The traditional trial-and-error method is expensive and time-consuming to determine the needling process parameters satisfying the stiffness requirements of the 3D needled composites. A new design method for these unknown needling process parameters is proposed using a convolutional neural network (CNN) surrogate model, in which a series of stress distribution images of representative volume cell (RVC) for 3D needled composites under different loads are implemented. These stress distribution images reserve both material stiffness and needling process information. The CNN surrogate model can be efficiently established to obtain the relationship between the stress distribution images and the needling process parameters. The accuracy of the training samples and the test samples in the CNN surrogate model reaches 93.85% and 87.50% respectively. An artificial RVC can be directly constructed corresponding to the stiffness properties. The unknown needling process parameters can be determined using the CNN surrogate model and the stress distribution images of the artificial RVC. The result shows the stiffness properties of 3D needled composites with the needling process parameters obtained by the CNN surrogate model are in good agreement with the experimental results, where the maximum relative error is 7.66%. This method provides a new way to design the needling process parameters satisfying the specific stiffness requirements of the 3D needled composites.
Water and chloride ions within pores of cementitious materials plays a crucial role in the damage processes of cement pastes, particularly in the binding material comprising calcium-silicate-hydrates (C-S-H). The migration mechanism of water and chloride ions restricted in C-S-H nanopores is complicated due to the presence of interfacial effects. The special mechanical properties of the solid–liquid interface determine the importance of boundary slip and Electric Double Layer (EDL) and ion diversity in pore solutions determines the difference of the EDL and the stability of water film slip. A cross-scale model covering slip effects, time-varying of EDL and ion correlation needs to be developed so that the interfacial effects concentrated at the pore scale can be extended to affect the overall diffusivity of C-S-H. The statistics of pore size distribution and fractal dimension were used to quantitatively compare the similarities between model and C-S-H structure, thus proving the reliability of cross-scale reconstructed C-S-H transmission model. The results show that the slip effect is the dominant factor affecting the diffusion ability of C-S-H, the contribution of the slip effect is up to 60% and the contribution rate of EDL time-varying only up to about 15%. Moreover, the slip effect is sensitive to both ion correlation and C-S-H inhomogeneity and EDL time-varying is almost insensitive to ion correlation changes. This quantification provides a necessary benchmark for understanding the destructiveness of cement-based materials in the salt rich environment and provides new insights into improving the durability of concrete by changing the solid–liquid interface on the micro-nanoscale.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.