EVALUATING THE PERFORMANCE OF A FAULT-DETECTION AND DIAGNOSTIC SYSTEMFOR VAPOR COMPRESSION EQUIPMENT

This paper presents a detailed evaluation of the performance of a stat istical, rule-based fault detection and diagnostic (FDD) technique pre sented by Rossi and Braun (1997). Steady-state and transient tests wer e performed on a simple rooftop air conditioner over a range of condit ions and fault levels. The steady-state delta without faults were used to train models that predict outputs for normal operation. The transi ent data with faults were used to evaluate I;DD performance. The effec t of a number of design variables on FDD sensitivity for different fau lts was evaluated and two prototype systems were specified for more co mplete evaluation. Good performance was achieved in detecting and diag nosing five faults using only six temperatures (2 input and 4 output) and linear models. The performance improved by about a factor of two w hen ten measurements (three input and seven output) and higher order m odels were used. This approach for evaluating and optimizing the perfo rmance of the statistical, rule-based FDD technique could be used as a design and evaluation tool when applying this FDD method to other pac kaged air-conditioning systems. Furthermore, the approach could also b e modified to evaluate the performance of other FDD methods.