Carbon fibre detection in polymer composites reinforced by chopped carbon fibres through digital image processing and machine learning

Abstract

Mechanical and thermodynamical properties and thus machinability of carbon fibre reinforced polymer composites significantly depend on the fibre orientation relative to the load direction. However, the orientations of the fibre groups in polymer composites reinforced by chopped carbon fibres are stochastic; therefore, the properties and machinability of such composites are challenging to plan, predict and optimise. We developed four different and novel approaches for fibre detection in polymer composites reinforced by chopped carbon fibres: (i) detecting the fibres through naked eye supported manual drawing, (ii) digital image processing of optical images, (iii) machine learning-based fibre detection, and (iv) rectangle fitting on the outputs of the automated processes using the Chaudhuri and Samal method. The applicability of the novel approaches was tested through optically captured images of polymer composites reinforced by chopped carbon fibres. The developed methods are each capable of detecting fibre groups at the top and bottom of the composite plate with certain limitations. The rectangle fitting approaches performed the best from the point of view of correctly identifying of fibre groups, followed by the machine learning-based and the conventional digital image processed, respectively. As a result of this study, the machining process planning and condition monitoring of polymer composites reinforced by chopped carbon fibres is more deeply supported.