This study employs a lattice fracture model to simulate static and fatigue fracture behaviour of Interfacial Transition Zone (ITZ) at microscale and mortar at mesoscale. The heterogeneous microstructure of ITZ and mesostructure of mortar are explicitly considered in the models. The initial step involves calibrating and validating the microscopic model of the ITZ through micro-cantilever bending tests. Subsequently, this validated ITZ model serves as a constitutive law to simulate the fracture behavior of mortar at the mesoscale using an uncoupled upscaling method. The influence of microstructural features, such as w/c ratio and microscopic roughness, on the fracture behaviour of ITZ is investigated. Moreover, the effect of ITZ properties and stress level on the fracture performance and fatigue damage evolution of mortar is also studied. The simulation results for both the ITZ and mortar demonstrate good agreement with experimental results. The proposed two models provide insights into the fracture mechanisms and fatigue damage evolution in cementitious materials subjected to static and cyclic loadings.

This paper employs computer vision techniques to predict the micromechanical properties (i.e., elastic modulus and hardness) of cement paste based on an input of Backscattered Electron (BSE) images. A dataset comprising 40,000 nanoindentation tests and 40,000 BSE micrographs was built by express nanoindentation test and Scanning Electron Microscopy (SEM). A Residual Convolutional Neural Network (Res-Net) model, which differs from a typical Convolutional Neural Network (CNN) architecture by a shortcut connection, was employed and compared with a simple table model. The models were trained, tuned, and tested over a training, validation and testing set comprising 70%, 15% and 15% of the 40,000 data pairs, respectively. The following conclusions were drawn: 1) Express nanoindentation tests can provide reliable information for cement paste. Deconvolution based on Gaussian Mixture Model (GMM) can obtain almost invariant statistics for each phase; 2) Based on averaged greyscale values of each BSE image, a table model can predict the elastic modulus and hardness with R² of 0.80 and 0.83, respectively; 3) Based on the intensity of each pixel as well as their patterns in each BSE image, the Res-Net model can predict the elastic modulus and hardness with a R² of 0.85 and 0.88, respectively. Deconvolution of the Res-Net prediction obtains similar invariant statistics as derived by the nanoindentation tests, which gives strong evidence of the applicability of the Res-Net model.