FAULT DETECTION BASED ON MOTOR START TRANSIENTS AND SHAFT HARMONICS MEASURED AT THE RTU ELECTRICAL SERVICE

Non-intrusive load monitoring (NILM) is accomplished by sampling voltage and current at high rates and reducing the resulting start transients or harmonic content to concise load “signatures.” Changes in these signatures can be used to detect, and possibly diagnose, equipment and component faults associated with roof-top cooling units. NILM-based fault detection and diagnosis (FDD) is important because 1) it complements other FDD schemes that are based on thermo-fluid sensors and analyses and 2) it is minimally intrusive (one measuring point in the relatively protected confines of the control panel) and therefore inherently reliable. This paper describes changes in the power signatures of fans and compressors that were found, experimentally and theoretically, to be useful for fault detection.