Optimization of Nanofluid Thermal Conductivity Using AI: A Genetic Algorithm Approach

Abstract

Optimizing the thermal conductivity of nanofluids is essential for advanced heat transfer applications. This study explores an artificial intelligence-based approach, using genetic algorithms to optimize the nanoparticle volume frac- tion in nanofluids. Leveraging the modified Maxwell-Garnett model, this re- search incorporates the effects of Brownian motion as well as key physical parameters, such as material conductivity, particle size, and temperature. The genetic algorithm, implemented with the DEAP library, is specifically designed to fine-tune the parameters adaptively, using appropriate genetic operators like crossover, mutation, and selection