This paper investigates the optimization of cooling systems in industrial settings, particularly within oil refining plants, focusing on reducing energy consumption, water usage, and environmental impact. The study forms part of a broader dissertation on “Intellectual Control of Cooling and Cleaning Processes,” with a key emphasis on integrating AI-driven controls into industrial applications. By examining various cooling methods, including evaporation and air blowing techniques, the research assesses their performance under different environmental conditions and fan operating speeds. Empirical data collection and analytical modeling reveal that while traditional evaporation methods achieve maximum cooling efficiency at high fan speeds, air blowing techniques demonstrate significant potential in cooler environments, offering lower water consumption and energy use. The findings underscore the importance of adaptive control strategies, which can dynamically adjust operational regimes based on real-time conditions, leading to more sustainable and cost-effective cooling processes. This study provides a foundation for the future application of AI technologies in optimizing industrial cooling systems.