Application of machine learning to predict the multiaxial strain-sensing response of CNT-polymer composites. (May 2019)

• Record Type: Journal Article
• Authors: Matos, Miguel A.S.; Pinho, Silvestre T.; Tagarielli, Vito L.
• Is Part Of: Carbon. Volume 146(2019)
• Page Start: 265
• Page End: 275
• Publication Date: 2019-05
• Subjects: Carbon -- Periodicals; Carbone -- Périodiques; Koolstof; Toepassingen; Electronic journals; 546.681
• DOI: 10.1016/j.carbon.2019.02.001
• Languages: English
• ISSNs: 0008-6223

Abstract

Abstract: We present predictive multiscale models of the multiaxial strain-sensing response of conductive CNT-polymer composites. Detailed physically-based finite element (FE) models at the micron scale are used to produce training data for an artificial neural network; the latter is then used, at macroscopic scale, to predict the electro-mechanical response of components of arbitrary shape subject to a non-uniform, multiaxial strain field, allowing savings in computational time of six orders of magnitude. We apply this methodology to explore the application of CNT-polymer composites to the construction of different types of sensors and to damage detection. Graphical abstract: Image 1