Research On Influencing Factors And The Classification Methods Of Room Radiation Time Series

The radiation time series method is a method for calculating the design load of air conditioners suitable for engineering applications.The radiation time series is closely related to the room structure type and its characteristic parameters,and its accuracy has a great influence on the accuracy of the design load calculation.The existing available radiation time series involves too few room structure types and characteristic parameters,and the division of room structure types is too simple,resulting in a large deviation of the air-conditioning design load,affecting the investment cost and operating efficiency of the air-conditioning system.The radiation time series can be calculated by the heat balance method,and it is impossible to give the corresponding radiation time series for all room types in the project.In order to reduce the design load error caused by the inaccurate radiation time series,it is proposed to use the big data analysis method to accurately classify the radiation time series.considering the types and characteristic parameters of commonly used building envelopes in China,The Monte Carlo sampling method is used to extract room samples with a combination of structure types and characteristic parameters firstly.Then,the heat balance method is used to calculate the radiation time series of each combination of room samples.Subsequently,the key characteristic parameters that affect the room radiation time series are extracted by the CART algorithm,and the room structure types and characteristic parameters are classified.Finally,the K-Medoids algorithm is used to determine the representative radiation time series of each type of room.Using the proposed decision tree classification method,the non-solar radiation time series and the solar radiation time series of the commonly used building types and their characteristic parameter combination rooms were divided into 12 categories and8 categories,respectively.The selected representative radiation time series was verified.the results show that after classification,the radiation time series of each type of room well represents all the rooms in this category.Compared with the design cooling load calculated by the time series,the deviation is small.The design cooling load calculated using the representative radiation time series significantly reduces the deviation from the design cooling load calculated using the heat balance method compared to the design cooling load calculated using the radiation time series provided by ASHRAE.Providing more accurate classification of room radiation time series can significantly improve the accuracy of air conditioning design load,and provide data and theoretical basis for the application and popularization of radiation time series method in China.