Incipient fault detection of chiller based on improved CVA

The chiller plays an important role for providing comfort environment. Once, the incipient faults are missed, they may develop to be fatal and further lead equipment damage casualties. Nevertheless, fault in running process of easily neglected noise. Moreover, variables have dynamic characteristics, each variable is correlated with other process, a certain interrelated at different times. To tackle these problems, we improved canonical analysis (ICVA) method detect units significant characteristics. In proposed method, exponentially weighted moving average (EWMA) first applied filter data. Then used fault. this paper, ASHRAE RP-1043 experimental data verify method. Simulation results show that compared traditional CVA ICVA has higher detection rate