A new proposal for energy efficiency in industrial manufacturing systems based on machine learning techniques

Abstract

This research presents a novel methodology for enhancing energy efficiency in industrial manufacturing systems through machine learning techniques. Specifically, the study focuses on the automatic classification of five steel types — ABNT SAE 1020, 1045, 4140, 4340, and VC — based on electrical and mechanical characteristics observed during turning operations. The methodology includes the prediction of energy consumption for these steel types, applying regression models, under various machining conditions, including different rotation speeds and feed rates. To the best of the authors’ knowledge, this study is the first to address this issue using this specific approach. The proposed method was validated through computational experiments using multiple machine learning algorithms, with the Multilayer Perceptron (MLP) neural network achieving the highest classification accuracy of 95.52%. In terms of energy consumption prediction, MLP models demonstrated superior performance in 13 out of 15 turning scenarios. The regression analysis further confirmed the effectiveness of these models, achieving low Root Mean Squared Error (RMSE) values across different configurations. The results indicate that integrating machine learning into machining processes can significantly improve energy efficiency, leading to more sustainable industrial practices.