Volume 8, Issue 2 (Journal OF Welding Science and Technology 2023)                   JWSTI 2023, 8(2): 145-154 | Back to browse issues page

XML Persian Abstract Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Maraki M, Mahmoodi M, Yousefieh M, Tagimalek H. Prediction and optimization of weld geometry in gas metal arc welding (GMAW) using least squares support vector machine. JWSTI 2023; 8 (2) :145-154
URL: http://jwsti.iut.ac.ir/article-1-419-en.html
1- Faculty of Materials and Metallurgy, Birjand University of Technology, Birjand, Iran , maraki@birjandut.ac.ir
2- Faculty of Mechanical Engineering, Semnan University, Semnan, Iran
3- Faculty of Materials Engineering and Metallurgy, Semnan University, Semnan, Iran
Abstract:   (2718 Views)
In Wire and arc additive manufacturing (WAAM) based on Gas metal arc welding (GMAW) is one of the methods of manufacturing metal layer by layer. One of this method's basic steps is predicting the welding geometry created in each welding step. In the current research, an experimental study was conducted in this field considering the effective parameters of welding geometry. For this purpose, three parameters of voltage, welding speed, and wire feeding speed were considered as effective parameters on the welding geometry of the process. The width and height of the weld bead was selected as the answer according to the type and application of the research. The least squares support vector machine was used to model the welding geometry in the process. The results obtained from the regression (R2) of train, test, validation, and total were 0.945, 0.793, 0.894, and 0.881 respectively. The comparison between the experimental data and the model data shows the significance of the proposed model.
Full-Text [PDF 1292 kb]   (792 Downloads)    
Type of Study: Research | Subject: Special

Add your comments about this article : Your username or Email:
CAPTCHA

Send email to the article author


Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

© 2024 CC BY-NC 4.0 | Journal of Welding Science and Technology of Iran

Designed & Developed by : Yektaweb