Machine learning-based fault detection and preliminary diagnosis for terminal air-handling units

With the advent of Artificial Intelligence (AI) powered classification techniques, data-driven Fault Detection and Diagnosis (FDD) methods have become increasingly prominent in smart building implementation. Of these, cluster analysis is particularly promising for Building management system (BMS) data. This paper presents an unsupervised learning-based strategy detecting faults terminal air handling units as well systems serving them. Historical sensor data pre-processed with PCA to reduce dimensions, followed by OPTICS clustering, which compared k-means. outperformed latter, readily identifying noise had high accuracy across all seasons.