Integrated Nesting and Scheduling for SLA 3D Printing: A Pixel-Based Evolutionary Algorithm With Convolutional Acceleration

Additive manufacturing (AM) constructs complex products through the layer-by-layer deposition of materials. AM enables complex geometry fabrication but faces spatiotemporal optimization challenges: maximizing space utilization and minimizing printing time, requiring intelligent nesting of products and scheduling of resources. The integration of nesting and scheduling further expands the solution space, but existing methods frequently overlook essential geometric intricacies in irregular products. This paper proposes a novel pixel-based grey wolf optimizer algorithm (PGWO) to improve packing density and reduce time cost in stereolithography (SLA) printing. In the proposed PGWO, point-cloud pixelization is employed to simplify 3D irregular parts. Each part independently performs autonomous orientation to minimize local space occupancy at a low cost. Based on the time-frequency domain conversion, a convolutionally accelerated localization strategy (Cals) is proposed to improve the speed of nesting. For efficient scheduling, a bottleneck-balanced local search phase is designed with two operators. By targeting critical bottlenecks in printing, two operators can effectively reduce the frequency of layer changes, further optimizing local optimal solutions. PGWO is evaluated on 70 instances with diverse scales, and shows significant superiority over other state-of-the-art methods in over 88% of instances. The results demonstrate its superior performance in reducing printing time and enhancing packing density. Note to Practitioners—This work is motivated by the challenge of optimizing additive manufacturing (AM) for irregularly shaped parts, particularly in industries requiring high customization like aerospace and medical devices. While AM enables efficient production of complex geometries, existing methods struggle to simultaneously optimize spatial arrangement (nesting) and temporal scheduling, leading to inefficient material usage and prolonged printing time, which are critical barriers in automation science. Current research often simplifies irregular geometries or decouple nesting from scheduling, sacrificing either precision or efficiency. This paper proposes an evolutionary algorithm to achieve speed-fidelity balancing abstraction of 3D irregular parts and high-quality generation of scheduling solutions. The experimental results demonstrate superior performance in packing density and time reduction compared to conventional methods. For practitioners, this approach enables automated, resource-efficient additive manufacturing that reduce material waste and shorten production cycles, which are critical factors for scaling customized manufacturing. Current limitations include computational overhead for ultra-high-resolution parts, which could be mitigated through GPU parallelization in future implementations. In the future, this framework could be extended to advanced AM technologies such as multi-material printing or multi-machine collaboration, where efficient spatial-temporal optimization is essential.