A Hybrid Regression and Machine Learning-Based Multi-Output Predictive Modeling of Cutting Forces and Surface Roughness in Rotational Turning of C45 Steel
Evaluates hybrid regression and machine learning to predict cutting forces and surface roughness in rotational turning, highlighting its significance for manufacturing.
Key Points
The study aims to develop a predictive model for cutting forces and surface roughness in rotational turning of C45 steel using hybrid regression and machine learning.
Applied hybrid regression and machine learning approaches for multi-output prediction.
Compared stepwise polynomial regression, Gaussian Process Regression, and Random Forest regression.
Utilized repeated five-fold cross-validation for model evaluation.
Focused on input variables: tool inclination angle, depth of cut, feed, and cutting speed.
Gaussian Process Regression achieved the highest predictive accuracy for axial and radial forces and surface roughness.
Stepwise regression provided comparable results for tangential force with better interpretability.
Random Forest regression showed lower accuracy in this experimental setup.
The combined approach enhances predictive modeling in rotational turning.