Microstructure-informed deep convolutional neural network for predicting short-term creep modulus of cement paste

This study aims to provide an efficient alternative for predicting creep modulus of cement paste based on Deep Convolutional Neural Network (DCNN). First, a microscale lattice model for short-term creep is adopted to build a database that contains 18,920 samples. Then, 3 DCNNs with different consecutive convolutional layers are built to learn...

Stress evolution in restrained GGBFS concrete due to autogenous deformation: bayesian optimization of aging creep

Stress evolution of restrained concrete is a significant direct index in early-age cracking (EAC) analysis of concrete. This study presents experiments and numerical modelling of the early-age stress evolution of Ground granulated blast furnace slag (GGBFS) concrete, considering the development of autogenous deformation and creep. Temperature...

Interpretable Ensemble-Machine-Learning models for predicting creep behavior of concrete

This study aims to provide an efficient and accurate machine learning (ML) approach for predicting the creep behavior of concrete. Three ensemble machine learning (EML) models are selected in this study: Random Forest (RF), Extreme Gradient Boosting Machine (XGBoost) and Light Gradient Boosting Machine (LGBM). Firstly, the creep data in...

Experimental investigation of the short-term creep recovery of hardened cement paste at micrometre length scale

This paper presents an experimental investigation on the short-term creep recovery of cement paste at micrometre length scale. Micro-cantilever beams were fabricated and tested with 8 different loading series using the nanoindenter. It is found that cement pastes show high recovery ratios (>80%) even subjected to very high stress levels....

Assessing strain rate sensitivity of cement paste at the micro-scale through micro-cantilever testing

This study presents an experimental investigation of the rate-dependent mechanical properties of cement paste at the microscale. With the use of a nanoindenter, micro-cantilever beams with the size of 300 μm × 300 μm × 1650 μm were loaded at five different strain rates from around 10⁻⁶/s to 10⁻²/s until failure. It is...

Micro-cantilever testing on the short-term creep behaviour of cement paste at micro-scale

This study proposes an experimental method for studying the short-term creep behaviour of cement paste at micro-scale. The micro-bending tests on miniaturized cantilever beams were used to characterize the viscoelastic properties of cement paste. The effects of w/b ratio, the type of binder and the stress level on the microscopic creep...