Abstract

Small commercial buildings (those with less than approximately 1000 m2 of total floor area) often do not have access to cost-effective automated fault detection and diagnosis (AFDD) tools for maintaining efficient building operations. AFDD tools based on machine-learning algorithms hold promise for lowering cost barriers for AFDD in small commercial buildings; however, such algorithms require access to high-quality training data that is often difficult to obtain. To fill the gap in this research area, this study covers the development (Part I) and validation (Part II) of fault models that can be used with the building energy modeling software EnergyPlus® and OpenStudio® to generate a cost-effective training data set for developing AFDD algorithms. Part I (this paper) presents a library of fault models, including detailed descriptions of each fault model structure and their implementation with EnergyPlus. This paper also discusses a case study of training data set generation, representing an actual building.

Highlights

  • Building faults, meaning improper or undesirable operations of building systems and equipment, are common in modern commercial buildings

  • Given that the detection and correction of faults represents a large energy savings opportunity, significant effort has been dedicated to the research, development, and deployment of fault detection and diagnosis (FDD) algorithms [2,3,4]

  • The results shown demonstrate the capability to generate fault impact data using physics-based building model combined with fault models, that could be used in the development and evaluation of automated fault detection and diagnosis (AFDD) algorithms

Read more

Summary

Introduction

Building faults, meaning improper or undesirable operations of building systems and equipment, are common in modern commercial buildings. For large-scale fault impact estimation, the availability of reliable fault impact data is a key challenge Both Roth et al [1] and Kim, Cai, and Braun [5] identify multiple gaps, uncertainties, and inconsistencies in the available literature regarding the average loss of efficiency resulting from various types of faults. Simulation studies, such as those performed by Fernandez et al [11] and Li and O’Neill [6], offer a rigorous and consistent approach to estimating fault impacts, provided that the fault models used are well validated. The remainder of this article is organized as follows: Section 2 surveys prior research in modeling building faults, Section 3 presents the methodology, and Section 4 describes the specific fault models developed, Section 5 provides a case study of fault model applications for generating a training data set, and Section 6 provides the conclusions of Part I

Prior Work
Methodology
Overall
Physical Models
Excessive Infiltration Through the Building Envelope
HVAC Setback Error
Lighting Setback Error
Improper Time Delay Setting in Occupancy Sensors
Oversized Equipment at Design
Supply Air Duct Leakages
Return Air Duct Leakages
Thermostat Measurement Bias
Economizer
4.1.10. Biased Economizer Sensors
Empirical
Condenser
Nonstandard Refrigerant Charging
Presence of Noncondensable Gas in Refrigerant
Refrigerant Liquid–Line Restriction
Semiempirical Models
Air Handling Unit Fan Motor Degradation
Duct Fouling
Condenser Fan Degradation
Case Study
Characteristics of the Reference Building Model
Generation of the Training Data Set
Prioritization of Sensors Affected by Faults
Findings
Conclusions

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.