Applying Machine Learning to Nanoindentation Data of (Nano-) Enhanced Composites

Abstract

Carbon fiber reinforced polymers (CFRPs) are continuously gaining attention in aerospace and space applications, and especially their multi-scale reinforcement with nanoadditives. Carbon nanotubes (CNTs), graphene, carbon nanofibers (CNFs), and their functionalized forms are often incorporated into interactive systems to engage specific changes in the environment of application to a smart response. Structural integrity of these nanoscale reinforced composites is assessed with advanced characterization techniques, with the most prominent being nanoindentation testing. Nanoindentation is a well-established technique, which enables quantitative mapping of nanomechanical properties with the µm surficial and nm indentation resolution scale and high precision characterization. This feature enables the characterization of the interface in a statistical and quantitative manner and the correlation of (nano-) reinforcement to interface properties of CFRPs. Identification of reinforcement is performed with k-Nearest Neighbors and Support Vector Machine classification algorithms. Expertise is necessary to describe the physical problem and create representative training/testing datasets. Development of open source Machine Learning algorithms can have an influential impact on uniformity of nanometry data creation and management. The statistical character of nanoindentation is a key factor to supply information on heterogeneity of multiscale reinforced composites. Both the identification of (nano-) reinforcement and quality assessment of composites are provided by involving artificial intelligence.

Testing Novel Portland Cement Formulations with Carbon Nanotubes and Intrinsic Properties Revelation: Nanoindentation Analysis with Machine Learning on Microstructure Identification

“…However, the model performance was not adequate even after tuning of hyperparameters, especially for the high-stiffness phases identification, reaching a minimum F1 score of 0.18 (Figure 10e). This result could be possibly correlated to the low population of data for these cement phases and imbalance in the population amongst cement microstructure classes [53]. On the other hand, all other algorithms (RF and Radial, Gaussian, and ANOVA SVC kernel types) after being properly tuned were able to use all seven variables to correctly classify nanoindentation events to Portland Cement phases.…”

“…In order to evaluate the prediction efficiency of the trained models, statistical metrics are involved. Accuracy, Precision, Recall, F1 were exported in each case [4,[51][52][53], after tuning each model to the optimum in regard to accuracy by performing grid parameterization. Accuracy accounts for overall model accuracy.…”

Carbon Fiber Reinforced Composites: Study of Modification Effect on Weathering-Induced Ageing via Nanoindentation and Deep Learning

“…Carbon-Fiber (CFs)-reinforced Polymers (CFRPs) are on the peak of their development, and are expected to be utilized massively in aerospace, automotive, and construction markets as substitutes to metal compartments [1][2][3][4][5][6][7][8][9][10]. Their advantages over other end-use materials are their low specific density and mechanical robustness, which have been highly valued by the research community [2,3,5,7].…”

Study of Nano-Mechanical Performance of Pretreated Natural Fiber in LDPE Composite for Packaging Applications

“…Nanoindentation is the most powerful and useful technique to analyze the nano-mechanical properties of biocomposites [3]. A nanoindenter provides quantitative data, which is the good source of information related to matrix and reinforcement materials in the biocomposites [20]. This technique has been extensively used for analyzing the mechanical properties of polymers [7].…”