Optimized Graphene Coating Solutions for Enhanced Frost Prevention in Cryogenic Applications Using Machine Learning Algorithms

Authors- Surendiran k, Assistant Professor Dr. Nandhini. K

Abstract-The system is designed to provide an innovative solution for preventing frost formation in cryogenic tanks through a systematic and comprehensive workflow. The process begins with the admin managing registrations and approving access for teams involved in the development process. Upon approval, users receive login credentials via email, granting them access to the platform. The admin uploads critical requirements, including specifications for the cryogenic tank, which form the foundation for subsequent calculations and processes. The workflow proceeds with the calculation of surface area and the precise amount of graphene oxide required to create a frost-preventing coating. Using this data, the production process involves determining the appropriate quantities of water, reagents, and the necessary steps for graphene synthesis, ensuring high material quality and suitability for application. Once synthesized, the graphene is assessed for its coating properties, including thickness and durability, to optimize its performance in extreme cryogenic conditions. To enhance process efficiency, K-means Clustering is utilized to classify and group graphene oxide samples based on key properties such as particle size, surface characteristics, and coating uniformity. Additionally, a Generative Adversarial Network (GAN) is employed to simulate and predict the graphene coating’s behavior under various cryogenic conditions, allowing for performance optimization before real-world application.

DOI: /10.61463/ijset.vol.13.issue3.134