RA-ECDM of Silicon Wafers Using Taguchi’s Methodology and Machine Learning Algorithms

As a prominent machining process, electrochemical discharge machining (ECDM) is used to process materials that are both fragile and difficult to cut. The growing use of this method for the machining of hard to cut materials has paved the way for the discovery of unexploited potential in machining outcomes. In the current study, silicon wafers were machined by rotary assisted electrochemical discharge machining using Taguchi`s L27 orthogonal array, having output process characteristics such as overcut and hole circularity. The optimization through Taguchi’s methodology shows that the overcut and circularity of holes improved by 1.40% and 2.44% by using optimal parametric combination as compared to orthogonal array. All output process parameters were again analysed through a machine learning algorithm by determining their root mean squared error (RMSE), R-Squared, mean squared error (MSE), mean absolute error (MAE), prediction speed, and training time. The obtained results show that in regression models of the Gaussian process, overcut and circularity of hole are well predicted by both the exponential and squared exponential regression models. The overcut and circularity of hole models had R-squared values of 0.92 and 0.90, respectively.