Statistical analysis of friction stir weld data

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


This chapter discusses the results of statistical analysis conducted on the weld data obtained from friction stir welding of aluminium and copper. The welds were produced by varying the process parameters; the rotational speed was varied between 600 and 1200 rpm and the welding speed varied between 50 and 300 mm/min. The Statistica (version 9.0) statistical analysis software package was used to generate the scatter and surface plots relative to the experimental results obtained from the tensile testing and the FSW data. Regression analysis was also done on the weld data. It was found that the downward vertical force during the welding process has a significant effect on the Ultimate Tensile Strength of the weld and that strong relationships exist between the heat input into the welds and the measured electrical resistivities of the welds.

Original languageEnglish
Title of host publicationIAENG Transactions on Engineering Technologies - Special Issue of the International MultiConference of Engineers and Computer Scientists 2012
PublisherSpringer Verlag
Number of pages14
ISBN (Print)9789400756236
Publication statusPublished - 2013
EventInternational MultiConference of Engineers and Computer Scientists 2012, IMECS 2012 - Hong Kong, Hong Kong
Duration: 14 Mar 201216 Mar 2012

Publication series

NameLecture Notes in Electrical Engineering
Volume186 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119


ConferenceInternational MultiConference of Engineers and Computer Scientists 2012, IMECS 2012
Country/TerritoryHong Kong
CityHong Kong


  • Analysis of scatter plot
  • Analysis of surface plot
  • Analysis of variance
  • Dissimilar materials
  • Friction stir welding
  • Regression analysis

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering


Dive into the research topics of 'Statistical analysis of friction stir weld data'. Together they form a unique fingerprint.

Cite this