Integrating machine learning and mathematical programming for efficient optimization of electric discharge machining technique

Abstract

This study focuses on predictive modeling in machining, specifically material removal rate (MRR), tool wear rate (TWR), and surface roughness (Ra) prediction using regression analysis. The research employs electrical discharge machining (EDM) experiments to validate the proposed unified predictive model. The approach involves varying machining parameters systematically and collecting empirical data. The dataset is split for training and testing, and advanced regression techniques are used to formulate the model. Evaluation metrics such as R-squared and mean-squared error (MSE) are employed to assess the model’s accuracy. Notable findings include accurate predictions for MRR, TWR, and Ra. This approach demonstrates the potential for real-world application, aiding decision-making processes and enhancing machining efficiency. The research underscores the importance of predictive modeling in manufacturing optimization, offering insights into refining model architectures, data preprocessing techniques, and feature selection. The findings affirm the relevance and applicability of predictive modeling in manufacturing, emphasizing its potential to elevate precision and efficiency