Pattern mining and fault detection via CoP_therm-based profiling with correlation analysis of circuit variables in chiller systems

In this paper, we propose methods of handling, analyzing, and profiling monitoring data of energy systems using their thermal coefficient of performance seen in uneven segmentations in their time series databases. Aside from assessing the performance of chillers using this parameter, we dealt with pinpointing different trends that this parameter undergoes through while the systems operate. From these results, we identified and cross-validated with domain experts outlier behavior which were ultimately identified as faulty operation of the chiller. Finally, we establish correlations of the parameter with the other independent variables across the different circuits of the machine with or without the observed faulty behavior.