Reverse engineering of additive manufactured composite part by toolpath reconstruction using imaging and machine learning

Development of composite material parts requires significant research and development effort. The fiber size, volume fraction and direction are important in determining the properties of the part. Additive manufacturing (AM) methods are increasingly used for printing composite materials. Advancements in 3D scanning and imaging technology have raised a significant concern in reverse engineering of parts made by AM, which may result in counterfeiting and unauthorized production of high quality parts. This work is focused on using imaging methods and machine learning to reverse engineer a composite material part, where not only the geometry is captured but also the tool path of 3D printing is reconstructed using machine learning of microstructure. A dimensional accuracy with only 0.33% difference is achieved for the reverse engineered model.