Neural Computing for Determining the Accuracy of Ultimate Tensile Strength of Friction Stir Welded Joints by using Various Activation Functions
Journal Title: JOURNAL OF ADVANCED RESEARCH IN MECHANICAL ENGINEERING AND TECHNOLOGY - Year 2019, Vol 6, Issue 1
Abstract
Activation functions in a particular Artificial Neural Network (ANN) architecture plays a vital role. It imparts non-linear properties to our Neural Networks. There is a complicated and non-linear complex functional mapping between the inputs and response variable. In our present work, we have focussed on the accuracy of the UTS of the dissimilar Friction Stir Welded joints obtained by the training and testing the Artificial Neural Network architecture on Sigmoid activation function, Rectified Linear unit (ReLu) activation function and Hyperbolic tangent activation function. Tool Rotational Speed (rpm), Welding speed (mm/min) are the inputs and Ultimate Tensile Strength (MPa) is the output in our neural network architecture
Authors and Affiliations
Akshansh Mishra
Keywords
Related Articles
- EP ID EP669309
- DOI 10.24321/2454.8650.201905
- Views 138
- Downloads 0
Journal of Advanced Research in Mechanical Engineering and Technology
To support the making of a powerful India, an initiative titled “Make in India” was instituted in 2014 duly complimented by National Manufacturing policy. This paper reviews the various imperatives and challenges, along...
Modelling and Optimization of Metamaterial Antennas using Kernel Machine Approach
This research work is concerned with the application of Gaussian process regression kernel machine learning approach in modelling a metamaterial antenna. MATLAB Graphical user interface (GUI) was used to randomly select...
Importance, Novelty and Formulation of Indian Weathering Cycle
Weathering is the adverse response of a material or product to climate, often causing unwanted and premature product failure. The factors responsible for weathering are; solar radiation (light energy), temperature and wa...
Computational Analysis for Random Winglet Designs on Light Aircraft
This paper describes 3-dimensional wing-winglet analysis that was performed on random winglet designs on varying cross-sections of air foil. A total of four random wing-winglet pairs have been studied and their performan...
Elastoplastic Analysis of a Metallic Mast with Stiffeners, Experimentation and Numerical Simulation
This work entitled - Elastoplastic Analysis of a Metallic Mast with Stiffeners - is devoted to optimize the weight of masts. These masts are made of steel and have a conical geometry with constant thickness. The masts ar...