Indoor condensation prediction based on a surface temperature estimation

Since indoor condensation occurs for a variety of complex reasons, it is difficult to find a fundamental solution to prevent it. Indoor condensation, which is caused by environmental changes (an increase in internal humidity or a low ambient temperature), is difficult to prevent in an occupied residential structure based on the design of the structure. In this paper, we propose a new model for predicting indoor dew condensation that occurs in a residential environment with IoT technology. First, a basic dataset in the condensation environment is collected through a test bed, and a surface temperature estimation method that uses the machine learning model used to evaluate the dataset. In addition to the surface temperature estimation technique, which achieves a low RMSE of 0.97 in the field test, an associated condensation time prediction algorithm is proposed. The proposed method is a new method for determining the intersection point between two temperature changes based on the real-time rate of change of the surface temperature and the dew point temperature. The high condensation prediction accuracy of the proposed method is experimentally demonstrated.