# Determining Material Removal and Electrode Wear in Electric Discharge Machining with a Generalist Machine Learning Framework

## TL;DR

This paper introduces a machine learning framework to predict material removal and electrode wear in EDM, improving accuracy and reducing experimental costs.

## Contribution

A generalist ML framework using Random Forest and ANNs is proposed, achieving high predictive accuracy in EDM process modeling.

## Key findings

- Random Forest and ANNs outperformed other models with R2 values up to 0.9979 for EDM predictions.
- ANNs significantly reduced prediction errors for both Material Removal Rate and Electrode Wear Rate.
- The framework incorporates cryogenic electrode treatment levels and multiple process parameters for improved modeling.

## Abstract

Electric Discharge Machining (EDM) is a well-established process for fabricating complex geometries from hard materials. However, identifying the influence of process parameters remains challenging and costly due to the stochastic nature of EDM and the expense of experimental validation. Machine Learning (ML) techniques provide an alternative to mitigate these limitations by enabling predictive modeling with reduced experimental effort. This research proposes a generalizable framework employing four ML models to analyze the correlation between EDM inputs and outputs, incorporating 11 levels of cryogenic electrode treatment. Independent variables include electrode material, cryogenic conditions, pulse current, and pulse duration, while performance is assessed through Material Removal Rate (MRR) and Electrode Wear Rate (EWR). The results demonstrate that Random Forest (RF) and Artificial Neural Networks (ANNs) achieve superior predictive performance compared to alternative approaches, improving the R2 metric from 0.973 to 0.9956 for EWR in the case of an ANN and from 0.980 to 0.9943 for RF with MRR, compared with previous work in the literature and the best methods across 30 executions. Both models consistently yield high predictive accuracy, with R2 values ranging from 0.9936 to 0.9979 in training and testing datasets. Furthermore, ANN significantly reduces mean squared error, decreasing EWR prediction error from 5.79 to 0.68 and MRR error from 122.75 to 35.89. This research contributes to a deeper understanding of EDM process dynamics.