Advances in data-driven fault detection and diagnosis for HVAC systems: a review of recent developments

Abstract: Building performance can degrade precipitously after commissioning without adequate maintenance. HVAC system malfunctions can result in excessive energy consumption, associated CO2 emissions, and poor indoor environmental quality, and productivity loss. Fault Detection and Diagnosis (FDD) algorithms using sensor networks and IoT devices are a topic of significant research. This paper presents a comprehensive literature review of HVAC FDD applications using machine learning methods, including supervised classification, unsupervised learning, regression, statistics-based, and hybrid approaches. Each is discussed with respect to their state of development, relative advantages and limitations.