.png){kind=icon}
.png){kind=icon}
Return
A Multi-Granularity Random Mutation Genetic Algorithm for Steel Cold Rolling Scheduling Optimization
.png){kind=icon}
OA
AI
DOI：10.3390/pr13103311.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Cold rolling is the precision finishing stage in the steel production process, and its scheduling optimization is essential for enhancing production efficiency. To address the complex process constraints and objectives, this paper proposes a multi-granularity random mutation genetic algorithm (MGRM-GA) for cold rolling scheduling optimization. First, a multi-objective collaborative optimization model is established to integrate the production cost and process constraints. Then, high-quality initial solutions are generated based on greedy heuristic rules to fulfill the cold rolling constraints. Finally, four random mutation strategies are designed at different task granularities and unit levels to search diverse candidates. The standard flexible job shop scheduling problem (FJSP) datasets and practical cold rolling production data are studied to validate the feasibility and competitiveness of the MGRM-GA. Experimental results show that the MGRM-GA achieves a 94.2% improvement in objective function optimization, a 14.8-fold increase in throughput, and a 94.8% reduction in execution time on cold rolling data. Compared with the heuristic mutation algorithm, MGRM-GA increases population heterogeneity and avoids premature convergence, which enhances global search ability and scheduling performance.
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
No journal information available