Impedance value prediction of carbon nanotube/polystyrene nanocomposites using tree-based machine learning models and the Taguchi technique

The impedance characteristics of multi-walled carbon nanotube (MWCNT)/polystyrene nanocomposites synthesized via microwave-assisted in-situ polymerization were systematically investigated to determine the effects of microwave power, exposure time, and frequency on impedance properties. The Taguchi method and analysis of variance (ANOVA) identified microwave power as the most significant factor, followed by exposure duration and frequency. A predictive model was developed, demonstrating high accuracy with a coefficient of determination (R2) of 0.96 between model predictions and experimental results. Additionally, response surface methodology (RSM) and contour plots were applied to explore optimal parameter combinations, offering valuable insights for achieving tailored impedance values. Machine learning model including Decision Tree, Random Forest, Extreme Gradient Boosting (XGBoost), Categorical Boost (CatBoost), and Light Gradient-Boosting Machine (LightGBM) were employed to enhance predictive capabilities. Among these, Random Forest and CatBoost demonstrated superior accuracy, achieving R2 values of 0.9880 and 0.9811 on testing data, respectively, while Decision Tree and LightGBM exhibited lower performance. This study highlights the potential of machine learning methods to precisely adjust and tailor impedance properties of PS/CNT nanocomposites, supporting the engineering of materials for diverse applications across materials science and engineering.