Greentelligent Scheduling for Energy-Efficient Aluminum Extrusion Casting: A Multi-Objective Optimization Approach

This study introduces a greentelligent scheduling approach to enhance energy efficiency in the aluminum extrusions casting workshop (ACW), addressing the high energy consumption and low efficiency inherent in these processes. Global energy consumption is significantly attributed to the manufacturing sector, with aluminum extrusions being one of the most common products, particularly in energy-intensive casting workshops. Given the considerable demand and potential for energy savings in aluminum extrusions manufacturing (AEM), this study proposes an intelligent scheduling approach to minimize non-processing energy consumption (NPE) while also reducing average completion time (ACT). Utilizing industrial internet of things (IIoT) technologies, practical production data is acquired to support a bi-objective scheduling model. An empirical knowledge-based evolution algorithm (EBA) with an improvement strategy (SO-EBA) is developed to efficiently solve this complex, NP-hard problem. A production case in an ACW demonstrates the effectiveness of the SO-EBA. Compared to benchmark algorithms, the SO-EBA achieves significant reductions in optimal NPE by more than 39.41%, while maintaining production efficiency. This work advances greentelligent manufacturing by integrating IIoT and intelligent algorithms, offering a scalable solution for sustainable production in energy-intensive industries.