<![CDATA[Manufacturing accounts for about 28.9% of global final energy use, making inefficient operations a major source of cost and greenhouse gas emissions. This review synthesizes how artificial intelligence supports energy optimization within Industry 4.0-enabled manufacturing systems. It organizes methods into four families: machine learning for forecasting and anomaly detection, deep learning for nonlinear and temporal modelling, reinforcement learning for adaptive scheduling and real-time control, and metaheuristics for balancing energy, throughput, and quality objectives. Applications span plant-level demand prediction and peak management, shop-floor rescheduling under dynamic pricing, equipment-level optimization through predictive maintenance, and system-wide planning using digital twins and cyber-physical integration. Reported benefits include lower energy costs, reduced downtime, improved productivity, and progress toward decarbonization. However, large-scale deployment is constrained by poor data quality and interoperability across IIoT, MES, ERP, and EMS platforms, high implementation and computational costs, skills gaps, and weak governance and benchmarking standards. Emerging solutions include federated learning and edge AI for privacy-preserving, low-latency analytics, explainable AI to enhance trust and auditability, tighter smart-grid integration, and circular economy-driven optimization. The review concludes with practical priorities for reliable, transparent, and scalable AI-enabled energy management.]]>
