Predicting the compressive strength of carbon-enhanced cementitious composites using two-dimensional convolutional neural networks

This study addresses the limitations of traditional statistical methods and artificial neural networks (ANNs) in extracting relevant features from carbon-based cementitious composites to assess their dynamic behaviors under various environmental conditions. However, previous deep-learning methods were limited in making efficient predictions utilizing multiple factors. These shortcomings are not appropriate for predicting the properties of cement composed of various elements. In this study, these elements were converted into image form to handle efficiently the multiple factors that consist of cement, and the prediction was performed using a convolutional neural network (CNN)-based model. The concentration range of multiwalled carbon nanotubes (MWCNTs) used was 0.25 wt% to 1.0 wt%. Additionally, the specimens utilized were 50×50×50mm3 in size, and a total of 532 pieces of data were employed. Based on mean absolute error (MAE), performance was improved by approximately 25% with ANN (MAE = 3.89) and 7.2% with random forest (MAE = 3.14) compared with the proposed model (MAE = 2.92). The findings of this study are a novel and practical approach for predicting the mechanical properties of cementitious composites, enabling reverse application to optimize mixing ratios for CNT cement composites, and streamlining fabrication.