On Materials Informatics and Knowledge Discovery: Mechanical Characterization of Vapor-grown Carbon Nanofiber/ Vinyl Ester Nanocomposites

In this study, data mining and knowledge discovery techniques were employed to acquire new information about the viscoelastic, flexural, compression, and tension properties for vapor-grown carbon nanofiber (VGCNF)/vinyl ester (VE) nanocomposites. These properties were used to design a unified VGCNF/VE framework solely from data derived from a designed experimental study. Formulation and processing factors (curing environment, use or absence of dispersing agent, mixing method, VGCNF fiber loading, VGCNF type, high shear mixing time, sonication time) and testing temperature were utilized as inputs and the true ultimate strength, true yield strength, engineering elastic modulus, engineering ultimate strength, flexural modulus, flexural strength, storage modulus, loss modulus, and tan delta were selected as outputs. The data mining and knowledge discovery algorithms and techniques included self-organizing maps (SOMs) and clustering techniques. SOMs demonstrated that temperature (particularly 30C) and tan delta had the most significant effects on the output responses followed by VGCNF high shear mixing time and sonication time. SOMs also showed how to produce optimal responses using a certain combination(s) of inputs. A clustering technique, i.e., fuzzy C-means algorithm (FCM), was also applied to discover certain patterns in nanocomposite behavior after using principal component analysis as a dimensionality reduction technique. Particularly, these techniques were able to separate the nanocomposite specimens into different clusters based on temperature (where 30C and 120C are the most dominant), tan delta, high shear mixing time, and sonication time features as well as to place the viscoelastic VGCNF/VE specimens that have the same storage and loss moduli and tested at the same temperature in separate clusters. FCM results also showed that all nanocomposites structures in the new framework are essential but the viscoelastic VGCNF/VE data is the most important. Most importantly, this work highlights the significance and utility of data mining and knowledge discovery techniques in the context of materials informatics by discovering certain patterns and trends that have not been known before.