Fault diagnosis of refrigerant charge based on Decision Tree for variable refrigerant flow air-conditioning system

Variable refrigerant flow (VRF) systems are easily subjected to performance degradation due to refrigerant leakage, mechanical failure or improper maintenance after years of operation. Ideal VRF systems should equip with fault detection and diagnosis (FDD) program to sustain its normal operation. This paper presents the fault diagnosis method for refrigerant charge faults of variable refrigerant flow (VRF) systems. It is developed based on the classification and regression tree (CART) algorithm. Data of the experimental VRF system is used to test the advantages of the CART method. Results show that the decision tree can achieve desirable diagnosis efficiency on undercharge faults, while it is less sensitive to the overcharge faults. Validation study is also conducted using the data of online VRF systems. Results implies that the CART method obtains an outstanding classification efficiency on the VRF system that has the same type as the one provides the training data. But it is unable to identify the data of different type systems