.png){kind=icon}
.png){kind=icon}
Return
Machine learning approach for the prediction of tensile strength of carbon nanotubes reinforced AA2024 by friction stir welding and friction stir processing
.png){kind=icon}
PRE
AI
T
P
L
S
DOI：10.1007/s12206-026-0119-y.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The focus of this research is the integration of friction stir welding (FSW) and friction stir processing (FSP) to enhance the ultimate tensile strength (UTS) of aluminium 2024 (AA2024) reinforced with multiwalled carbon nanotubes (CNTs) and to predict UTS using machine learning (ML) techniques. Tensile strength increased from 476 MPa to 780 MPa after processing and optimal parameters of tool rotation speed (TRS), feed rate (FR), groove depth (GD), and tilt angle (TA) were determined using the Taguchi method. Traditional statistical methods, such as linear regression, were less effective in capturing nonlinear relationships, whereas ML models, including random forest regression, gradient boosting, TPOT regression, and neural networks, provided more accurate predictions.
Keywords:
Carbon nanotubes
Friction stir processing
Friction stir welding
Ultimate tensile strength
Journal
IF:
1.7
Papers:
481
Citations:
1.2W
Organization
Cited Papers