Data-driven probabilistic performance of Wire EDM: A machine learning based approach

Abstract

The wire electric discharge machining (WEDM) is a potential alternative over the conventional machining methods, in terms of accuracy and ease in producing intricate shapes. However, the WEDM process parameters are exposed to unavoidable and unknown sources of uncertainties, following their inevitable influence over the process performance features. Thus, in the present work, we quantified the role of parametric uncertainty on the performance of the WEDM process. To this end, we used the practically relevant noisy experimental dataset to construct the four different machine learning (ML) models (linear regression, regression trees, support vector machines, and Gaussian process regression) and compared their goodness of fit based on the corresponding R2 and RMSE values. We further validated the prediction capability of the tested models by performing the error analysis. The model with the highest computational efficiency among the tested models is then used to perform data-driven uncertainty quantification and sensitivity analysis. The findings of the present article suggest that the pulse on time ( Ton) and peak current (IP) are the most sensitive parameters that influence the performance measures of the WEDM process. In this way, the current study achieves two goals: first, it proposes a predictive framework for determining the performance features of WEDM for unknown design points, and second, it reports data-driven uncertainty analysis in the light of parametric perturbations. The observations reported in the present article provide comprehensive computational insights into the performance characteristics of the WEDM process.