Moisture Content Prediction in Polymer Composites Using Machine Learning Techniques.

The principal objective of this study is to employ non-destructive broadband dielectric spectroscopy/impedance spectroscopy and machine learning techniques to estimate the moisture content in FRP composites under hygrothermal aging. Here, classification and regression machine learning models that can accurately predict the current moisture saturation state are developed using the frequency domain dielectric response of the composite, in conjunction with the time domain hygrothermal aging effect. First, to categorize the composites based on the present state of the absorbed moisture supervised classification learning models (i.e., quadratic discriminant analysis (QDA), support vector machine (SVM), and artificial neural network-based multilayer perceptron (MLP) classifier) have been developed. Later, to accurately estimate the relative moisture absorption from the dielectric data, supervised regression models (i.e., multiple linear regression (MLR), decision tree regression (DTR), and multi-layer perceptron (MLP) regression) have been developed, which can effectively estimate the relative moisture absorption from the dielectric response of the material with an R¬2 value greater than 0.95. The physics behind the hygrothermal aging of the composites has then been interpreted by comparing the model attributes to see which characteristics most strongly influence the predictions.

Smart Self-Sensing Composite: Piezoelectric and Magnetostrictive FEA Modeling and Experimental Characterization Using Wireless Detection Systems.

This research work focuses on the development of a piezoelectric magnetostrictive smart composite with advanced sensing capability. The composite piezoelectric property is achieved from the dispersion of single-walled carbon nanotubes (SWCNTs) and the magnetostrictive property from Terfenol-D nanoparticles. Finite element analysis (FEA) is used to examine the feasibility of modelling the piezoelectric (change in electric field) and magnetostrictive (change in magnetic field) self-sensing responses in the presence of applied stress. The numerical work was coupled with a series of mechanical tests to characterize the piezoelectric response, magnetostriction response and mechanical strength. Tensile tests of the composite samples manufactured as is (virgin), samples with SWCNTs, samples with Terfenol-D nanoparticles and samples with both SWCNTs and Terfenol-D nanoparticles were conducted. It was observed that an increase in volume fraction of Terfenol-d nanoparticles increases the change in magnetization, therefore increasing voltage response up to the point of saturation. The optimum change in amplitude was observed with 0.35% volume fraction of Terfenol-D nanoparticles. A constant ratio of SWCNTs was maintained, and maximum change in electrical resistance was at 7.4%. Fracture toughness for the samples with all nanoparticles was explored, and the results showed improved resistance to crack propagation.