K-Means Clustering Algorithm–Based Energy Profiling of Milling Machines: Status Based Optimization of Energy

ABSTRACT The optimization of energy consumption is an emerging topic in the manufacturing sector because it is the first and most likely step for the transition toward a greener manufacturing strategy. The present study focuses on monitoring and optimizing the energy consumption of milling machines, which are essential tools in modern manufacturing and are used by many manufacturing companies but which also consume a large amount of energy and generate significant environmental impacts. This study presents a step-by-step methodology for energy profiling of milling machines using vector-quantization–based unsupervised machine learning. The process includes long-term power monitoring, preprocessing with peak shaving, clustering into machine states using K-means, and subsystem-level analysis. Data were collected from a PAMA Speedram 2000 milling machine, and the approach demonstrated its ability to differentiate between operational states and identify energy optimization opportunities. Results show that adjusting auxiliary system duty cycles based on machine states can reduce total energy use by more than 50 % in some scenarios. Our findings indicate that specific operational modes exhibit distinct energy-consumption characteristics, which can be leveraged to enhance the efficiency of milling operations. A scenario that implements some solutions to develop a greener milling process is presented based on the partial use of the most energy-demanding auxiliary systems.