Building energy doctors: SPC and Kalman filter-based fault detection

Abstract

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 issue. The problem, however, is difficult since HVAC systems are large in scale, consisting of many coupling subsystems, building and equipment dependent, and operating under uncertain 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 (1) Statistical Process Control (SPC) for measuring and analyzing variations; (2) Kalman filtering based on gray-box models to provide predictions and determine SPC control limits; and (3) system analysis for analyzing fault propagation. The method has been tested against a simulation model of a 420-meter-high building. It detects both sudden faults and gradual degradation, and differentiates faults within a subsystem or propagated from elsewhere. Furthermore, the method is simple and generic, and should have good replicability and scalability.