EUVIMEDEUVIMED entdecken
Crossref

Heat input prediction during dissimilar welding of steel using different machine learning model

Yeshwanth Dendi, Wasim Akram

International Journal of Enhanced Research In Science Technology & Engineering · 2022

DOI: 10.55948/ijerste.2022.1115 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Enhanced Research In Science Technology & Engineering, 2022. Verfasst von Yeshwanth Dendi und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the current research work, different machine learning model such as random forest (RF), support vector regression (SVR), XGBoost and Linear regression (LR) is used to predict the heat input involved in dissimilar welding of AISI 304 stainless steel and AISI 1020 carbon steel. The welding is accomplished using gas metal arc welding with different input parameter such as welding speed, welding current and torch angle. The acceptability of different model is checked based on coefficient of correlation (CC)and root mean square error (RMSE). The RMSE for test data for random forest model and XGBoost model are found to be 10.99 and 9.97 respectively. The corelation coefficient (CC) for test data for random forest model and XGBoost regressor model is found to be 0.9965 and 0.9962 respectively.

Zitieren

APA

Dendi, Y., & Akram, W. (2022). Heat input prediction during dissimilar welding of steel using different machine learning model. International Journal of Enhanced Research In Science Technology & Engineering. https://doi.org/10.55948/ijerste.2022.1115

Vancouver

Dendi Y, Akram W. Heat input prediction during dissimilar welding of steel using different machine learning model. International Journal of Enhanced Research In Science Technology & Engineering. 2022. doi:10.55948/ijerste.2022.1115

BibTeX
@article{Dendi2022,
  author = {Dendi, Yeshwanth and Akram, Wasim},
  title = {Heat input prediction during dissimilar welding of steel using different machine learning model},
  journal = {International Journal of Enhanced Research In Science Technology & Engineering},
  year = {2022},
  doi = {10.55948/ijerste.2022.1115}
}
Kostenlos starten →