Clustering-Based Energy Modeling for Sustainable CNC Woodcutting Machinery

Energy efficiency in manufacturing is critical for achieving both economic and environmental sustainability. This study focuses on energy assessment and modelling for CNC woodcutting machine tools, comparing their behaviour to metal cutting machining centers. This work aims to provide a model for energy state identification and classification based on a data-driven approaches and focused on woodcutting machine tools. A novel, data-driven approach is proposed to classify the energy states of woodcutting machines using real-field sensor data. By integrating clustering methods and statistical techniques, the work develops an energy model tailored for woodcutting machinery. Validation through an industrial case study demonstrates the approach's effectiveness in enhancing user awareness and optimizing energy consumption. Future applications include anomaly detection, cross-machine benchmarking, and predictive modeling to further improve machine performance and sustainability.