Change search
ReferencesLink to record
Permanent link

Direct link
Prediction of the nugget size in resistance spot welding with a combination of a finite-element analysis and an artificial neural network
School of Mechanical Engineering, Iran University of Science and Technology, Tehran, Iran .
Iran Univ Sci & Technol, Tehran, Iran.
KTH, School of Engineering Sciences (SCI), Aeronautical and Vehicle Engineering, Lightweight Structures.ORCID iD: 0000-0003-4180-4710
2014 (English)In: Materiali in tehnologije, ISSN 1580-2949, Vol. 48, no 1, 33-38 p.Article in journal (Refereed) Published
Abstract [en]

The goal of this investigation is to predict the nugget size for a resistance spot weld of thick aluminum 6061-T6 sheets 2 mm. The quality and strength of spot welds determine the integrity of the structure, which depends thoroughly on the nugget size. In this study, the finite-element method and artificial neural network were used to predict the nugget size. Different spot welding parameters such as the welding current and the welding time were selected to be used for a coupled, thermal-electrical-structural finite-element model. In order to validate the numerical results a series of experiments were carried out and the nugget sizes were measured. The results obtained with the finite-element analysis were used to build up a back-propagation, artificial-neural-network model for the nugget-size prediction. The results revealed that a combination of these two developed models can accurately and rapidly predict the nugget size for a resistance spot weld.

Place, publisher, year, edition, pages
2014. Vol. 48, no 1, 33-38 p.
Keyword [en]
resistance spot weld, nugget size, finite-element analysis, artificial neural network, aluminum alloys
National Category
Vehicle Engineering
URN: urn:nbn:se:kth:diva-131317ISI: 000331494300006ScopusID: 2-s2.0-84894055751OAI: diva2:655786

QC 20140325. Updated from accepted to published.

Available from: 2013-10-14 Created: 2013-10-14 Last updated: 2014-03-25Bibliographically approved
In thesis
1. Mechanical Properties of Resistance Spot Welds in Lightweight Applications
Open this publication in new window or tab >>Mechanical Properties of Resistance Spot Welds in Lightweight Applications
2013 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

This licentiate thesis is concerned with residual stresses in aluminum alloy 6061-T6 resistance spot welded joint. Several topics related to mechanical strength of welded structures are treated such as; nugget size and microhardness and microstructures of weld zone and their influence on mechanical strength of welded structure, failure load measurement using tensile-shear test, resistance spot welding simulation, residual stress measurement by X-ray diffraction method and analysis effect of welding parameters on the mechanical strength and the residual stresses.

To investigate the effect of resistance spot weld parameters on mechanical strength of welded structures, various welding parameters e.g. welding current, welding time and electrode force are selected to produce welded joints with different quality. According to the failure mode, the empirical equation was used to prediction of failure load base on nugget size and hardness of failure line. Microstructure study has been carried out to investigate microstructural changes in the welded joints. Microhardness tests are done to find hardness profiles due to microstructural changes and determine the minimum hardness.

In addition, an electro-thermal-structural coupled finite element model and X-ray diffraction residual stress measurement have been utilized to analyze residual stresses distribution in weld zone. The electrical and thermal contact conductance, as mandatory factors are applied in contact area between electrode-workpiece and workpiece-workpiece to resolve the complexity of the finite element model. The physical and mechanical properties of the material are defined as thermal-dependent in order to improve the accuracy of the model. Furthermore, the electrodes are removed after holding cycle using the birth and death elements method. Moreover, the effect of welding parameters on maximum residual stress is investigated and a regression model is proposed to predict maximum tensile residual stresses in terms of welding parameters.

The results obtained from the finite element analysis have been used to build up two back-propagation artificial neural network models for the residual stresses and the nugget size prediction. The results revealed that the neural network models created in this study can accurately predict the nugget size and the residual stresses produced in resistance spot weld. Using a combination of these two developed models, the nugget size and the residual stresses can be predicted in terms of spot weld parameters with high speed and accuracy.

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 2013. v, 19 p.
Trita-AVE, ISSN 1651-7660 ; 2013:45
Spot Weld, Aluminum alloy, Mechanical Properties, Finite Element
National Category
Vehicle Engineering
Research subject
SRA - Production
urn:nbn:se:kth:diva-131306 (URN)978-91-7501-838-6 (ISBN)
2013-09-30, M37, Brinellvagen 64, KTH, Stockholm, 13:15 (English)

QC 20131014

Available from: 2013-10-14 Created: 2013-10-12 Last updated: 2013-10-14Bibliographically approved

Open Access in DiVA

No full text


Search in DiVA

By author/editor
Afshari, DavoodBarsoum, Zuhier
By organisation
Lightweight Structures
In the same journal
Materiali in tehnologije
Vehicle Engineering

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 199 hits
ReferencesLink to record
Permanent link

Direct link