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

Abstract

The rise of AI-powered classification techniques has ushered in a new era for data-driven Fault Detection and Diagnosis (FDD) in smart building systems. While extensive research has championed supervised FDD approaches, the real-world application of unsupervised methods remains limited. Among these, cluster analysis stands out for its potential with Building Management System (BMS) data. This study introduces an unsupervised learning strategy to detect faults in terminal air handling units and their associated systems. The methodology involves pre-processing historical sensor data using Principal Component Analysis (PCA) to streamline dimensions. This is then followed by OPTICS clustering, juxtaposed against kmeans for comparison. The effectiveness of the proposed strategy was gauged using several labeled datasets depicting various fault scenarios and real-world building BMS data. Results showed that OPTICS consistently surpassed k-means in accuracy across seasons. Notably, OPTICS offers a unique visualization feature for users called "reachability distance," allowing a preview of detected clusters before setting thresholds. Moreover, according to the results, while PCA is beneficial for reducing computational costs and enhancing noise reduction-thereby generally improving the clarity of cluster differentiation in reachability distance-it also has its limitations, particularly in complex fault scenarios. In such cases, PCA's dimensionality reduction may result in the loss of critical information, leading to some clusters being less discernible or entirely undetected. These overlooked clusters could be indicative of underlying faults, and their obscurity represents a significant limitation of PCA when identifying potential fault lines in intricate datasets.