• Corpus ID: 212560504

Artificial Neural Network Modeling For Material Removal Rate In Traveling Wire Electro-Chemical Spark Machining Process

@inproceedings{Charan2017ArtificialNN,
  title={Artificial Neural Network Modeling For Material Removal Rate In Traveling Wire Electro-Chemical Spark Machining Process},
  author={P M Charan},
  year={2017}
}

• P. M. Charan
• Published 2017
• Materials Science

Manufacturing Engineers are facing new challenges during machining of electrically nonconducting or partially conducting materials such as glass, quartz, ceramics and composites. Traveling Wire Electrochemical Spark Machining (TW-ECSM), a largely unknown technology, has been applied successfully for cutting, these types of electrically non-conducting or partially conducting materials. However, very few theoretical works have been reported related to machining performance of TW-ECSM process. This paper reports, an intelligent approach for the modelling of TW–ECSM process using Finite Element Method (FEM) and Artificial Neural Network (ANN) in integrated manner. First, a 3-D finite element transient thermal model has been developed for the determination of MRR during TW–ECSM process. Using results from the FEM simulation, a three layer Back Propagation (BP) neural network process model was developed to predict MRR. The BP neural network process model was found to accurately predict TW–ECSM process response for chosen process conditions.