Data-driven Whole Building Fault Detection and Diagnosis

Residential and commercial buildings are responsible for more than 40% of the primary energy consumption in the United States. Energy wastes are estimated to reach 15% to 30% of total energy consumption due to malfunctioning sensors, components, and control systems, as well as degrading components in Heating, Ventilation, Air-conditioning (HVAC) systems and lighting systems in commercial buildings in the U.S. Studies have demonstrated that a large energy saving can be achieved by automated fault detection and diagnosis (AFDD) followed by corrections. Field studies have shown that, AFDD tools can help to reach energy savings by 5-30% from different systems such as HVAC systems, lighting systems, and refrigeration systems. At the same time, the deployment of AFDD tools can also significantly improve indoor air quality, reduce peak demand, and lower pollution. In buildings, many components or equipment are closely coupled in a HVAC system. Because of the coupling, a fault happening in one component might propagate and affect other components or subsystems. In this study, a whole building fault (WBF) is defined as a fault that occurs in one component or equipment but causes fault impacts (abnormalities) on other components and subsystems, or causes significant impacts on energy consumption and/or indoor air quality. Over the past decades, extensive research have been conducted on the development of component AFDD methods and tools. However, whole building AFDD methods, which can detect and diagnose a WBF, have not been well studied. Existing component level AFDD solutions often fail to detect a WBF or generate a high false alarm rate. Isolating a WBF is also very challenging by using component level AFDD solutions. Even with the extensive research, cost-effectiveness and scalability of existing AFDD methods are still not satisfactory. Therefore, the focus of this research is to develop cost-effective and scalable solutions for WBF AFDD. This research attempts to integrate data-driven methods with expert knowledge/rules to overcome the above-mentioned challenges. A suite of WBF AFDD methods have hence been developed, which include: 1) a weather and schedule based pattern matching method and feature based Principal Component Analysis (WPM-FPCA) method for whole building fault detection. The developed WPM-FPCA method successfully overcome the challenges such as the generation of accurate and dynamic baseline and data dimensionality reduction. And 2) a data-driven and expert knowledge/rule based method using both Bayesian Network (BN) and WPM for WBF diagnosis. The developed WPM-BN method includes a two-layer BN structure model and BN parameter model which are either learned from baseline data or developed from expert knowledge. Various WBFs have been artificially implemented in a real demo building. Building operation data which include baseline data, data that contain naturally-occurred faults and artificially implemented faults are collected and analyzed. Using the collected real building data, the developed methods are evaluated. The evaluation demonstrates the efficacy of the developed methods to detect and diagnose a WBF, as well as their implementation cost-effectiveness.