ML-driven Computational Design of High-Performance Silicone Elastomer Coatings
In a recent paper, a group of researchers from North Dakota State University and Iowa State University presented an Artificial intelligence (AI) driven computational design strategy for high performance elastomeric coatings, specifically focusing on the compatibility of silicone elastomers modified with silicone oils.
The novel modeling framework integrates machine learning (ML), statistical thermodynamics, molecular dynamics simulation, and surface characterization techniques to gain deeper insights on the parameters governing the compatibility of the oil with the rubber. The work claims that the developed machine-learning model identified the key features that influence overall surface energy and miscibility behavior of silicone oil in a model PDMS matrix. In addition, COSMO-RS based computational simulation methods and high-resolution imaging techniques are employed to study the phase-separation behavior of silicone elastomers. Through this integrated framework, it was possible to gain molecular insights into the thermodynamic and kinetic attributes of silicone elastomers, which play a crucial role in determining the characteristics of the PDMS surface morphology. The findings can be used as a tool to relate the silicon oil and elastomer/rubber compatibility with elastomer’s performance and further as a guiding tool to enhance the performance of specific elastomers. Ultimately, this AI-driven computational approach provides a foundation for advanced design strategies of polymeric materials, including rubber.
Karuth A., Szwiec S., Casañola-Martín G.M., Khanam A., Safaripour M., Boucher D., Xia W., Webster D.C., Rasulev B. Integrated Machine Learning, Computational, and Experimental Investigation of Fouling Release Characteristics in Oil-Modified Silicone Elastomer Coatings, Progress in Organic Coatings, 193, 108526 (2024)
