A Stair-Step Probabilistic Approach for Automatic Anomaly Detection in Building Ventilation System Operation

Emil Kjøller Alexandersen, Mathis Riber Skydt, Sebastian Skals Engelsgaard, Mads Bang, Muhyiddine Jradi, Hamid Reza Shaker*

*Kontaktforfatter for dette arbejde

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

Resumé

HVAC systems contribute to a large part of energy consumption in buildings and studies suggest that savings up to 30% can be achieved by utilising the potential of FDD methods which aim to identify faults and their root causes. In particular, model-based FDD are becoming more useful as the modelling and simulation of complex building systems have been eased due to advancements within the field. However, methods often lack the ability of effectively distinguishing between healthy and abnormal operation and some are highly subject to human evaluation. Bang et al. proposed a model-based fault detection method for automatic identification of abnormal energy performance on a daily basis in building ventilation units using a statistical definition of abnormality based on the Chernoff bound. The method enables the fault detection process to be automated which removes the need for human evaluation. However, the method is governed by linear interpolation leading to uncertain identification of abnormal operation and imprecise probability calculations, thereby triggering the need for modifications. This work upgrades the model-based fault detection method by introducing a stair-step approach to more accurately identify abnormal behaviour. The outcomes of the upgraded approach are reported for a case study building and evaluated in comparison with the original method. The improved method shows correct identification of abnormal periods and detected the precise day of a faulty occupancy counter. Moreover, it shows that the ascribed probabilities of the original approach are consequently lower for the two analysed ventilation units by an average of 13 and 15% points, respectively.

OriginalsprogEngelsk
TidsskriftBuilding and Environment
Vol/bind157
Sider (fra-til)165-171
ISSN0360-1323
DOI
StatusUdgivet - 15. jun. 2019

Fingeraftryk

Stairs
Fault detection
Ventilation
ventilation
building
anomaly
detection method
Identification (control systems)
Interpolation
Energy utilization
abnormality
interpolation
detection
method
savings
evaluation
energy consumption
energy
simulation
modeling

Citer dette

Alexandersen, Emil Kjøller ; Skydt, Mathis Riber ; Engelsgaard, Sebastian Skals ; Bang, Mads ; Jradi, Muhyiddine ; Shaker, Hamid Reza. / A Stair-Step Probabilistic Approach for Automatic Anomaly Detection in Building Ventilation System Operation. I: Building and Environment. 2019 ; Bind 157. s. 165-171.
@article{69aabfb7a1a1448aa9bc348399e9c20b,
title = "A Stair-Step Probabilistic Approach for Automatic Anomaly Detection in Building Ventilation System Operation",
abstract = "HVAC systems contribute to a large part of energy consumption in buildings and studies suggest that savings up to 30{\%} can be achieved by utilising the potential of FDD methods which aim to identify faults and their root causes. In particular, model-based FDD are becoming more useful as the modelling and simulation of complex building systems have been eased due to advancements within the field. However, methods often lack the ability of effectively distinguishing between healthy and abnormal operation and some are highly subject to human evaluation. Bang et al. proposed a model-based fault detection method for automatic identification of abnormal energy performance on a daily basis in building ventilation units using a statistical definition of abnormality based on the Chernoff bound. The method enables the fault detection process to be automated which removes the need for human evaluation. However, the method is governed by linear interpolation leading to uncertain identification of abnormal operation and imprecise probability calculations, thereby triggering the need for modifications. This work upgrades the model-based fault detection method by introducing a stair-step approach to more accurately identify abnormal behaviour. The outcomes of the upgraded approach are reported for a case study building and evaluated in comparison with the original method. The improved method shows correct identification of abnormal periods and detected the precise day of a faulty occupancy counter. Moreover, it shows that the ascribed probabilities of the original approach are consequently lower for the two analysed ventilation units by an average of 13 and 15{\%} points, respectively.",
keywords = "Building performance, Chernoff bound, Fault detection and diagnostics, Stair-step approach, Ventilation systems",
author = "Alexandersen, {Emil Kj{\o}ller} and Skydt, {Mathis Riber} and Engelsgaard, {Sebastian Skals} and Mads Bang and Muhyiddine Jradi and Shaker, {Hamid Reza}",
year = "2019",
month = "6",
day = "15",
doi = "10.1016/j.buildenv.2019.04.036",
language = "English",
volume = "157",
pages = "165--171",
journal = "Building and Environment",
issn = "0360-1323",
publisher = "Pergamon Press",

}

A Stair-Step Probabilistic Approach for Automatic Anomaly Detection in Building Ventilation System Operation. / Alexandersen, Emil Kjøller; Skydt, Mathis Riber; Engelsgaard, Sebastian Skals; Bang, Mads; Jradi, Muhyiddine; Shaker, Hamid Reza.

I: Building and Environment, Bind 157, 15.06.2019, s. 165-171.

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

TY - JOUR

T1 - A Stair-Step Probabilistic Approach for Automatic Anomaly Detection in Building Ventilation System Operation

AU - Alexandersen, Emil Kjøller

AU - Skydt, Mathis Riber

AU - Engelsgaard, Sebastian Skals

AU - Bang, Mads

AU - Jradi, Muhyiddine

AU - Shaker, Hamid Reza

PY - 2019/6/15

Y1 - 2019/6/15

N2 - HVAC systems contribute to a large part of energy consumption in buildings and studies suggest that savings up to 30% can be achieved by utilising the potential of FDD methods which aim to identify faults and their root causes. In particular, model-based FDD are becoming more useful as the modelling and simulation of complex building systems have been eased due to advancements within the field. However, methods often lack the ability of effectively distinguishing between healthy and abnormal operation and some are highly subject to human evaluation. Bang et al. proposed a model-based fault detection method for automatic identification of abnormal energy performance on a daily basis in building ventilation units using a statistical definition of abnormality based on the Chernoff bound. The method enables the fault detection process to be automated which removes the need for human evaluation. However, the method is governed by linear interpolation leading to uncertain identification of abnormal operation and imprecise probability calculations, thereby triggering the need for modifications. This work upgrades the model-based fault detection method by introducing a stair-step approach to more accurately identify abnormal behaviour. The outcomes of the upgraded approach are reported for a case study building and evaluated in comparison with the original method. The improved method shows correct identification of abnormal periods and detected the precise day of a faulty occupancy counter. Moreover, it shows that the ascribed probabilities of the original approach are consequently lower for the two analysed ventilation units by an average of 13 and 15% points, respectively.

AB - HVAC systems contribute to a large part of energy consumption in buildings and studies suggest that savings up to 30% can be achieved by utilising the potential of FDD methods which aim to identify faults and their root causes. In particular, model-based FDD are becoming more useful as the modelling and simulation of complex building systems have been eased due to advancements within the field. However, methods often lack the ability of effectively distinguishing between healthy and abnormal operation and some are highly subject to human evaluation. Bang et al. proposed a model-based fault detection method for automatic identification of abnormal energy performance on a daily basis in building ventilation units using a statistical definition of abnormality based on the Chernoff bound. The method enables the fault detection process to be automated which removes the need for human evaluation. However, the method is governed by linear interpolation leading to uncertain identification of abnormal operation and imprecise probability calculations, thereby triggering the need for modifications. This work upgrades the model-based fault detection method by introducing a stair-step approach to more accurately identify abnormal behaviour. The outcomes of the upgraded approach are reported for a case study building and evaluated in comparison with the original method. The improved method shows correct identification of abnormal periods and detected the precise day of a faulty occupancy counter. Moreover, it shows that the ascribed probabilities of the original approach are consequently lower for the two analysed ventilation units by an average of 13 and 15% points, respectively.

KW - Building performance

KW - Chernoff bound

KW - Fault detection and diagnostics

KW - Stair-step approach

KW - Ventilation systems

U2 - 10.1016/j.buildenv.2019.04.036

DO - 10.1016/j.buildenv.2019.04.036

M3 - Journal article

VL - 157

SP - 165

EP - 171

JO - Building and Environment

JF - Building and Environment

SN - 0360-1323

ER -