Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Modeling of Magnetic Assisted EDM of EN24 Steel Using Artificial Neural Network


Affiliations
1 Veermata Jijabai Technological Institute, Mumbai, Maharashtra, India
2 Walchand College of Engineering, Sangli, Maharashtra, India
     

   Subscribe/Renew Journal


EDM is a non-conventional method of electro-thermal machining process where electrical energy produces electrical sparks. To learn the performance of the process parameter on the response variable, the experiment was carried out on EN-24 steel with a copper electrode. For analysis, process parameters like current, pulse on time, voltage are considered. The Matlab ANN Toolbox is used for modeling purpose. ANN Model is developed with Traingdx, Learngdx, MSE, Logsig as training, learning, performance, and transfer functions, using a Feed-forward back-propagation as an algorithm with three nodes in the input layer and one node in the output layer for material removal rate (MRR), electrode wear rate (EWR), surface roughness (SR), using various nodes in hidden layers. Eight networks are tried 3-1-3, 3-3-3, 3-6-3, 3-7-3, 3-1-3, 3-3-3-3-3, 3-6-6-3 and 3-7-7-3 structure. To predict the value of the response variable, a 3-7-3 network structure is found as best fit for the proposed model.

Keywords

Artificial Neural Network, Electro Discharge Machining, Material Removal Rate, Electrode Wear Rate, Surface Roughness.
User
Subscription Login to verify subscription
Notifications
Font Size


  • Modeling of Magnetic Assisted EDM of EN24 Steel Using Artificial Neural Network

Abstract Views: 382  |  PDF Views: 1

Authors

Utkarsha U. Dabade
Veermata Jijabai Technological Institute, Mumbai, Maharashtra, India
Prajakta R. Nalawade
Walchand College of Engineering, Sangli, Maharashtra, India
Amar S. Bhandare
Walchand College of Engineering, Sangli, Maharashtra, India

Abstract


EDM is a non-conventional method of electro-thermal machining process where electrical energy produces electrical sparks. To learn the performance of the process parameter on the response variable, the experiment was carried out on EN-24 steel with a copper electrode. For analysis, process parameters like current, pulse on time, voltage are considered. The Matlab ANN Toolbox is used for modeling purpose. ANN Model is developed with Traingdx, Learngdx, MSE, Logsig as training, learning, performance, and transfer functions, using a Feed-forward back-propagation as an algorithm with three nodes in the input layer and one node in the output layer for material removal rate (MRR), electrode wear rate (EWR), surface roughness (SR), using various nodes in hidden layers. Eight networks are tried 3-1-3, 3-3-3, 3-6-3, 3-7-3, 3-1-3, 3-3-3-3-3, 3-6-6-3 and 3-7-7-3 structure. To predict the value of the response variable, a 3-7-3 network structure is found as best fit for the proposed model.

Keywords


Artificial Neural Network, Electro Discharge Machining, Material Removal Rate, Electrode Wear Rate, Surface Roughness.

References