Analysis of power consumption influencing factors in different modes of semiconductor factory refrigeration station based on association rule mining.

At present, the energy consumption of room air conditioning in major rooms is relatively high, and the use of relevant methods to study the relationship between various parameters during the operation of the room refrigeration station is of great significance to the energy saving and regulation of the room air conditioning system. In this paper, a room refrigeration station in Xiamen is selected as the research object to study the realtime operation data of the system from March to June. After processing the outliers and missing values in the original dataset, the clustering algorithm K-means is first used to divide them into three categories, and the operating status and load size of chillers in various modes are preliminarily analyzed. Then, the association rule analysis algorithm Apriori is used to find the association rules between the parameters in each type of data, and the results show that the parameters that are more related to the system power are the outdoor temperature and the inlet and outlet temperature of the cooling water in the circulation. Using this result, the appropriate operating mode can be found by collecting system operating data, which can provide guidance for the energysaving operation and regulation of the room’s air conditioning.