Abstract

Data analysis is divided into two categories i.e. classification and prediction. These two categories can be used for extraction of models from the dataset and further determine future data trends or important set of classes available in the dataset. The aim of the present work is to determine location of the fracture failure in dissimilar friction stir welded joint by using various machine learning classification models such as Decision Tree, Support Vector Machine (SVM), Random Forest, Naïve Bayes and Artificial Neural Network (ANN). It is observed that out of these classification algorithms, Artificial Neural Network results have the best accuracy score of

Abstract

Image processing algorithms are finding various applications in manufacturing and materials industries such as identification of cracks in the fabricated samples, calculating the geometrical properties of the given microstructure, presence of surface defects, etc. The present work deals with the application of Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm for improving the quality of the microstructure images of the Friction Stir Welded joints. The obtained results showed that the obtained value of quantitative metric features such as Entropy value and RMS Contrast value were high which resulted in enhanced microstructure images.

Abstract

The composition of High Entropy Alloys is quite different from the existing classical engineering alloys because in near equiatomic ratios they contain multiple principal alloying elements. Design and development of high entropy alloys is very important to overcome the shortcomings of conventionally used alloys in applications where operating conditions of temperature and loading are extreme. High entropy alloys generally find applications in compressor blades of an aerospace engine, energy, and transportation industries due to its low density and high strength. In order to enhance the application of high entropy alloys, the proper selection of a feasible welding process is very important. It has been observed that when high entropy alloys are subjected to the welding process other than the Friction Stir Welding process then it will result in reduced overall strength and lower hardness in the fusion zone and heat-affected zone. In this recent paper, the application of Friction Stir Welding for joining the high entropy alloys and also using Friction Stir Processing for improving the mechanical and microstructure properties of high entropy alloys are discussed.

Abstract

In modern computational science, the interplay existing between machine learning and optimization process marks the most vital developments. Optimization plays an important role in mechanical industries because it leads to reduce in material cost, time consumption and increase in production rate. The recent work focuses on performing the optimization task on Friction Stir Welding process for obtaining the maximum Ultimate Tensile Strength (UTS) of the friction stir welded joints. Two machine learning algorithms i.e. Artificial Neural Network (ANN) and Decision Trees regression model are selected for the purpose. The input variables are Tool Rotational Speed (RPM), Tool Traverse Speed (mm/min) and Axial Force (KN) while the output variable is Ultimate Tensile Strength (MPa). It is observed that in case of the Artificial Neural Networks the Root Mean Square Errors for training and testing sets are 0.842 and 0.808 respectively while in case of Decision Trees regression model, the training and testing sets result Root Mean Square Errors of 11.72 and 14.61. So, it can be concluded that ANN algorithm gives better and accurate result than Decision Tree regression algorithm.