Physics-Informed AI Framework for Waste Heat Recovery and Thermal Energy Optimization in Sustainable Laser Additive Manufacturing of Aerospace Components

Laser additive manufacturing has become an important technology for producing lightweight and high-performance aerospace components with complex geometries and reduced material waste. However, the process consumes a large amount of energy because of repeated laser scanning, rapid heating and cooling cycles, unstable melt pool behavior, and significant thermal losses during fabrication. A major portion of the supplied thermal energy is lost as waste heat, which reduces process efficiency, increases production cost, and affects sustainability. Most existing studies mainly focus on surface quality and mechanical performance, while waste heat recovery and thermal energy optimization remain largely unexplored. This study proposes a novel physics-informed artificial intelligence framework for waste heat recovery and thermal energy optimization in sustainable laser additive manufacturing of aerospace components. Unlike conventional data-driven models, the proposed approach combines machine learning with thermal physics, energy balance principles, and exergy analysis to improve prediction accuracy and physical reliability. Key process parameters such as laser power, scan speed, hatch spacing, and layer thickness are integrated with thermal descriptors including melt pool temperature, cooling rate, thermal gradients, and heat accumulation behavior. The developed framework predicts specific energy consumption, thermal efficiency, waste heat generation, and porosity sensitivity during the manufacturing process. A multi-objective optimization strategy is further applied to minimize energy loss while maintaining high part quality and process stability. The model also supports real-time process monitoring and digital twin-based decision-making for intelligent manufacturing environments. The proposed methodology offers a new direction for sustainable aerospace manufacturing by transforming thermal losses into process intelligence. This work contributes to greener production systems by improving energy efficiency, reducing carbon footprint, and enabling smarter control of advanced manufacturing processes.