摘要：In recent years,extensive research has focused on applying machine learning(ML)techniques to predict the properties of engineered cementitious composites(ECCs).ECCs exhibit crucial characteristics such as compressive strength(CS),tensile strength(TS),and tensile strain(TSt).Accurate forecasting of these critical properties can reduce material waste,lower construction expenses,and expedite project timelines for engineers and *** study investigates mixture design components and corresponding strengths of ECCs based on only polyethylene fiber drawing from existing *** neural network(ANN)models are developed to predict CS,TS,and TSt using a dataset of 339 experimental results with twelve input *** ANN models,implemented in MATLAB,consider various hidden layers and neurons to optimize accuracy and validation metrics demonstrate the model’s high *** analysis explores individual parameter *** inspiration from this study,it would be advantageous to enhance the predictive modeling toolkit by leveraging the progress made in existing technologies,thereby driving the green and low-carbon development of civil *** approach not only improves the efficiency and sustainability of construction practices but also aligns with global environmental goals by reducing the carbon footprint associated with civil engineering projects.