Data Mining and Knowledge Discovery in Materials Science and Engineering: A Polymer Nanocomposites Case Study
AbuOmar, O., Nouranian, S., King, R., Bouvard, J.-L., Toghiani, H., Lacy, T., & Pittman, C. (2013). Data Mining and Knowledge Discovery in Materials Science and Engineering: A Polymer Nanocomposites Case Study. Advanced Engineering Informatics. 27(4), 615–624. DOI:10.1016/j.aei.2013.08.002.
In this study, data mining and knowledge discovery techniques were employed to validate their efficacy in acquiring information about the viscoelastic properties of vapor-grown carbon nanofiber (VGCNF)/vinyl ester (VE) nanocomposites solely from data derived from a designed experimental study. Formulation and processing factors (VGCNF type, use of a dispersing agent, mixing method, and VGCNF weight fraction) and testing temperature were utilized as inputs and the 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 has the most significant effect on the output responses followed by VGCNF weight fraction. SOMs also showed how to prepare different VGCNF/VE nanocomposites with the same storage and loss modulus responses. Clustering techniques, such as fuzzy C-means, were also applied to discover certain patterns in specimens’ physical behavior. Particularly, these techniques were able to separate the anocomposite specimens into different clusters based on temperature and tan delta features as well as to place the neat VE specimens (i.e. VGCNF specimens treated at 0.00 parts per hundred(phr)) in separate clusters. Most importantly, the results from data mining are consistent with previous response surface characterizations of this nanocomposite systems’s behavior.