Prediction of the optimal FSW process parameters for joints using machine learning techniques

Küçük Resim Yok

Tarih

2021

Dergi Başlığı

Dergi ISSN

Cilt Başlığı

Yayıncı

Walter de Gruyter GmbH

Erişim Hakkı

info:eu-repo/semantics/closedAccess

Özet

In this work, a couple of dissimilar AA2024/AA7075 plates were experimentally welded for the purpose of considering the effect of friction-stir welding (FSW) parameters on mechanical properties. First, the main mechanical properties such as ultimate tensile strength (UTS) and hardness of welded joints were determined experimentally. Secondly, these data were evaluated through modeling and the optimization of the FSW process as well as an optimal parametric combination to affirm tensile strength and hardness using a support vector machine (SVM) and an artificial neural network (ANN). In this study, a new ANN model, including the Nelder-Mead algorithm, was first used and compared with the SVM model in the FSW process. It was concluded that the ANN approach works better than SVM techniques. The validity and accuracy of the proposed method were proved by simulation studies.

Açıklama

Anahtar Kelimeler

Friction-stir welding, ANN, SVM, aluminum alloys, nelder-mead nonlinear optimization algorithm

Kaynak

Materials Testing

WoS Q Değeri

Q2

Scopus Q Değeri

Cilt

Sayı

Künye

Sarsilmaz, F., & Kavuran, G. (2021). Prediction of the optimal FSW process parameters for joints using machine learning techniques. Materials Testing, 63(12), 1104-1111.