Automated fault detection and diagnosis of airflow and refrigerant charge faults in residential HVAC systems using IoT-enabled measurements

Ejenakevwe, Kevwe Andrew; Wang, Junke; Jiang, Yilin; Song, Li; Kini, Roshan L.

doi:10.1080/23744731.2023.2234231

Automated fault detection and diagnosis of airflow and refrigerant charge faults in residential HVAC systems using IoT-enabled measurements

Journal Article · Wed Aug 02 00:00:00 EDT 2023 · Science and Technology for the Built Environment

DOI:https://doi.org/10.1080/23744731.2023.2234231· OSTI ID:2204485

^[1]; Wang, Junke ^[2]; ^[2]; Song, Li ^[2]; Kini, Roshan L. ^[3]

University of Oklahoma, Norman, OK (United States); University of Oklahoma
University of Oklahoma, Norman, OK (United States)
Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)

While automated fault detection and diagnosis (AFDD) in residential heating, ventilation, and air-conditioning (HVAC) using smart thermostat data is gaining increasing attention in recent times, it still requires in-depth investigation for market adoption, especially with real-life data. Furthermore, this paper proposes an Internet of Things (IoT) - based approach that adds a smart sensor to the smart thermostat data to carry out AFDD. The approach uses a model which predicts enthalpy change across the evaporator and compares the prediction to the measured enthalpy change. Deviations which exceed analytically determined thresholds then signal faults in the HVAC system. The faults detected are either installation related or degradation related. Experimental tests were carried out in four homes located in Norman, Oklahoma. From the tests, installation issues like indoor/outdoor mismatch were detected in two homes, while a 30% low charge and low indoor airflow rate were detected in one home. The results show that the proposed AFDD algorithm was able to successfully detect two prevalent faults, namely low indoor airflow and low refrigerant charge. Unlike most of the smart thermostat-based approaches, the proposed IoT-based approach can detect and diagnose both faults but only require one additional sensor which is provided by smart thermostat manufacturers.

View Accepted Manuscript (DOE)

Research Organization:: University of Oklahoma, Norman, OK (United States)

Sponsoring Organization:: USDOE Office of Energy Efficiency and Renewable Energy (EERE), Energy Efficiency Office. Building Technologies Office

Grant/Contract Number:: EE0008697

OSTI ID:: 2204485

Journal Information:: Science and Technology for the Built Environment, Journal Name: Science and Technology for the Built Environment Journal Issue: 9 Vol. 29; ISSN 2374-4731

Publisher:: Taylor & FrancisCopyright Statement

Country of Publication:: United States

Language:: English

References (22)

Development and evaluation of virtual refrigerant mass flow sensors for fault detection and diagnostics Kim, Woohyun; Braun, James E. International Journal of Refrigeration, Vol. 63 https://doi.org/10.1016/J.IJREFRIG.2015.11.005	journal	March 2016
Deep learning-based fault diagnosis of variable refrigerant flow air-conditioning system for building energy saving Guo, Yabin; Tan, Zehan; Chen, Huanxin Applied Energy, Vol. 225 https://doi.org/10.1016/j.apenergy.2018.05.075	journal	September 2018
A review of fault detection and diagnosis methods for residential air conditioning systems Rogers, A. P.; Guo, F.; Rasmussen, B. P. Building and Environment, Vol. 161 https://doi.org/10.1016/j.buildenv.2019.106236	journal	August 2019
Methods for a Smart Thermostat to Estimate the Characteristics of a House Based on Sensor Data van der Ham, Wim; Klein, Michel; Tabatabaei, Seyed Amin Energy Procedia, Vol. 95 https://doi.org/10.1016/j.egypro.2016.09.067	journal	September 2016
Residential HVAC fault detection using a system identification approach Turner, W. J. N.; Staino, A.; Basu, B. Energy and Buildings, Vol. 151 https://doi.org/10.1016/j.enbuild.2017.06.008	journal	September 2017
Design and analysis of optimal pre-cooling in residential buildings Wang, Junke; Tang, Choon Yik; Song, Li Energy and Buildings, Vol. 216 https://doi.org/10.1016/j.enbuild.2020.109951	journal	June 2020
Automated fault detection of residential air-conditioning systems using thermostat drive cycles Chintala, Rohit; Winkler, Jon; Jin, Xin Energy and Buildings, Vol. 236 https://doi.org/10.1016/j.enbuild.2020.110691	journal	April 2021
Decoupling features and virtual sensors for diagnosis of faults in vapor compression air conditioners Li, Haorong; Braun, James E. International Journal of Refrigeration, Vol. 30, Issue 3 https://doi.org/10.1016/j.ijrefrig.2006.07.024	journal	May 2007
Refrigerant leakage detection in an EEV installed residential air conditioner with limited sensor installations Yoo, Jin Woo; Hong, Sung Bin; Kim, Min Soo International Journal of Refrigeration, Vol. 78 https://doi.org/10.1016/j.ijrefrig.2017.03.001	journal	June 2017
Gradual fault early stage diagnosis for air source heat pump system using deep learning techniques Sun, Zhe; Jin, Huaqiang; Gu, Jiangping International Journal of Refrigeration, Vol. 107 https://doi.org/10.1016/j.ijrefrig.2019.07.020	journal	November 2019
A review of the fault behavior of heat pumps and measurements, detection and diagnosis methods including virtual sensors Bellanco, I.; Fuentes, E.; Vallès, M. Journal of Building Engineering, Vol. 39 https://doi.org/10.1016/j.jobe.2021.102254	journal	July 2021
Data-Driven Methodology for Energy and Peak Load Reduction of Residential HVAC Systems Cetin, Kristen Sara; Kallus, Catilyn Procedia Engineering, Vol. 145 https://doi.org/10.1016/j.proeng.2016.04.205	journal	January 2016
Review Article: Methods for Fault Detection, Diagnostics, and Prognostics for Building Systems—A Review, Part II Katipamula, Srinivas; Brambley, Michael HVAC&R Research, Vol. 11, Issue 2 https://doi.org/10.1080/10789669.2005.10391133	journal	April 2005
Development, Evaluation, and Demonstration of a Virtual Refrigerant Charge Sensor Li, Haorong; Braun, James HVAC&R Research, Vol. 15, Issue 1 https://doi.org/10.1080/10789669.2009.10390828	journal	January 2009
Virtual Refrigerant Pressure Sensors for Use in Monitoring and Fault Diagnosis of Vapor-Compression Equipment Li, Haorong; Braun, James HVAC&R Research, Vol. 15, Issue 3 https://doi.org/10.1080/10789669.2009.10390853	journal	May 2009
Uncertainty analysis for a virtual flow meter using an air-handling unit chilled water valve Song, Li; Wang, Gang; Brambley, Michael R. HVAC&R Research, Vol. 19, Issue 3 https://doi.org/10.1080/10789669.2013.774890	journal	April 2013
Uncertainty analysis and field implementation of a fault detection method for residential HVAC systems Rogers, Austin; Guo, Fangzhou; Rasmussen, Bryan Science and Technology for the Built Environment, Vol. 26, Issue 3 https://doi.org/10.1080/23744731.2019.1676093	journal	October 2019
Multivariate fault detection for residential HVAC systems using cloud-based thermostat data, part II: Case studies Guo, Fangzhou; Rogers, Austin P.; Rasmussen, Bryan P. Science and Technology for the Built Environment, Vol. 28, Issue 2 https://doi.org/10.1080/23744731.2021.1987141	journal	December 2021
Multivariate fault detection for residential HVAC systems using cloud-based thermostat data, part I: Methodology Guo, Fangzhou; Rogers, Austin P.; Rasmussen, Bryan P. Science and Technology for the Built Environment, Vol. 28, Issue 2 https://doi.org/10.1080/23744731.2021.2005375	journal	December 2021
Review of Fault Detection and Diagnosis Studies on Residential HVAC Systems Ejenakevwe, Kevwe A.; Song, Li Volume 8B: Energy https://doi.org/10.1115/IMECE2021-72745	conference	November 2021
Beyond Control Jain, Milan; Gupta, Mridula; Singh, Amarjeet Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, Vol. 3, Issue 1 https://doi.org/10.1145/3314401	journal	March 2019
Use of risk-adjusted CUSUM and RSPRTcharts for monitoring in medical contexts Grigg, O. A.; Farewell, V. T.; Spiegelhalter, D. J. Statistical Methods in Medical Research, Vol. 12, Issue 2 https://doi.org/10.1177/096228020301200205	journal	April 2003