Regression modeling and neural computing for predicting the Ultimate Tensile Strength of Friction Stir Welded aerospace aluminium alloy

  • Akshansh Mishra Stir Research Technologies, Uttar Pradesh, India https://orcid.org/0000-0003-4939-359X
  • Jonathan Ve Vance Department of Engineering Design, Indian Institute of Technology Madras, Ćennaj, Tamilnadu, India
DOI: https://doi.org/10.30464/jmee.2019.3.3.221
Keywords: Artificial neural network, Regression model, Friction Stir Welding

Abstract

AA7075 is an aluminum alloy that's almost as strong as steel, yet it weighs just one third as much. Unfortunately, its use has been limited, due to the fact that pieces of it couldn't be securely welded together by the traditional welding process. Friction Stir Welding (FSW) process overcomes the limitations of the conventional welding process. The aim of our present is to compare the predicted results of the Ultimate Tensile Strength (UTS) of Friction Stir welded similar joints through Regression modeling and Artificial Neural Network (ANN) modeling. It was observed that the linear regression algorithm is able to make more accurate predictions compared to neural network algorithm for small dataset.

Downloads

Download data is not yet available.

Author Biographies

Akshansh Mishra, Stir Research Technologies, Uttar Pradesh, India

author_Mishra.png

Akshansh Mishra is a founder of Stir Research Technologies which deals in collaborative research in Artificial Intelligence and Friction Stir Welding. Currently, he now works as a Principal Deep Learning Scientist in Codes & Coffee.  He had developed the first MOOC on Friction Stir Welding which is available on Udemy. His main research interests are Friction Stir Welding, Artificial Neural Network and Reinforcement Learning. He has published 7 research books dealing with Friction Stir Welding, Composites, Laser Welding and Artificial Intelligence which are available on Amazon.

Jonathan Ve Vance, Department of Engineering Design, Indian Institute of Technology Madras, Ćennaj, Tamilnadu, India

author_Ve_Vance.png

Jonathan Ve Vance is an undergraduate student in the Department of Engineering Design, IIT Madras. His main research interests are Artificial Intelligence, Neural Network and Deep Learning.

JMME 3(3) 2019 front cover
Published
2019-12-23
How to Cite
Mishra, A. and Ve Vance, J. (2019) “Regression modeling and neural computing for predicting the Ultimate Tensile Strength of Friction Stir Welded aerospace aluminium alloy”, Journal of Mechanical and Energy Engineering, 3(3), pp. 221-226. doi: 10.30464/jmee.2019.3.3.221.
Issue
Vol 3 No 3 (2019)
Section
Mechanical Engineering

Copyright (c) 2019 Akshansh Mishra, Jonathan Ve Vance

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors retain full copyright to their individual works.
The Journal of Mechanical and Energy Engineering (JMEE) publishes fully open access articles.

Open Access benefits:

  • High visibility – all articles are made freely available online for everyone worldwide, immediately upon publication.
  • Increased visibility and readership.
  • Rapid publication.
  • All articles are CC BY licensed. The final article can be reused and immediately deposited in any repository.
  • Authors retain the copyright to their work.

By publishing with us, you retain the copyright of your work under the terms of a Creative Commons Attribution 4.0 International (CC BY) license.

The CC BY license permits unrestricted use, distribution and reproduction in any medium, provided appropriate credit is given to the original author(s) and the source, a link to the Creative Commons license is included, and it is indicated if any changes were made. This means that you can deposit the final version of your work in any digital repository immediately after publication.

We are committed to providing high-level peer review, author and production services, so you can trust in the quality and reliability of the work that we publish.