Intelligent Temperature Control Using Artificial Neural Networks in an IoT-Enabled Cyber-Physical Hot-Air Drying System: Analysis of Drying Kinetics and Thermal Efficiency

A control algorithm based on artificial neural networks was developed to regulate the hot-air drying temperature for carrot dehydration within an IoT-enabled cyber-physical system. The experimental setup employs an Arduino Mega 2560 equipped with AM2302, MLX90614, and SHT35 sensors, an HX711 load cell, and a WS68 anemometer, with cloud communication provided by an ESP8266 module for remote monitoring via Wi-Fi under an IoT framework. The neural controller, implemented using the Arduino Neurona li-brary, adjusts the dryer temperature in real time, ensuring thermal stability throughout operation. Three initial loads (2, 4, and 6 kg) were analyzed to obtain the drying kinetics and determine the thermal efficiency. In the dehydration experiments, the 2 kg load reached a final moisture content of 10% in 4.4 h, consuming 1,390 kJ with a thermal effi-ciency of 83%. The 4 kg load exhibited the best time–energy balance (6.6 h, 1,850.0 kJ, 88%), while the 6 kg load achieved the highest efficiency (8.1 h, 2,250.0 kJ, 91%). These results demonstrate the effectiveness of neural-network-based control implemented on low-cost microcontrollers to enhance thermal efficiency in food dehydration processes.