Moisture Content Prediction in Polymer Composites Using Machine Learning Techniques

Abstract

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.