Semi-Supervised Machine Learning for Fault Detection and Diagnosis of a Rooftop Unit
Most heating, ventilation, and air-conditioning (HVAC) systems operate with one or more faults that result in increased energy consumption and that could lead to system failure over time. Today, most building owners are performing reactive maintenance only and may be less concerned or less able to a...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2023-06-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2022.9020015 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832557420788842496 |
|---|---|
| author | Mohammed G. Albayati Jalal Faraj Amy Thompson Prathamesh Patil Ravi Gorthala Sanguthevar Rajasekaran |
| author_facet | Mohammed G. Albayati Jalal Faraj Amy Thompson Prathamesh Patil Ravi Gorthala Sanguthevar Rajasekaran |
| author_sort | Mohammed G. Albayati |
| collection | DOAJ |
| description | Most heating, ventilation, and air-conditioning (HVAC) systems operate with one or more faults that result in increased energy consumption and that could lead to system failure over time. Today, most building owners are performing reactive maintenance only and may be less concerned or less able to assess the health of the system until catastrophic failure occurs. This is mainly because the building owners do not previously have good tools to detect and diagnose these faults, determine their impact, and act on findings. Commercially available fault detection and diagnostics (FDD) tools have been developed to address this issue and have the potential to reduce equipment downtime, energy costs, maintenance costs, and improve occupant comfort and system reliability. However, many of these tools require an in-depth knowledge of system behavior and thermodynamic principles to interpret the results. In this paper, supervised and semi-supervised machine learning (ML) approaches are applied to datasets collected from an operating system in the field to develop new FDD methods and to help building owners see the value proposition of performing proactive maintenance. The study data was collected from one packaged rooftop unit (RTU) HVAC system running under normal operating conditions at an industrial facility in Connecticut. This paper compares three different approaches for fault classification for a real-time operating RTU using semi-supervised learning, achieving accuracies as high as 95.7% using few-shot learning. |
| format | Article |
| id | doaj-art-1bf1ede38a0f4fc780b99a9c0ab8c9bc |
| institution | Kabale University |
| issn | 2096-0654 |
| language | English |
| publishDate | 2023-06-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj-art-1bf1ede38a0f4fc780b99a9c0ab8c9bc2025-02-03T04:58:51ZengTsinghua University PressBig Data Mining and Analytics2096-06542023-06-016217018410.26599/BDMA.2022.9020015Semi-Supervised Machine Learning for Fault Detection and Diagnosis of a Rooftop UnitMohammed G. Albayati0Jalal Faraj1Amy Thompson2Prathamesh Patil3Ravi Gorthala4Sanguthevar Rajasekaran5Department of Mechanical Engineering, School of Engineering, University of Connecticut, Storrs, CT 06269, USADepartment of Computer Science and Engineering, University of Connecticut, Storrs, CT 06269, USADepartment of Mechanical Engineering, School of Engineering, University of Connecticut, Storrs, CT 06269, USADepartment of Mechanical and Industrial Engineering, Tagliatela College of Engineering, University of New Haven, West Haven, CT 06516, USADepartment of Mechanical and Industrial Engineering, Tagliatela College of Engineering, University of New Haven, West Haven, CT 06516, USADepartment of Computer Science and Engineering, University of Connecticut, Storrs, CT 06269, USAMost heating, ventilation, and air-conditioning (HVAC) systems operate with one or more faults that result in increased energy consumption and that could lead to system failure over time. Today, most building owners are performing reactive maintenance only and may be less concerned or less able to assess the health of the system until catastrophic failure occurs. This is mainly because the building owners do not previously have good tools to detect and diagnose these faults, determine their impact, and act on findings. Commercially available fault detection and diagnostics (FDD) tools have been developed to address this issue and have the potential to reduce equipment downtime, energy costs, maintenance costs, and improve occupant comfort and system reliability. However, many of these tools require an in-depth knowledge of system behavior and thermodynamic principles to interpret the results. In this paper, supervised and semi-supervised machine learning (ML) approaches are applied to datasets collected from an operating system in the field to develop new FDD methods and to help building owners see the value proposition of performing proactive maintenance. The study data was collected from one packaged rooftop unit (RTU) HVAC system running under normal operating conditions at an industrial facility in Connecticut. This paper compares three different approaches for fault classification for a real-time operating RTU using semi-supervised learning, achieving accuracies as high as 95.7% using few-shot learning.https://www.sciopen.com/article/10.26599/BDMA.2022.9020015semi-supervised machine learningfault classificationfault detection and diagnosticsheating, ventilation, and air-conditioningdata-driven modelingenergy efficiency |
| spellingShingle | Mohammed G. Albayati Jalal Faraj Amy Thompson Prathamesh Patil Ravi Gorthala Sanguthevar Rajasekaran Semi-Supervised Machine Learning for Fault Detection and Diagnosis of a Rooftop Unit Big Data Mining and Analytics semi-supervised machine learning fault classification fault detection and diagnostics heating, ventilation, and air-conditioning data-driven modeling energy efficiency |
| title | Semi-Supervised Machine Learning for Fault Detection and Diagnosis of a Rooftop Unit |
| title_full | Semi-Supervised Machine Learning for Fault Detection and Diagnosis of a Rooftop Unit |
| title_fullStr | Semi-Supervised Machine Learning for Fault Detection and Diagnosis of a Rooftop Unit |
| title_full_unstemmed | Semi-Supervised Machine Learning for Fault Detection and Diagnosis of a Rooftop Unit |
| title_short | Semi-Supervised Machine Learning for Fault Detection and Diagnosis of a Rooftop Unit |
| title_sort | semi supervised machine learning for fault detection and diagnosis of a rooftop unit |
| topic | semi-supervised machine learning fault classification fault detection and diagnostics heating, ventilation, and air-conditioning data-driven modeling energy efficiency |
| url | https://www.sciopen.com/article/10.26599/BDMA.2022.9020015 |
| work_keys_str_mv | AT mohammedgalbayati semisupervisedmachinelearningforfaultdetectionanddiagnosisofarooftopunit AT jalalfaraj semisupervisedmachinelearningforfaultdetectionanddiagnosisofarooftopunit AT amythompson semisupervisedmachinelearningforfaultdetectionanddiagnosisofarooftopunit AT prathameshpatil semisupervisedmachinelearningforfaultdetectionanddiagnosisofarooftopunit AT ravigorthala semisupervisedmachinelearningforfaultdetectionanddiagnosisofarooftopunit AT sanguthevarrajasekaran semisupervisedmachinelearningforfaultdetectionanddiagnosisofarooftopunit |