Nesting and Scheduling in Additive Manufacturing: The Impact of Practical Nesting Strategies on Overall Makespan Efficiency

Abstract

In recent years, significant advancements in digital information management and new capabilities within Industry 4.0/5.0 systems have transformed production systems, enabling mass customisation as a new realistic paradigm. Additive manufacturing (AM), or 3D printing, represents a revolutionary approach by allowing the creation of highly personalised products without significantly increasing costs or production time. Efficient utilisation of AM resources requires effective production planning and management, particularly in scheduling production orders, which involves complex nesting logic due to the nonidentical nature of the pieces produced. This work aims to generate actionable knowledge for practitioners, enhancing their ability to understand and effectively tackle these challenges. To achieve this, various deterministic heuristics are proposed to solve the nesting/batching process, and their impact on the quality of final scheduling and computational time is analysed. Real datasets are used to evaluate these strategies, solving larger-sized problems than those previously addressed, to assess resolution capacity. This approach allows for practical rules (easily assimilable by practitioners) to be derived, which ultimately enhance the efficiency of AM systems. The results demonstrate that generating heterogeneous builds—distinct in average heights or volumes—not only improves makespan values by approximately 2%, but also, significantly accelerates the scheduling optimisation process. For the largest instances, computational time is reduced from over 1100 s to just 22 s, representing a remarkable 184% reduction. The underlying intuition for this drastic CPU time reduction is that heterogeneous builds benefit MILP solvers by tightening relaxed solutions; that is, fractional values for binary variables tend to align more closely with the final optimal values.