Optimizing CNC Turning Process Parameters Through Machine Learning Modelling

Abstract

Mechanical and production industries grapple with escalating challenges towards sustainable practices in the age of smart manufacturing. Balancing production efficiency with quality is paramount and achievable through parametric optimization. This work focus on CNC turning data to build the machine learning (ML) model. Polynomial Regression, Support Vector and Random Forest methods are applied and the best fit method is used to develop the model which is used to optimize the variables using Teaching and Learning Based Optimization (TLBO) algorithm. The outcome of this work provides tailor-made solutions to enhance the productivity as well as quality and useful in industries.