A Bi-Level Data-Driven Framework for Fault-Detection and Diagnosis of HVAC Systems feature explainability

Abstract

Machine learning methods have lately received considerable interest for fault detection diagnostic (FDD) analysis of heating, ventilation, and air conditioning (HVAC) systems due to their high detection accuracy. Meanwhile, HVAC malfunctions are regarded as rare occurrences, hence normal operating data samples are much more accessible than data samples in faulty and malfunctioning conditions. The dominating frequency of normal operation in HVAC datasets have also led to heavily biased classification algorithms within the literature. Moreover, the focus of previous literature has been on increasing accuracy of the models while this leads to a high number of false positives (misleading alarms) in the system. To enhance the performance of diagnostic procedures and fill the mentioned gaps, this study proposes a novel data-driven framework. A bi-level machine learning framework is developed for diagnosing faults in air handling units and rooftop units based on principal component analysis (PCA), time series anomaly detection, and random forest (RF). It is shown that PCA can reduce the dataset dimension with one principal component accounting for 95% of data variance. Also, the random forest could classify the faults with 89% precision for single zone AHU, 85% precision for RTU, and 79% for multi-zone AHU.