Application of Generalized Regression Neural Network and Gaussian Process Regression for Modelling Hybrid Micro-Electric Discharge Machining: A Comparative Study

Micro-Electric Discharge Machining (μ-EDM) is one of the widely applied micromanufacturing processes. However, it has several limitations, such as a low cutting rate, difficult debris removal, and poor surface integrity, etc. Hybridization μ-EDM proposed an alternative to overcome process limitations. Conversely, complicates nature poses challenge for modelling predicting critical responses. Therefore, in this work, two distinct, nonparametric, previously unreported, workpiece material independent models using Generalized Regression Neural Network (GRNN) Gaussian Process (GPR) were developed compared assess their performance with limited training data. Various smoothing factors kernels tested GRNN GPR, respectively. The prediction was terms mean absolute percentage error, root square coefficient determination. results showed that GPR outperforms accurately predicts GRNN’s better less stochastic output discernible pattern than other outputs. Automatic Relevance Determination (ARD) squared exponential kernel found be best performing among those chosen. can used reasonable accuracy predetermine outputs they have R2 values above 0.90 both validation data all This work paves way future industrial implementation model predict complex hybrid machining