A rule augmented statistical method for air-conditioning system fault detection and diagnostics

Abstract Cumulative sum (CUSUM) chart is a general method in statistical control engineering to monitor controlled variables. CUSUM chart has been applied to VAV terminal units by NIST for fault detection, known as VAV Box Performance Assessment Control Charts (VPACC) method. This paper combines CUSUM method with a fault counter approach, which extends the functionality of CUSUM method from fault detection to fault diagnostics. To use this method, user needs to specify a causal relationship between all the control variables, and between the control variables and their controlling components. Based on the real time monitored data, a CUSUM score is calculated for each control variable, and a fault counter is then updated based on an automatic count mechanism. The testing of this approach in a simulation case shows that it has good performance in detecting incipient faults. It is realized that the CUSUM method can only detect faults that lead to control problems, therefore the capability of this method is limited. But the proposed method has some strong advantages, for example, it requires only building control related sensor information, and it can be easily adapted if the system is changed or upgraded, which frequently happens in renovations.