Measuring the mechanical properties of polymer–carbon nanotube composites by artificial intelligence

Abstract

Polymer-Carbon nanotube composites (PCNCs) are a new class of composite materials, which is receiving significant attention both in academia and industry. In this paper, the application of Artificial Intelligence (AI) to the measurement of the elastic modulus of PCNCs was investigated. This is the first time that an AI-based modeling algorithm is used as an alternative tool for nano-indentation methods such as depth-sensing indentation (DSI). To build the model, 138 pair input-target data were gathered from the literature, randomly divided into 88 and 50 data sets and then were respectively trained and tested by the proposed AI model. In the set of the models, matrix type, nanofiller type, processing method, nanofiller content and method of analysis were introduced to the AI model as input layers, while the elastic modulus (either quasi-static E or dynamic [Formula: see text]) is used as output parameter. Although the modeling process is done with a nanometer sensitivity, the training and testing set results of the explicit formulations obtained by the AI model showed that artificial intelligent methods have strong potential and can be applied for the measurement of the elastic modulus of PCNCs as a non-destructive testing.