DETECTION OF SURFACE DEFECTS IN FRICTION STIR WELDED JOINTS BY USING A NOVEL MACHINE LEARNING APPROACH

The Friction stir welding process is a new entrant in welding technology. The FSW joints have high strength and helps in weight saving considerably than the other joining process as no filler material is added during welding. The weld quality is affected because of various kinds of defects occurring...

Full description

Bibliographic Details
Main Authors: Akshansh Mishra, Saloni Bhatia Dutta
Format: Article
Language:English
Published: The Association of Intellectuals for the development of Science in Serbia - "The Serbian Academic Center" 2020-03-01
Series:Applied Engineering Letters
Subjects:
Online Access:https://www.aeletters.com/wp-content/uploads/2020/03/AEL00182.pdf
id doaj-95fe3d084c394e4cb231a02b80f195c3
record_format Article
spelling doaj-95fe3d084c394e4cb231a02b80f195c32020-11-25T02:07:57ZengThe Association of Intellectuals for the development of Science in Serbia - "The Serbian Academic Center"Applied Engineering Letters2466-46772466-48472020-03-0151162110.18485/aeletters.2020.5.1.3DETECTION OF SURFACE DEFECTS IN FRICTION STIR WELDED JOINTS BY USING A NOVEL MACHINE LEARNING APPROACHAkshansh Mishra0Saloni Bhatia Dutta1Center for Artificial Intelligence and Friction Stir Welding, Stir Research Technologies, IndiaSchool of Electrical and Electronics Engineering, Gurgaon, India The Friction stir welding process is a new entrant in welding technology. The FSW joints have high strength and helps in weight saving considerably than the other joining process as no filler material is added during welding. The weld quality is affected because of various kinds of defects occurring during the FSW process. Defects like cavity, surface grooves and flash could occur due to inappropriate set of process parameters which results in excessive or insufficient heat input. Defects analysis can be done by several non-destructive methods like immersion ultrasonic techniques, X-ray radiography, thermography, eddy current testing, synchrotron technique etc. In the present work the image processing techniques are applied over the test samples to detect the surface defects like pin holes, surface grooves etc. https://www.aeletters.com/wp-content/uploads/2020/03/AEL00182.pdffriction stir weldingmachine learningdefectsimage processingimage pyramid
collection DOAJ
language English
format Article
sources DOAJ
author Akshansh Mishra
Saloni Bhatia Dutta
spellingShingle Akshansh Mishra
Saloni Bhatia Dutta
DETECTION OF SURFACE DEFECTS IN FRICTION STIR WELDED JOINTS BY USING A NOVEL MACHINE LEARNING APPROACH
Applied Engineering Letters
friction stir welding
machine learning
defects
image processing
image pyramid
author_facet Akshansh Mishra
Saloni Bhatia Dutta
author_sort Akshansh Mishra
title DETECTION OF SURFACE DEFECTS IN FRICTION STIR WELDED JOINTS BY USING A NOVEL MACHINE LEARNING APPROACH
title_short DETECTION OF SURFACE DEFECTS IN FRICTION STIR WELDED JOINTS BY USING A NOVEL MACHINE LEARNING APPROACH
title_full DETECTION OF SURFACE DEFECTS IN FRICTION STIR WELDED JOINTS BY USING A NOVEL MACHINE LEARNING APPROACH
title_fullStr DETECTION OF SURFACE DEFECTS IN FRICTION STIR WELDED JOINTS BY USING A NOVEL MACHINE LEARNING APPROACH
title_full_unstemmed DETECTION OF SURFACE DEFECTS IN FRICTION STIR WELDED JOINTS BY USING A NOVEL MACHINE LEARNING APPROACH
title_sort detection of surface defects in friction stir welded joints by using a novel machine learning approach
publisher The Association of Intellectuals for the development of Science in Serbia - "The Serbian Academic Center"
series Applied Engineering Letters
issn 2466-4677
2466-4847
publishDate 2020-03-01
description The Friction stir welding process is a new entrant in welding technology. The FSW joints have high strength and helps in weight saving considerably than the other joining process as no filler material is added during welding. The weld quality is affected because of various kinds of defects occurring during the FSW process. Defects like cavity, surface grooves and flash could occur due to inappropriate set of process parameters which results in excessive or insufficient heat input. Defects analysis can be done by several non-destructive methods like immersion ultrasonic techniques, X-ray radiography, thermography, eddy current testing, synchrotron technique etc. In the present work the image processing techniques are applied over the test samples to detect the surface defects like pin holes, surface grooves etc.
topic friction stir welding
machine learning
defects
image processing
image pyramid
url https://www.aeletters.com/wp-content/uploads/2020/03/AEL00182.pdf
work_keys_str_mv AT akshanshmishra detectionofsurfacedefectsinfrictionstirweldedjointsbyusinganovelmachinelearningapproach
AT salonibhatiadutta detectionofsurfacedefectsinfrictionstirweldedjointsbyusinganovelmachinelearningapproach
_version_ 1724928608769671168