Quantum-Inspired Evolutionary Algorithms and Machine Learning for Minimizing Energy Consumption in Precision Machining

This study analyzes four techniques—Taguchi Method, Artificial Neural Network (ANN), Machine Learning (ML) Regression, and Quantum-Inspired Evolutionary Algorithm (QIEA)—to predict and optimize power consumption in machining. Using an L27 orthogonal array, experiments were conducted by varying Depth of Cut, Feed, and Speed. Taguchi provided a baseline, while ANN and ML captured nonlinear patterns. QIEA outperformed all with the lowest predicted power consumption (0.9599 kW). Its strength lies in exploring continuous variables and nonlinear interactions using quantum-inspired operators. The study confirms QIEA's superiority and supports integrating soft computing techniques for energy-efficient machining in advanced manufacturing systems.