Adverse Condition and Critical Event Prediction in Commercial Buildings: Danish Case Study

Søren Egedorf, Hamid Reza Shaker, Rodney A. Martin, Bo Nørregaard Jørgensen

Research output: Contribution to journalJournal articleResearchpeer-review

124 Downloads (Pure)

Abstract

Over the last two decades, there has been a growing realization that the actual energy performances of many buildings fail to meet the original intent of building design. Faults in systems and equipment, incorrectly configured control systems and inappropriate operating procedures increase the energy consumption about 20% and therefore compromise the building energy performance. To improve the energy performance of buildings and to prevent occupant discomfort, adverse condition and critical event prediction plays an important role. The Adverse Condition and Critical Event Prediction Toolbox (ACCEPT) is a generic framework to compare and contrast methods that enable prediction of an adverse event, with low false alarm and missed detection rates. In this paper, ACCEPT is used for fault detection and prediction in a real building at the University of Southern Denmark. To make fault detection and prediction possible, machine learning methods such as Kernel Density Estimation (KDE), and Principal Component Analysis (PCA) are used. A new PCA–based method is developed for artificial fault generation. While the proposed method finds applications in different areas, it has been used primarily for analysis purposes in this work. The results are evaluated, discussed and compared with results from Canonical Variate Analysis (CVA) with KDE. The results show that ACCEPT is more powerful than CVA with KDE which is known to be one of the best multivariate data-driven techniques in particular, under dynamically changing operational conditions.
Original languageEnglish
Article number10
JournalEnergy Informatics
Volume1
Number of pages19
ISSN2520-8942
DOIs
Publication statusPublished - 2018

Fingerprint

Fault detection
Principal component analysis
Learning systems
Energy utilization
Control systems

Cite this

@article{62c05b798eaa4de3adb1fadf589aa654,
title = "Adverse Condition and Critical Event Prediction in Commercial Buildings: Danish Case Study",
abstract = "Over the last two decades, there has been a growing realization that the actual energy performances of many buildings fail to meet the original intent of building design. Faults in systems and equipment, incorrectly configured control systems and inappropriate operating procedures increase the energy consumption about 20{\%} and therefore compromise the building energy performance. To improve the energy performance of buildings and to prevent occupant discomfort, adverse condition and critical event prediction plays an important role. The Adverse Condition and Critical Event Prediction Toolbox (ACCEPT) is a generic framework to compare and contrast methods that enable prediction of an adverse event, with low false alarm and missed detection rates. In this paper, ACCEPT is used for fault detection and prediction in a real building at the University of Southern Denmark. To make fault detection and prediction possible, machine learning methods such as Kernel Density Estimation (KDE), and Principal Component Analysis (PCA) are used. A new PCA–based method is developed for artificial fault generation. While the proposed method finds applications in different areas, it has been used primarily for analysis purposes in this work. The results are evaluated, discussed and compared with results from Canonical Variate Analysis (CVA) with KDE. The results show that ACCEPT is more powerful than CVA with KDE which is known to be one of the best multivariate data-driven techniques in particular, under dynamically changing operational conditions.",
author = "S{\o}ren Egedorf and Shaker, {Hamid Reza} and Martin, {Rodney A.} and J{\o}rgensen, {Bo N{\o}rregaard}",
year = "2018",
doi = "10.1186/s42162-018-0015-5",
language = "English",
volume = "1",
journal = "Energy Informatics",
issn = "2520-8942",
publisher = "Springer",

}

Adverse Condition and Critical Event Prediction in Commercial Buildings: Danish Case Study. / Egedorf, Søren; Shaker, Hamid Reza; Martin, Rodney A. ; Jørgensen, Bo Nørregaard.

In: Energy Informatics, Vol. 1, 10, 2018.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Adverse Condition and Critical Event Prediction in Commercial Buildings: Danish Case Study

AU - Egedorf, Søren

AU - Shaker, Hamid Reza

AU - Martin, Rodney A.

AU - Jørgensen, Bo Nørregaard

PY - 2018

Y1 - 2018

N2 - Over the last two decades, there has been a growing realization that the actual energy performances of many buildings fail to meet the original intent of building design. Faults in systems and equipment, incorrectly configured control systems and inappropriate operating procedures increase the energy consumption about 20% and therefore compromise the building energy performance. To improve the energy performance of buildings and to prevent occupant discomfort, adverse condition and critical event prediction plays an important role. The Adverse Condition and Critical Event Prediction Toolbox (ACCEPT) is a generic framework to compare and contrast methods that enable prediction of an adverse event, with low false alarm and missed detection rates. In this paper, ACCEPT is used for fault detection and prediction in a real building at the University of Southern Denmark. To make fault detection and prediction possible, machine learning methods such as Kernel Density Estimation (KDE), and Principal Component Analysis (PCA) are used. A new PCA–based method is developed for artificial fault generation. While the proposed method finds applications in different areas, it has been used primarily for analysis purposes in this work. The results are evaluated, discussed and compared with results from Canonical Variate Analysis (CVA) with KDE. The results show that ACCEPT is more powerful than CVA with KDE which is known to be one of the best multivariate data-driven techniques in particular, under dynamically changing operational conditions.

AB - Over the last two decades, there has been a growing realization that the actual energy performances of many buildings fail to meet the original intent of building design. Faults in systems and equipment, incorrectly configured control systems and inappropriate operating procedures increase the energy consumption about 20% and therefore compromise the building energy performance. To improve the energy performance of buildings and to prevent occupant discomfort, adverse condition and critical event prediction plays an important role. The Adverse Condition and Critical Event Prediction Toolbox (ACCEPT) is a generic framework to compare and contrast methods that enable prediction of an adverse event, with low false alarm and missed detection rates. In this paper, ACCEPT is used for fault detection and prediction in a real building at the University of Southern Denmark. To make fault detection and prediction possible, machine learning methods such as Kernel Density Estimation (KDE), and Principal Component Analysis (PCA) are used. A new PCA–based method is developed for artificial fault generation. While the proposed method finds applications in different areas, it has been used primarily for analysis purposes in this work. The results are evaluated, discussed and compared with results from Canonical Variate Analysis (CVA) with KDE. The results show that ACCEPT is more powerful than CVA with KDE which is known to be one of the best multivariate data-driven techniques in particular, under dynamically changing operational conditions.

U2 - 10.1186/s42162-018-0015-5

DO - 10.1186/s42162-018-0015-5

M3 - Journal article

VL - 1

JO - Energy Informatics

JF - Energy Informatics

SN - 2520-8942

M1 - 10

ER -