Search

This paper investigates the tensile behaviors and self-healing of engineered cementitious composite (ECC) under sulfate wet–dry cycles to reflect the durability. Four pretensile strain levels of 0%, 1%, 1.5%, and 2% were designed. The uniaxial tensile test, three-point bending test, and single-crack tensile test were performed, along with the microscopic characterizations of scanning electron microscope (SEM) and X-ray diffraction (XRD). The results indicated that the sulfate wet–dry cycle exposure had a positive effect on the tensile strength and initial cracking strength of the uncracked ECC, while that was negative on the tensile strain capacity. The insufficient margin of the σoc/σcr and Jb′/Jtip indices explained the lower tensile strain. The tensile strength and initial cracking strength of the cracked ECC with 1% pretensile strain surpassed those of the uncracked ECC after undergoing 80 sulfate wet–dry cycles (80 C), while that did not hold for the other cracked ECCs. All the cracked ECCs showed a similar tensile strain after undergoing 80 C. The crack with a width of less than 100 μm achieved complete self-healing. The self-healing products of ECC under sulfate wet–dry cycle exposure may comprise of calcium (alumino) silicate hydrate [C-(A)-S-H] gel, calcite, ettringite, and gypsum. The current findings could offer reference points for applying ECC use in coastal regions. [ABSTRACT FROM AUTHOR]

Current development of high-performance fiber-reinforced cementitious composites (HPFRCC) mainly relies on intensive experiments. The main purpose of this study is to develop a machine learning method for effective and efficient discovery and development of HPFRCC. Specifically, this research develops machine learning models to predict the mechanical properties of HPFRCC through innovative incorporation of micromechanics, aiming to increase the prediction accuracy and generalization performance by enriching and improving the datasets through data cleaning, principal component analysis (PCA), and K-fold cross-validation. This study considers a total of 14 different mix design variables and predicts the ductility of HPFRCC for the first time, in addition to the compressive and tensile strengths. Different types of machine learning methods are investigated and compared, including artificial neural network (ANN), support vector regression (SVR), classification and regression tree (CART), and extreme gradient boosting tree (XGBoost). The results show that the developed machine learning models can reasonably predict the concerned mechanical properties and can be applied to perform parametric studies for the effects of different mix design variables on the mechanical properties. This study is expected to greatly promote efficient discovery and development of HPFRCC. [ABSTRACT FROM AUTHOR]