Sensor Fault Detection and Diagnosis Method for AHU Using 1-D CNN and Clustering Analysis

Table 3

The description of the batch of data used to search for the optimal T_c.

Type	Bias	Noise (dBm)	Size of dataset
Tsup sensor fault	0.5/1.0/1.5	6∼13	264
Twr sensor fault	0.5/1.0/1.5	6∼13	264
Tws sensor fault	0.5/1.0/1.5	6∼13	264
Mw sensor fault	5%	6∼13	264
Normal	—	6∼13	1056

Note: in faulty condition, WGNs are added to the output of the faulty sensor during the simulation. In normal condition, WGNs are added to the outputs of T_ws sensor, T_wr sensor, and M_w sensor during the simulation, respectively.