Application of neural network for the prediction of tensile properties of friction stir welded composites

Arun Kumar Shettigar, Subramanya Prabhu, Rashmi Malghan, Shrikantha Rao, Mervin Herbert

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

In this paper, an attempt has been made to apply the neural network (NN) techniques to predict the mechanical properties of friction stir welded composite materials. Nowadays, friction stri welding of composites are predominatally used in aerospace, automobile and shipbuilding applications. The welding process parameters like rotational speed, welding speed, tool pin profile and type of material play a foremost role in determining the weld strength of the base material. An error back propagation algorithm based model is developed to map the input and output relation of friction stir welded composite material. The proposed model is able to predict the joint strength with minimum error.

Original languageEnglish
Title of host publication4th Asia Conference on Mechanical and Materials Engineering
PublisherTrans Tech Publications Ltd
Pages128-131
Number of pages4
ISBN (Print)9783038357445
DOIs
Publication statusPublished - 01-01-2017
Event4th Asia Conference on Mechanical and Materials Engineering, ACMME 2016 - Kuala Lumpur, Malaysia
Duration: 14-07-201618-07-2016

Publication series

NameMaterials Science Forum
Volume880
ISSN (Print)0255-5476

Conference

Conference4th Asia Conference on Mechanical and Materials Engineering, ACMME 2016
CountryMalaysia
CityKuala Lumpur
Period14-07-1618-07-16

Fingerprint

tensile properties
Tensile properties
friction
Friction
Neural networks
welding
composite materials
Composite materials
Welding
weld strength
friction welding
predictions
Friction welding
Shipbuilding
Backpropagation algorithms
automobiles
Automobiles
Welds
mechanical properties
Mechanical properties

All Science Journal Classification (ASJC) codes

  • Materials Science(all)
  • Condensed Matter Physics
  • Mechanics of Materials
  • Mechanical Engineering

Cite this

Shettigar, A. K., Prabhu, S., Malghan, R., Rao, S., & Herbert, M. (2017). Application of neural network for the prediction of tensile properties of friction stir welded composites. In 4th Asia Conference on Mechanical and Materials Engineering (pp. 128-131). (Materials Science Forum; Vol. 880). Trans Tech Publications Ltd. https://doi.org/10.4028/www.scientific.net/MSF.880.128
Shettigar, Arun Kumar ; Prabhu, Subramanya ; Malghan, Rashmi ; Rao, Shrikantha ; Herbert, Mervin. / Application of neural network for the prediction of tensile properties of friction stir welded composites. 4th Asia Conference on Mechanical and Materials Engineering. Trans Tech Publications Ltd, 2017. pp. 128-131 (Materials Science Forum).
@inproceedings{f56c61038aff4c99ae6b5497a47133e0,
title = "Application of neural network for the prediction of tensile properties of friction stir welded composites",
abstract = "In this paper, an attempt has been made to apply the neural network (NN) techniques to predict the mechanical properties of friction stir welded composite materials. Nowadays, friction stri welding of composites are predominatally used in aerospace, automobile and shipbuilding applications. The welding process parameters like rotational speed, welding speed, tool pin profile and type of material play a foremost role in determining the weld strength of the base material. An error back propagation algorithm based model is developed to map the input and output relation of friction stir welded composite material. The proposed model is able to predict the joint strength with minimum error.",
author = "Shettigar, {Arun Kumar} and Subramanya Prabhu and Rashmi Malghan and Shrikantha Rao and Mervin Herbert",
year = "2017",
month = "1",
day = "1",
doi = "10.4028/www.scientific.net/MSF.880.128",
language = "English",
isbn = "9783038357445",
series = "Materials Science Forum",
publisher = "Trans Tech Publications Ltd",
pages = "128--131",
booktitle = "4th Asia Conference on Mechanical and Materials Engineering",

}

Shettigar, AK, Prabhu, S, Malghan, R, Rao, S & Herbert, M 2017, Application of neural network for the prediction of tensile properties of friction stir welded composites. in 4th Asia Conference on Mechanical and Materials Engineering. Materials Science Forum, vol. 880, Trans Tech Publications Ltd, pp. 128-131, 4th Asia Conference on Mechanical and Materials Engineering, ACMME 2016, Kuala Lumpur, Malaysia, 14-07-16. https://doi.org/10.4028/www.scientific.net/MSF.880.128

Application of neural network for the prediction of tensile properties of friction stir welded composites. / Shettigar, Arun Kumar; Prabhu, Subramanya; Malghan, Rashmi; Rao, Shrikantha; Herbert, Mervin.

4th Asia Conference on Mechanical and Materials Engineering. Trans Tech Publications Ltd, 2017. p. 128-131 (Materials Science Forum; Vol. 880).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Application of neural network for the prediction of tensile properties of friction stir welded composites

AU - Shettigar, Arun Kumar

AU - Prabhu, Subramanya

AU - Malghan, Rashmi

AU - Rao, Shrikantha

AU - Herbert, Mervin

PY - 2017/1/1

Y1 - 2017/1/1

N2 - In this paper, an attempt has been made to apply the neural network (NN) techniques to predict the mechanical properties of friction stir welded composite materials. Nowadays, friction stri welding of composites are predominatally used in aerospace, automobile and shipbuilding applications. The welding process parameters like rotational speed, welding speed, tool pin profile and type of material play a foremost role in determining the weld strength of the base material. An error back propagation algorithm based model is developed to map the input and output relation of friction stir welded composite material. The proposed model is able to predict the joint strength with minimum error.

AB - In this paper, an attempt has been made to apply the neural network (NN) techniques to predict the mechanical properties of friction stir welded composite materials. Nowadays, friction stri welding of composites are predominatally used in aerospace, automobile and shipbuilding applications. The welding process parameters like rotational speed, welding speed, tool pin profile and type of material play a foremost role in determining the weld strength of the base material. An error back propagation algorithm based model is developed to map the input and output relation of friction stir welded composite material. The proposed model is able to predict the joint strength with minimum error.

UR - http://www.scopus.com/inward/record.url?scp=85002169010&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85002169010&partnerID=8YFLogxK

U2 - 10.4028/www.scientific.net/MSF.880.128

DO - 10.4028/www.scientific.net/MSF.880.128

M3 - Conference contribution

SN - 9783038357445

T3 - Materials Science Forum

SP - 128

EP - 131

BT - 4th Asia Conference on Mechanical and Materials Engineering

PB - Trans Tech Publications Ltd

ER -

Shettigar AK, Prabhu S, Malghan R, Rao S, Herbert M. Application of neural network for the prediction of tensile properties of friction stir welded composites. In 4th Asia Conference on Mechanical and Materials Engineering. Trans Tech Publications Ltd. 2017. p. 128-131. (Materials Science Forum). https://doi.org/10.4028/www.scientific.net/MSF.880.128