Experimental Analysis of Friction Stir Welding of Dissimilar Aluminium Alloys by Machine Learning
Keywords:
Friction stir welding, Analysis of variance, Ultimate tensile strength, Random forest regressor, Artificial Neural NetworkAbstract
This research focusses on joining of dissimilar materials on AA5083 and AA6082 using friction stir welding process. Tool rotation speed, welding speed and tool tilt angle are optimized using L27 Orthogonal design of experiments with tensile strength as the response. To evaluate potential of sophisticated machine learning methodologies, random forest regressor and artificial neural network algorithms are utilized for predicting the joint strength of friction stir welded dissimilar plates of AA5083 and AA6082. These models are used to investigate discrepancies between experimental and predicted results. Of the available results, 21 readings are chosen for training the model while remaining are used for testing the model. Random forest regressor and artificial neural network techniques were formed using the data associated with the experiment. Moreover, results of the analysis of variances are compared to the machine learning predicted results to determine the variances.
Downloads
Downloads
Published
Issue
Section
License
Copyright (c) 2023 International Journal of Integrated Engineering
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Open access licenses
Open Access is by licensing the content with a Creative Commons (CC) license.
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.