COMPUTATIONAL INTELLIGENCE-BASED OPTIMIZATION OF HEAT TRANSFER IN ADVANCED THERMAL SYSTEMS

Abstract

The growing demand for energy-efficient thermal systems has intensified the need for advanced techniques to enhance heat transfer performance. Computational intelligence (CI) methods have emerged as powerful tools for optimizing complex heat transfer processes where conventional analytical approaches face limitations. This study explores the application of computational intelligence techniques, including artificial neural networks, genetic algorithms, and hybrid learning models, for advanced heat transfer optimization. These methods enable accurate modeling of nonlinear thermal behavior and identification of optimal design and operating parameters. By learning from experimental and simulated data, CI-based models improve heat transfer efficiency while reducing energy consumption and computational cost. Comparative analysis demonstrates that computational intelligence–driven optimization outperforms traditional optimization techniques in terms of accuracy and adaptability. The results highlight the potential of CI approaches to support intelligent thermal system design and sustainable energy management.