Abstract
Abstract
This paper investigate into the complex field of electrical discharge machining (EDM) to improve material removal rate (MRR), electrode wear rate (EWR), and surface roughness (SR) for the machining of Inconel 718, a difficult-to-machine superalloy. The effects of discharge current, pulse duration, and pulse interval on machining performance were assessed through experiments. Response surface methodology (RSM) and artificial neural network (ANN) models, such as RNN, LSTM, and CNN, were used to optimize. Twenty runs of confirmation experiments were used to confirm the optimal process parameters found by the created models for better machining. For Inconel 718, the novel Cu-Ni-B4C nanocomposite electrode greatly enhanced EDM performance. The ideal configuration increased MRR while decreasing wear and surface roughness. Machined surfaces were inspected using SEM and EDAX analysis. With optimal settings of 50 μs pulse duration and 90 μs pulse interval, increasing current to 8 Amps increased MRR to 0.0118 g min−1, reducing EWR to 0.001 g min−1 and SR to 3.108 μm. Compared to the RNN, LSTM, and RSM models, the CNN model had the greatest R-squared (R2) score of 0.9999, suggesting greater MRR, EWR, and SR prediction.