Building Energy Doctors: An SPC and Kalman Filter-Based Method for System-Level Fault Detection in HVAC Systems

Buildings worldwide account for nearly 40% of global energy consumption. The biggest energy consumer in buildings is the Heating, Ventilation and Air Conditioning (HVAC) systems. HVAC also ranks top in terms of number of complaints by tenants. Maintaining HVAC systems in good conditions through early fault detection is thus a critical problem. The problem, however, is difficult since HVAC systems are large in scale, consisting of many coupling subsystems, building and equipment dependent, and working under time-varying conditions. In this paper, a model-based and data-driven method is presented for robust system-level fault detection with potential for large-scale implementation. It is a synergistic integration of: ) Statistical Process Control (SPC) for measuring and analyzing variations; 2) Kalman filtering based on gray-box models to provide predictions and to determine SPC control limits; and (3) system analysis for analyzing propagation of faults' effects across subsystems. In the method, two new SPC rules are developed for detecting sudden and gradual faults. The method has been tested against a simulation model of the HVAC system for a 420-meter-high building. It detects both sudden faults and gradual degradation, and both device and sensor faults. Furthermore, the method is simple and generic, and has potential replicability and scalability. Note to Practitioners-HVAC systems work under time-varying weather and cooling load, and it is therefore difficult to detect faults. In addition, the various devices of HVAC systems require the detection method simple and robust so that it has good replicability and scalability. A gray-box model-based and data-driven method is developed in this paper. It is a novel combination of SPC, Kalman filter, and system analysis. By measuring and analyzing variations of model parameters, a fault can be detected when it causes these parameters to deviate from their normal ranges. The method detects both sudden and gradual faults with high detection rate and low false alarm rate. It also detects effects of faults in one subsystem on another to help detect and confirm device faults.