An evolutional algorithm for automatic 2D layer segmentation in laser-aided additive manufacturing

Abstract

Path planning is an important task in laser aided additive manufacturing (LAAM). The sliced 2D layers usually need to be partitioned into sub-regions such that appropriate filling toolpaths can be designed for different sub-regions. However, reported approaches for 2D layer segmentation generally require manual interaction that is tedious and time-consuming. To increase segmentation efficiency, this paper proposes an autonomous approach based on evolutional computation for 2D layer segmentation. The algorithm works in an identify-and-segment manner. Specifically, the largest quasi-quadrilateral is identified and segmented from the target layer iteration by iteration. Results from case studies have validated the effectiveness and efficacy of the developed algorithm. To further improve its performance, a roughing-finishing strategy is proposed. Via multi-processing, the strategy can remarkably increase the solution variety without significant sacrifice of solution quality and search time, thus providing great application potential in LAAM path planning. The developed segmentation algorithm has also been experimentally validated by comparing with the benchmarking toolpath generated by Powermill. With the developed segmentation algorithm, the quality of the deposited samples could be significantly improved. To the best of the authors’ knowledge, this work is the first to address automatic 2D layer segmentation problem in LAAM process. Therefore, it can be a valuable supplement to the state of the art in this area.