<p>Solar dryers are among the environmentally friendly and energy-efficient <br /> drying systems designed for effective dehydration of agricultural products under <br /> natural conditions. These systems, by utilizing solar energy, optimize the moisture <br /> content of products and help preserve their quality. However, the efficiency of solar <br /> dryers depends on external factors such as ambient temperature, solar radiation, <br /> and airflow, making real-time control of these parameters essential. Traditional <br /> PI controllers are not sufficiently effective under such variable conditions due to <br /> their long tuning time and significant overshoot. In this study, a predictive control <br /> system based on artificial neural networks (ANN) was developed to enhance the <br /> performance of solar dryers and was compared with a PI-controller-based system. <br /> A mathematical model of the drying process was created in the MATLAB R2014a <br /> environment using the Simulink software package, and computer simulations <br /> were carried out for various control methods. The results showed that the system <br /> controlled by the predictive neuro-controller achieved a settling time of 160 <br /> seconds, which is 36% faster compared to the PI-controlled system (settling time <br /> of 250 seconds). Additionally, the neural control system maintained temperature <br /> stability with an accuracy of ±1.2°C, demonstrating significantly higher precision <br /> compared to the PI-controller. The results confirm that a control system based on <br /> artificial neural networks plays a crucial role in ensuring the stable operation of <br /> solar dryers, optimizing energy consumption, and improving product quality. This <br /> approach enables the automation of agricultural drying technologies and ensures <br /> their environmentally sustainable implementation. The findings indicate promising <br /> prospects for the large-scale industrial application of this system.</p>