Mechanical Characterization of SMAW and TIG Welded Joints Using Machine Learning Techniques

Patchamatla Satyanarayana Raju; Gogulamanda Veerendra Kumar; A. Gopichand

doi:10.4028/p-69Dznh

Paper Titles

Preface

Comparative Evaluation of Zinc Coatings on Mild Steel: Microstructure and Corrosion Resistance
p.3

Mechanical Characterization of SMAW and TIG Welded Joints Using Machine Learning Techniques
p.11

Recyclability, Water Absorption and Durability of Unstabilized Clay Brick Reinforced with Straw
p.21

Mechanical Behavior of Fiberglass-Reinforced Cementitious Composites at Low Fiber Concentrations
p.37

Experimental and Numerical Study of Flexural Strength of Kenaf Fibre-Reinforced Concrete Beams
p.45

The Application of Base Isolation System as Earthquake Resisting Technology on Mulya Medika Hospital, Samarinda
p.61

Design and Performance Evaluation of HVAC Systems with Thermal Load and Duct Sizing Considerations Theater Buildings
p.73

Electrosynthesis of NaBH₄ from NaBO₂ for Hydrogen Storage
p.87

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 931Mechanical Characterization of SMAW and TIG Welded...

Mechanical Characterization of SMAW and TIG Welded Joints Using Machine Learning Techniques

Abstract:

This research integrates experimental testing and Machine Learning (ML) techniques to predict the weld quality of Tungsten Inert Gas (TIG) and Shielded Metal Arc Welding (SMAW). A balanced dataset comprising weld parameters and mechanical test results including tensile strength, impact energy, and bend test outcomes was compiled for mild steel and stainless steel specimens with thickness ranging from 6mm to 10mm. Experimental results revealed that TIG welding produced superior tensile strength (up to 572 MPa) and impact energy (up to 58J) compared to SMAW. A Random Forest classifier achieved 100% accuracy in classifying weld quality as Good or Defect, while linear Regression produced tensile strength with an R2 of 0.68, Mean Absolute Error (MAE) of 17.5 MPa, and Root Mean Squared Error (RMSE) of 20.27 MPa. These results confirm the viability of ML techniques as non-destructive tools for weld quality prediction and mechanical property estimation. The framework developed in this research contributes to intelligent welding process control and supports the transition toward efficient, data driven manufacturing.

You might also be interested in these eBooks

Structural Materials, Energy Storage, Aerodynamic Design

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volume 931)

Pages:

11-17

DOI:

https://doi.org/10.4028/p-69Dznh

Citation:

Cite this paper

Online since:

February 2026

Authors:

Patchamatla Satyanarayana Raju*, Gogulamanda Veerendra Kumar, A. Gopichand

Keywords:

Intelligent Manufacturing, Linear Regression, List TIG Welding, Machine Learning, Non-Destructive Evaluation, Random Forest Classifier, SMAW, Tensile Strength Prediction, Weld Quality Prediction

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] M. Mothilal and A. Kumar, "Predictive Modeling of ultimate tensile strength in dissimilar friction stir welded aluminum alloys via machine learning approach," philos. Mag. Lett. 105, 2472669 (2025)