Metrics and Methods to Assess Building Fault Detection and Diagnosis Tools

Technical Report · Wed Mar 20 00:00:00 EDT 2019

DOI:https://doi.org/10.2172/1503166· OSTI ID:1503166

Frank, Stephen M.  ^[1]; Lin, Guanjing ^[2]; Jin, Xin ^[1]; Singla, Rupam ^[3]; Farthing, Amanda ^[4]; Zhang, Liang ^[1]; Granderson, Jessica ^[2]

---

1. National Renewable Energy Laboratory (NREL), Golden, CO (United States)
2. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
3. TRC Energy Services, Lowell, MA (United States)
4. Univ. of Michigan, Ann Arbor, MI (United States)

This paper presents the research methodology and findings related to fault definition, input samples, and evaluation metrics. We discuss these findings in light of key considerations for FDD algorithm performance testing, and conclude with recommendations and suggested areas of future work.

• Research Organization: National Renewable Energy Lab. (NREL), Golden, CO (United States)
• Sponsoring Organization: USDOE Office of Energy Efficiency and Renewable Energy (EERE), Energy Efficiency Office. Building Technologies Office
• DOE Contract Number: AC36-08GO28308
• OSTI ID: 1503166
• Report Number(s): NREL/TP-5500-72801
• Country of Publication: United States
• Language: English

Related Subjects

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION
fault detection
fault diagnosis
buildings
algorithms
FDD