Using neural networks to predict icephobic performance

TL;DR

This paper introduces neural network models to predict icephobic performance of concrete, enabling optimization of surface properties under freezing conditions with high accuracy.

Contribution

It presents the first neural network approach to model icephobicity, predicting surface ice adhesion and droplet rebound with high precision using experimental data.

Findings

Neural network models achieved R^2 of 0.92 and 0.96 for predicting COR and ice adhesion.

Models identified key factors influencing icephobicity through permutation importance.

The approach facilitates optimization of concrete surfaces for better icephobic performance.

Abstract

Icephobic surfaces inspired by superhydrophobic surfaces offer a passive solution to the problem of icing. However, modeling icephobicity is challenging because some material features that aid superhydrophobicity can adversely affect the icephobic performance. This study presents a new approach based on artificial neural networks to model icephobicity. Artificial neural network models were developed to predict the icephobic performance of concrete. The models were trained on experimental data to predict the surface ice adhesion strength and the coefficient of restitution (COR) of water droplet bouncing off the surface under freezing conditions. The material and coating compositions, and environmental condition were used as the models' input variables. A multilayer perceptron was trained to predict COR with a root mean squared error of 0.08, and a 90% confidence interval of [0.042, 0.151]. The model had a coefficient of determination of 0.92 after deployment. Since ice adhesion strength varied over a wide range of values for the samples, a mixture density network was model was developed to learn the underlying relationship in the multimodal data. Coefficient of determination for the model was 0.96. The relative importance of the input variables in icephobic performance were calculated using permutation importance. The developed models will be beneficial to optimize icephobicity of concrete.