Search published articles


Showing 1 results for Least Squares Support Vector Machine

M.r. Maraki, M. Mahmoodi, M. Yousefieh, H. Tagimalek,
Volume 8, Issue 2 (1-2023)
Abstract

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.


Page 1 from 1     

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

Designed & Developed by : Yektaweb