Design and prediction method of dual working medium solar energy drying system

Abstract The design method of dual working medium solar energy drying system is proposed in this study. The operation control strategy of system is given. In order to obtain the drying chambers suitable air temperature controlling method and the expected operating environment of the system, the flat plate solar collector with dual-function hybrid dryer is regarded as a case. The influence of operation environment parameters on the performance of solar heating unit is analyzed by traditional thermodynamics, and five machine learning methods with python software are carried out to predict the thermal performance of solar heating unit. The effects of ambient temperature, solar radiation intensity and supply air flow of solar heating unit on the outlet air temperature and collecting efficiency are obtained. In addition, ambient relative humidity is found to be the most important effect factors for the outlet temperature of solar heating unit. Gradient Boosting Regression can be regarded as the best prediction performance with R2 of 0.98 and 0.94 on training data and testing data, respectively. This study also pointed out the direction for the application and development of the traditional thermodynamics and machine learning.