Abstract
Accurate energy consumption modeling is crucial for sustainable industrial energy optimization, helping reduce energy use effectively. This study introduces a green decision-making approach specifically tailored for orthogonal turn-milling machining by integrating a detailed energy consumption model with a robust multi-objective optimization algorithm, the nondominated sorting genetic algorithm II (NSGA-II). Energy consumption was determined based on material removal rate and specific energy, derived from key machining parameters such as workpiece speed, depth of cut, and axial feed rate. Surface roughness was also calculated from these parameters to ensure a comprehensive assessment. A central composite experimental design generated coefficients for both the energy consumption model and an Ra response surface model, achieving an impressive accuracy rate of 99.1%. Using NSGA-II, optimal parameters were identified for minimizing energy usage while maintaining a minimum acceptable Ra of 1.5 mu m: a workpiece speed of 20 rpm, a depth of cut of 2.93 mm, and a feed rate of 33.69 mm/min. This configuration yielded an energy use of 328.9 kJ and a machining time of 62 s. Experimental validation confirmed a Ra of 1.477 mu m, energy consumption of 328.4 kJ, and machining time of 62 s, with accuracy surpassing 98%.