Filament Extraction for 3D Printing (2024-09)¶

The architecture, engineering, and construction (AEC) industry continuously evolves to meet the demand for sustainable and effective design and construction of the built environment. One of the primary techniques for large-scale additive manufacturing is extrusion. In extrusion, a digitally controlled nozzle is used for layer-by-layer material extrusion [1]. The continuous flow of concrete material that is extruded to create the printed structure is called filament or a layer. As these filaments are the essential structure for defining the printed object, quality control of the geometry of these structural elements is crucial. To extend our work for filament extraction in [2], in this paper, we introduce a method of geometry controlling filaments for concrete 3D printing technique. This paper presents an automated procedure to assess the filaments by providing a workflow to generate an automated image from a point cloud of the printed object that has been captured by either photogrammetry, structured light system (SLS) or terrestrial laser scanner (TLS), as shown in Fig. 1. Furthermore, filament geometry is controlled by using a deep learning model to segment the area between each filament from the generated images.