A method for fault detection and diagnostics in ventilation units using virtual sensors

Claudio Giovanni Mattera, Joseba Quevedo, Teresa Escobet, Hamid Reza Shaker, Muhyiddine Jradi

Research output: Contribution to journalJournal articleResearchpeer-review

110 Downloads (Pure)

Abstract

Buildings represent a significant portion of global energy consumption. Ventilation units are complex components, often customized for the specific building, responsible for a large part of energy consumption. Their faults impact buildings' energy efficiency and occupancy comfort. In order to ensure their correct operation, proper fault detection and diagnostics methods must be applied. Hardware redundancy, an effective approach to detect faults, leads to increased costs and space requirements. We propose exploiting physical relations inside ventilation units to create virtual sensors from other sensors' readings, introducing redundancy in the system. We use two different measures to detect when a virtual sensor deviates from the physical one: coefficient of determination for linear models, and acceptable range. We tested our method on a real building at the University of Southern Denmark, developing three virtual sensors: temperature, airflow, and fan speed. We employed linear regression models, statistical models, and non-linear regression models. All models detected an anomalous strong oscillation in the temperature sensors. Readings fell outside the acceptable range and the coefficient of determination dropped. Our method showed promising results by introducing redundancy in the system, which can benefit several applications, such as fault detection and diagnostics and fault-tolerant control. Future work will be necessary to discover thresholds and set up automatic fault detection and diagnostics.

Original languageEnglish
Article number3931
JournalSensors
Volume18
Issue number11
ISSN1424-8220
DOIs
Publication statusPublished - 14. Nov 2018

Fingerprint

fault detection
ventilation
Fault detection
Ventilation
Redundancy
Linear Models
Temperature sensors
redundancy
Reading
sensors
Sensors
Energy utilization
energy consumption
temperature sensors
Nonlinear Dynamics
Statistical Models
Denmark
regression analysis
Linear regression
Fans

Keywords

  • fault detection and diagnosis
  • virtual sensors
  • HVAC
  • smart buildings
  • User-Computer Interface
  • Algorithms
  • Computer Simulation
  • Denmark
  • Ventilation
  • Models, Statistical
  • Equipment Failure Analysis

Cite this

Mattera, Claudio Giovanni ; Quevedo, Joseba ; Escobet, Teresa ; Shaker, Hamid Reza ; Jradi, Muhyiddine. / A method for fault detection and diagnostics in ventilation units using virtual sensors. In: Sensors. 2018 ; Vol. 18, No. 11.
@article{3e3bf4f36cd04085979ee27ec487a50d,
title = "A method for fault detection and diagnostics in ventilation units using virtual sensors",
abstract = "Buildings represent a significant portion of global energy consumption. Ventilation units are complex components, often customized for the specific building, responsible for a large part of energy consumption. Their faults impact buildings' energy efficiency and occupancy comfort. In order to ensure their correct operation, proper fault detection and diagnostics methods must be applied. Hardware redundancy, an effective approach to detect faults, leads to increased costs and space requirements. We propose exploiting physical relations inside ventilation units to create virtual sensors from other sensors' readings, introducing redundancy in the system. We use two different measures to detect when a virtual sensor deviates from the physical one: coefficient of determination for linear models, and acceptable range. We tested our method on a real building at the University of Southern Denmark, developing three virtual sensors: temperature, airflow, and fan speed. We employed linear regression models, statistical models, and non-linear regression models. All models detected an anomalous strong oscillation in the temperature sensors. Readings fell outside the acceptable range and the coefficient of determination dropped. Our method showed promising results by introducing redundancy in the system, which can benefit several applications, such as fault detection and diagnostics and fault-tolerant control. Future work will be necessary to discover thresholds and set up automatic fault detection and diagnostics.",
keywords = "fault detection and diagnosis, virtual sensors, HVAC, smart buildings, User-Computer Interface, Algorithms, Computer Simulation, Denmark, Ventilation, Models, Statistical, Equipment Failure Analysis",
author = "Mattera, {Claudio Giovanni} and Joseba Quevedo and Teresa Escobet and Shaker, {Hamid Reza} and Muhyiddine Jradi",
year = "2018",
month = "11",
day = "14",
doi = "10.3390/s18113931",
language = "English",
volume = "18",
journal = "Sensors",
issn = "1424-8220",
publisher = "MDPI",
number = "11",

}

A method for fault detection and diagnostics in ventilation units using virtual sensors. / Mattera, Claudio Giovanni ; Quevedo, Joseba; Escobet, Teresa; Shaker, Hamid Reza; Jradi, Muhyiddine.

In: Sensors, Vol. 18, No. 11, 3931, 14.11.2018.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - A method for fault detection and diagnostics in ventilation units using virtual sensors

AU - Mattera, Claudio Giovanni

AU - Quevedo, Joseba

AU - Escobet, Teresa

AU - Shaker, Hamid Reza

AU - Jradi, Muhyiddine

PY - 2018/11/14

Y1 - 2018/11/14

N2 - Buildings represent a significant portion of global energy consumption. Ventilation units are complex components, often customized for the specific building, responsible for a large part of energy consumption. Their faults impact buildings' energy efficiency and occupancy comfort. In order to ensure their correct operation, proper fault detection and diagnostics methods must be applied. Hardware redundancy, an effective approach to detect faults, leads to increased costs and space requirements. We propose exploiting physical relations inside ventilation units to create virtual sensors from other sensors' readings, introducing redundancy in the system. We use two different measures to detect when a virtual sensor deviates from the physical one: coefficient of determination for linear models, and acceptable range. We tested our method on a real building at the University of Southern Denmark, developing three virtual sensors: temperature, airflow, and fan speed. We employed linear regression models, statistical models, and non-linear regression models. All models detected an anomalous strong oscillation in the temperature sensors. Readings fell outside the acceptable range and the coefficient of determination dropped. Our method showed promising results by introducing redundancy in the system, which can benefit several applications, such as fault detection and diagnostics and fault-tolerant control. Future work will be necessary to discover thresholds and set up automatic fault detection and diagnostics.

AB - Buildings represent a significant portion of global energy consumption. Ventilation units are complex components, often customized for the specific building, responsible for a large part of energy consumption. Their faults impact buildings' energy efficiency and occupancy comfort. In order to ensure their correct operation, proper fault detection and diagnostics methods must be applied. Hardware redundancy, an effective approach to detect faults, leads to increased costs and space requirements. We propose exploiting physical relations inside ventilation units to create virtual sensors from other sensors' readings, introducing redundancy in the system. We use two different measures to detect when a virtual sensor deviates from the physical one: coefficient of determination for linear models, and acceptable range. We tested our method on a real building at the University of Southern Denmark, developing three virtual sensors: temperature, airflow, and fan speed. We employed linear regression models, statistical models, and non-linear regression models. All models detected an anomalous strong oscillation in the temperature sensors. Readings fell outside the acceptable range and the coefficient of determination dropped. Our method showed promising results by introducing redundancy in the system, which can benefit several applications, such as fault detection and diagnostics and fault-tolerant control. Future work will be necessary to discover thresholds and set up automatic fault detection and diagnostics.

KW - fault detection and diagnosis

KW - virtual sensors

KW - HVAC

KW - smart buildings

KW - User-Computer Interface

KW - Algorithms

KW - Computer Simulation

KW - Denmark

KW - Ventilation

KW - Models, Statistical

KW - Equipment Failure Analysis

UR - https://www.mdpi.com/1424-8220/18/11/3931

U2 - 10.3390/s18113931

DO - 10.3390/s18113931

M3 - Journal article

C2 - 30441797

VL - 18

JO - Sensors

JF - Sensors

SN - 1424-8220

IS - 11

M1 - 3931

ER -