Abstract: At present, with the development of society, air conditioning systems are widely used in various buildings, and fault detection of air conditioners is also considered to be one of the main challenges facing modern buildings. Because the data on the operation of the air conditioner comes from a large number of sensors, it is difficult to detect and detect at an early stage. Although in recent years, the use of statistical modeling and machine learning methods has been widely used in air conditioning fault detection and diagnosis. However, early detection is still a difficult task, and it also faces the problem of poor accuracy of fault detection. By combining a hybrid classifier of a random forest and support vector machine are used for fault detection and diagnostic applications of air conditioning systems. Experiments show that this kind of mixed classification model of random forest and support vector machine has high accuracy in fault classification, and the requirements for training samples are not high, and fewer training samples can be used to train and obtain better accuracy.

Key words: Air-conditioning system, Fault detection and diagnosis, Support vector machine, Random forest