Deep learning approach for optimizing material removal rate in wire electrical discharge machining using neural networks

This research focuses on optimizing the Material Removal Rate (MRR) in Wire Electrical Discharge Machining (Wire EDM) using deep learning techniques. The study identifies existing challenges in predicting MRR due to complex, non-linear relationships between process parameters. By adopting a systematic design of experiments, a dataset was generated to evaluate the impact of pulse on time, pulse off time, current, voltage, and wire feed rate on MRR. A neural network model was developed and trained with different activation functions, with the Sigmoid function yielding the best performance metrics, including an R-square of 0.9999 and a Mean Squared Error (MSE) of 0.0004. This work demonstrates the potential of artificial intelligence to enhance machining processes, providing valuable insights for industrial applications and paving the way for future research in advanced manufacturing technologies.