Predicting the material removal rate during electrical discharge diamond grinding using the Gaussian process regression: a comparison with the artificial neural network and response surface methodology

Abstract

Machine learning approaches can help facilitate the optimization of machining processes. Model performance, including accuracy, stability, and robustness, are major criteria to choose among different methods. Besides, the applicability, ease of implementations, and cost-effectiveness should be considered for industrial applications. In the current study, we present the Gaussian process regression model to predict the material removal rate during electrical discharge diamond surface grinding of Inconel-718. The model uses descriptors that include the wheel speed, current, pulse-on-time, and duty factor. The model is simple and manifests high accuracy and stability, which contributes to fast material removal rate estimations. By combining the optimization results from the Taguchi method and GPR approach, it is expected that more quantitative data can be extracted from fewer experimental trials at the same time.