and reproducible approaches, offering progressively higher levels of robustness and efficiency.The One-Factor-at-a-Time (OFAT) MethodThe One-Factor-at-a-Time (OFAT) method involves adjusting a single variable while keeping all others constant. However, it cannot detect interactions between variables, often leading to suboptimal outcomes when...

You might also read

Related Articles

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

Sort by

Same author

Sudden Fall Detection of Human Body Using Transformer Model.

Sensors (Basel, Switzerland)·2025

Same author

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

Sensors (Basel, Switzerland)·2024

Same author

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

Sensors (Basel, Switzerland)·2022

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 28, 2026

Knowledge Based Cloud FE Simulation of Sheet Metal Forming Processes

Knowledge Based Cloud FE Simulation of Sheet Metal Forming Processes

Published on: December 13, 2016

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

Min Seop So¹, Duck Bong Kim², Duncan Kibet¹

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

Sensors (Basel, Switzerland)

|February 27, 2026

Summary

This study introduces an AI framework to optimize Wire Arc Additive Manufacturing (WAAM) by controlling surface roughness. The AI rapidly identifies optimal parameters, reducing post-processing and improving productivity.

Keywords:

arc welding deep neural network surface roughness wire + arc additive manufacturing

More Related Videos

Production of Single Tracks of Ti-6Al-4V by Directed Energy Deposition to Determine the Layer Thickness for Multilayer Deposition

Production of Single Tracks of Ti-6Al-4V by Directed Energy Deposition to Determine the Layer Thickness for Multilayer Deposition

Published on: March 13, 2018

Surrogate Model Development for Digital Experiments in Welding

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

Related Experiment Videos

Last Updated: Jun 28, 2026

Knowledge Based Cloud FE Simulation of Sheet Metal Forming Processes

Knowledge Based Cloud FE Simulation of Sheet Metal Forming Processes

Published on: December 13, 2016

Production of Single Tracks of Ti-6Al-4V by Directed Energy Deposition to Determine the Layer Thickness for Multilayer Deposition

Production of Single Tracks of Ti-6Al-4V by Directed Energy Deposition to Determine the Layer Thickness for Multilayer Deposition

Published on: March 13, 2018

Surrogate Model Development for Digital Experiments in Welding

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

Area of Science:

Manufacturing Engineering
Materials Science
Artificial Intelligence

Background:

Conventional manufacturing methods like cutting generate waste and limit design complexity.
Wire Arc Additive Manufacturing (WAAM) offers an alternative but suffers from surface irregularities, requiring extensive post-processing.
Optimizing WAAM deposition parameters is crucial for productivity but challenging due to evolving layer geometries.

Purpose of the Study:

To develop an AI-based framework for real-time control of surface roughness in multilayer WAAM.
To enable rapid identification of near-optimal process parameters in response to changing bead geometry.
To enhance WAAM productivity by minimizing post-processing requirements.

Main Methods:

Generated a large-scale simulation dataset using a pre-trained deep neural network (DNN) to predict surface roughness for one million bead geometry variations.
Trained a classification model on optimal parameter labels derived from the simulation data to recommend process conditions based on current bead geometry.
Evaluated model performance using predictor-estimated surface roughness, achieving high precision, recall, and F1-score (0.98) with an average AUC of 0.977.

Main Results:

The AI-driven framework demonstrated high accuracy in predicting optimal WAAM parameters.
Comparative analysis using a validated surface roughness prediction model showed AI-recommended conditions consistently reduced predicted surface roughness.
The AI framework achieved weighted precision, recall, and F1-score of 0.98, with an average AUC of 0.977.

Conclusions:

The proposed AI framework effectively controls surface roughness in WAAM by identifying optimal process parameters.
AI-driven optimization has the potential to significantly improve surface quality in WAAM.
This approach can reduce the need for post-processing, thereby increasing overall manufacturing productivity.