IoT-based Environmental Monitoring and Prediction of Banana Moisture Content in a Solar Greenhouse Dryer

Modernizing the drying process will reduce agricultural product waste and environmental pollution. The aim of this study was to design a monitoring system based on the internet of things (IoT), temperature and relative humidity for a solar dryer. This system consists of a data collection module that gathers data regarding temperature (Ta), external relative humidity (RH) and on/off time of the solar dryer exhaust fans; a communication module that transmits Ta and RH information via LoRa and Wifi to ThingSpeak for monitoring on a mobile device; and a power module providing electrical power for system operation by solar energy. The operation of the IoT monitoring system was evaluated in three drying experiments of Dominican bananas (Musa paradisiaca var sapientum), in which system performance was satisfactory, allowing the user to visualize graphically in a web and mobile interface the behavior of Ta and RH inside the dryer. The data measured by the system were used to predict banana moisture content with an autoregressive model with exogenous variables (ARX) identified online. The mathematical model found predicted the behavior of moisture content with a good goodness of fit, with values of R2 = 0.99, MSE = 1.2910-5 and MAE = -5.0310-6. The solar dryer allowed reducing the moisture content of bananas up to 19.84 % wet basis (w.b.) in a period of 4 days and by 20.03% w.b. for 5 days in the presence of rainfall.