(46c) Machine Learning-Based Prediction of Liquid Wettability of iCVD Polymers | AIChE

(46c) Machine Learning-Based Prediction of Liquid Wettability of iCVD Polymers

Authors 

Hunsberger, J. - Presenter, Drexel University
Soroush, M., Drexel University
Lau, K., Drexel University
Nguyen, T., Drexel University
Chen, Z., Drexel University
Initiated chemical vapor deposition (iCVD) is a reactive process that creates polymeric materials by adsorbing vapor phase monomers, which then polymerize on a surface via free-radical additive propagation. Although contiguous polymer thin films are usually formed, the iCVD process can sometimes lead to discrete micro- and nano-structures. For example, our iCVD synthesis of poly(perfluorodecyl acrylate) (PPFDA) has resulted in the growth of micro- and nano-worms, which tend to grow normal to the surface [1]. Due to the low surface energy of the fluorinated polymer and the heterogeneous worm-like surface, liquid wetting can be substantially reduced by entering the Cassie-Baxter state. The micro- and nano-structures of the worm-like features directly depend on iCVD operating conditions. They in turn influence bulk properties such as repellency of oils, like heptane. With the contact angle being dependent on iCVD operating conditions, it would be advantageous to create a model that captures the dependence.

Using conventional reaction rate equations and parameters, the reaction kinetics can be modeled with enough accuracy [2]. However, the mechanisms that determine the growth of the worm-like structures are currently not well understood. Given this currently-inadequate chemical and physical understanding, an alternative to first-principles modeling to relate product (polymer) properties such as contact angle to iCVD processing conditions is to use an empirical modeling approach such as neural networks. A typical neural network model can contain a number of fitting parameters, many times greater than the number of observations available to fit the model with. This relatively large number of fitting parameters provides a lot of flexibility for shaping the response surface of the target (output) variable(s).

In this work, we model the contact angle of heptane on PPFDA as a function of iCVD operating conditions using a neural network architecture. We then use the developed model to determine the optimal iCVD operating conditions that maximizes the heptane contact angle on the worm-like surface. To verify model predictions, we independently perform iCVD laboratory experiments with the model-predicted optimal operating conditions, perform microscopy to elucidate the polymer structure, and measure the resulting heptane contact angles.

References

  1. Lau, K.K.S.; Chen, Z.; Nguyen, T. Directed Vapor Deposition and Assembly of Polymer Micro- and Nanostructures. S. Patent Application 62941086; November 27, 2019.
  2. Lau, K.K.S. Growth Mechanism, Kinetics, and Molecular Weight. In CVD Polymers: Fabrication of Organic Surfaces and Devices (ed. Gleason, K.K.); Wiley 2015.