Solar dryers are recognized as sustainable and energy-efficient technologies for dehydrating agricultural products under environmentally friendly conditions. These systems utilize solar radiation as a renewable energy source to reduce the moisture content of produce while preserving its nutritional and microbiological quality. However, the performance of solar dryers is significantly affected by environmental variables such as ambient temperature, solar irradiance, and airflow rate, which fluctuate dynamically during the drying process. Conventional control strategies, such as Proportional–Integral (PI) controllers, often exhibit limitations in such nonlinear and time-variant systems due to their slower response and limited adaptability.

This study proposes an intelligent control approach based on Artificial Neural Networks (ANNs) to enhance the accuracy and responsiveness of temperature regulation within a solar drying chamber. A mathematical model of the drying process was developed and implemented using MATLAB R2014a and the Simulink simulation environment. The ANN-based predictive controller was benchmarked against a traditional PI controller through a series of comparative simulations. The results indicated that the ANN-based system achieved a settling time of 160 seconds, representing a 36% improvement over the 250-second response time observed with the PI controller. Moreover, the ANN controller maintained temperature stability within ±1.2°C, demonstrating superior precision and robustness.

The findings suggest that neural network-based intelligent regulation significantly improves the dynamic performance of solar drying systems, enabling the real-time optimization of drying conditions. This method holds considerable promise for automating and industrializing solar drying technologies, with potential benefits in energy savings and product quality enhancement.