An artifactual fibre overlap removal algorithm for micro-computed tomography image post-processing and 3D microstructure generation with graphics processing unit acceleration

A novel algorithm based on radial basis functions is proposed for the removal of artifactual fibre overlap within fibre structures extracted from micro-computed tomography (micro-CT) images of fibre reinforced polymer matrix composites. The proposed algorithm is highly efficient and excels in preserving the original fibre structures extracted from the micro-CT images. Besides, graphics processing unit (GPU) acceleration is applied to further enhance the efficiency of the fibre overlap removal process. Furthermore, the proposed algorithm is also modified for the generation of periodic 3D microstructures. For practical application, the proposed algorithm is implemented for both the artifactual fibre overlap removal within micro-CT images from an injection moulded part and the microstructure generation for 3D printed samples. The unidirectional elastic modulus of the resultant microstructures is computed via numerical simulations and shows a close match to the experimental measurements with relative errors less than 2%. Overall, the proposed algorithm significantly facilitates the reconstruction of micro-CT image-based numerical models and can also be easily repurposed to generate complex microstructures, which is of great value for the development of data-driven models for characterization and design of composite materials that demands large amounts of data on material microstructures. • An algorithm for the efficient removal of artifactual fibre overlap within fibre structures extracted from micro-CT images. • The proposed algorithm introduces minimal distortion to the original fibre structures from micro-CT images. • The proposed algorithm is also adapted to generate periodical 3D microstructures that contain both fibres and voids. • Runtime of the proposed algorithm is further reduced via parallelization and graphics processing unit computing. • The practical application of the proposed algorithm is demonstrated through two case studies with validated results.