Towards automated fault detection and diagnosis in district heating customers: generation and analysis of a labeled dataset with ground truth

Daniel Leiria; Kamilla Heimar Andersen; Simon Pommerencke Melgaard; Hicham Johra; Anna Marszal-Pomianowska; Marco Piscitelli; Alfonso Capozzoli; Michal Zbigniew Pomianowski

doi:10.26868/25222708.2023.1576

Towards automated fault detection and diagnosis in district heating customers: generation and analysis of a labeled dataset with ground truth

Daniel Leiria^*, Kamilla Heimar Andersen, Simon Pommerencke Melgaard, Hicham Johra, Anna Marszal-Pomianowska, Marco Piscitelli, Alfonso Capozzoli, Michal Zbigniew Pomianowski

^*Kontaktforfatter

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

74 Downloads (Pure)

Abstract

This study aims to develop a framework for automated fault detection and diagnosis (AFDD) in district heating (DH) substations by comprehensively understanding typical faults. AFDD is presently dependent on manual detection and diagnosis, leading to limitations. To address this issue, the study utilized data from 158 fault reports and smart heat meter data from residential buildings in Denmark to investigate common faults and conduct a fault impact assessment. The study suggests additional indicators for use by DH utility companies to detect anomalies in the future. The findings indicate that greater attention to fault detection and diagnosis can decrease energy usage and return temperatures, demonstrating the significance of AFDD implementation.

Originalsprog	Engelsk
Titel	Proceedings of Building Simulation 2023 : 18th Conference of International Building Performance Simulation Association. Shanghai, China, 4-6 September 2023
Antal sider	8
Vol/bind	18
Forlag	International Building Performance Simulation Association
Publikationsdato	sep. 2023
Sider	3620-3628
Artikelnummer	1576
ISBN (Elektronisk)	978-1-7750520-3-6
DOI	https://doi.org/10.26868/25222708.2023.1576
Status	Udgivet - sep. 2023
Begivenhed	IBPSA Building Simulation 2023 - Shanghai, Shanghai, Kina Varighed: 4 sep. 2023 → 6 sep. 2023 https://bs2023.org/

Konference

Konference	IBPSA Building Simulation 2023
Lokation	Shanghai
Land/Område	Kina
By	Shanghai
Periode	04/09/2023 → 06/09/2023
Internetadresse	https://bs2023.org/

Navn	Building Simulation Conference proceedings
Vol/bind	18
ISSN	2522-2708

FN’s Verdensmål

Denne publikation bidrager til følgende verdensmål

Adgang til dokumentet

10.26868/25222708.2023.1576

Leiria et al., 2023Forlagets udgivne version, 1,5 MB

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

Andre filer og links

Link to publication in Scopus

1 Afsluttet

PRELUDE: Prescient building Operation utilizing Real Time data for Energy Dynamic Optimization
Pomianowski, M. Z. (Projektkoordinator), Pereira, D. H. L. E. (Projektdeltager), Marszal-Pomianowska, A. (Projektdeltager), Johra, H. (Projektdeltager), Jensen, R. L. (Projektdeltager), Frandsen, M. (Projektdeltager), Holmene, C. F. (Projektleder), Veit, M. (Projektdeltager) & Rommerdahl Bock, A. (Projektleder)
01/12/2020 → 31/05/2024
Projekter: Projekt › Forskning

1 Organisering af eller deltagelse i konference

IBPSA Building Simulation 2023
Johra, H. (Deltager)
4 sep. 2023 → 6 sep. 2023
Aktivitet: Deltagelse i faglig begivenhed › Organisering af eller deltagelse i konference

1 Ph.d.-afhandling

From Smart Heat Meters to Diagnostics: Data-Driven Methodologies for Building Efficiency Assessment within District Heating
Leiria, D., 2024, Aalborg University Open Publishing. 150 s.
Publikation: Ph.d.-afhandling

Åben adgang
Fil

25 Downloads (Pure)

Citationsformater

Leiria, D., Andersen, K. H., Melgaard, S. P., Johra, H., Marszal-Pomianowska, A., Piscitelli, M., Capozzoli, A., & Pomianowski, M. Z. (2023). Towards automated fault detection and diagnosis in district heating customers: generation and analysis of a labeled dataset with ground truth. I Proceedings of Building Simulation 2023: 18th Conference of International Building Performance Simulation Association. Shanghai, China, 4-6 September 2023 (Bind 18, s. 3620-3628). Artikel 1576 International Building Performance Simulation Association. https://doi.org/10.26868/25222708.2023.1576

Leiria, Daniel ; Andersen, Kamilla Heimar ; Melgaard, Simon Pommerencke et al. / Towards automated fault detection and diagnosis in district heating customers : generation and analysis of a labeled dataset with ground truth. Proceedings of Building Simulation 2023: 18th Conference of International Building Performance Simulation Association. Shanghai, China, 4-6 September 2023. Bind 18 International Building Performance Simulation Association, 2023. s. 3620-3628 (Building Simulation Conference proceedings, Bind 18).

@inproceedings{9bcfbfd39cd94d44adab4088bf60e8c4,

title = "Towards automated fault detection and diagnosis in district heating customers: generation and analysis of a labeled dataset with ground truth",

abstract = "This study aims to develop a framework for automated fault detection and diagnosis (AFDD) in district heating (DH) substations by comprehensively understanding typical faults. AFDD is presently dependent on manual detection and diagnosis, leading to limitations. To address this issue, the study utilized data from 158 fault reports and smart heat meter data from residential buildings in Denmark to investigate common faults and conduct a fault impact assessment. The study suggests additional indicators for use by DH utility companies to detect anomalies in the future. The findings indicate that greater attention to fault detection and diagnosis can decrease energy usage and return temperatures, demonstrating the significance of AFDD implementation.",

keywords = "Smart heat data, 4th generation district heating, fault detection and diagnosis, Fault assessment reports",

author = "Daniel Leiria and Andersen, {Kamilla Heimar} and Melgaard, {Simon Pommerencke} and Hicham Johra and Anna Marszal-Pomianowska and Marco Piscitelli and Alfonso Capozzoli and Pomianowski, {Michal Zbigniew}",

note = "Authors retain the copyright while having granted IBPSA a nonexclusive right to publish the paper, but only in unmodified form. ; IBPSA Building Simulation 2023 ; Conference date: 04-09-2023 Through 06-09-2023",

year = "2023",

month = sep,

doi = "10.26868/25222708.2023.1576",

language = "English",

volume = "18",

series = "Building Simulation Conference proceedings",

publisher = "International Building Performance Simulation Association",

pages = "3620--3628",

booktitle = "Proceedings of Building Simulation 2023",

url = "https://bs2023.org/",

}

Leiria, D , Andersen, KH , Melgaard, SP , Johra, H , Marszal-Pomianowska, A, Piscitelli, M, Capozzoli, A & Pomianowski, MZ 2023, Towards automated fault detection and diagnosis in district heating customers: generation and analysis of a labeled dataset with ground truth. i Proceedings of Building Simulation 2023: 18th Conference of International Building Performance Simulation Association. Shanghai, China, 4-6 September 2023. bind 18, 1576, International Building Performance Simulation Association, Building Simulation Conference proceedings, bind 18, s. 3620-3628, IBPSA Building Simulation 2023, Shanghai, Kina, 04/09/2023. https://doi.org/10.26868/25222708.2023.1576

Towards automated fault detection and diagnosis in district heating customers: generation and analysis of a labeled dataset with ground truth. / Leiria, Daniel ; Andersen, Kamilla Heimar ; Melgaard, Simon Pommerencke et al.
Proceedings of Building Simulation 2023: 18th Conference of International Building Performance Simulation Association. Shanghai, China, 4-6 September 2023. Bind 18 International Building Performance Simulation Association, 2023. s. 3620-3628 1576 (Building Simulation Conference proceedings, Bind 18).

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

TY - GEN

T1 - Towards automated fault detection and diagnosis in district heating customers

T2 - IBPSA Building Simulation 2023

AU - Leiria, Daniel

AU - Andersen, Kamilla Heimar

AU - Melgaard, Simon Pommerencke

AU - Johra, Hicham

AU - Marszal-Pomianowska, Anna

AU - Piscitelli, Marco

AU - Capozzoli, Alfonso

AU - Pomianowski, Michal Zbigniew

N1 - Authors retain the copyright while having granted IBPSA a nonexclusive right to publish the paper, but only in unmodified form.

PY - 2023/9

Y1 - 2023/9

N2 - This study aims to develop a framework for automated fault detection and diagnosis (AFDD) in district heating (DH) substations by comprehensively understanding typical faults. AFDD is presently dependent on manual detection and diagnosis, leading to limitations. To address this issue, the study utilized data from 158 fault reports and smart heat meter data from residential buildings in Denmark to investigate common faults and conduct a fault impact assessment. The study suggests additional indicators for use by DH utility companies to detect anomalies in the future. The findings indicate that greater attention to fault detection and diagnosis can decrease energy usage and return temperatures, demonstrating the significance of AFDD implementation.

AB - This study aims to develop a framework for automated fault detection and diagnosis (AFDD) in district heating (DH) substations by comprehensively understanding typical faults. AFDD is presently dependent on manual detection and diagnosis, leading to limitations. To address this issue, the study utilized data from 158 fault reports and smart heat meter data from residential buildings in Denmark to investigate common faults and conduct a fault impact assessment. The study suggests additional indicators for use by DH utility companies to detect anomalies in the future. The findings indicate that greater attention to fault detection and diagnosis can decrease energy usage and return temperatures, demonstrating the significance of AFDD implementation.

KW - Smart heat data

KW - 4th generation district heating

KW - fault detection and diagnosis

KW - Fault assessment reports

UR - http://www.scopus.com/inward/record.url?scp=85179503955&partnerID=8YFLogxK

U2 - 10.26868/25222708.2023.1576

DO - 10.26868/25222708.2023.1576

M3 - Article in proceeding

VL - 18

T3 - Building Simulation Conference proceedings

SP - 3620

EP - 3628

BT - Proceedings of Building Simulation 2023

PB - International Building Performance Simulation Association

Y2 - 4 September 2023 through 6 September 2023

ER -

Leiria D , Andersen KH , Melgaard SP , Johra H , Marszal-Pomianowska A, Piscitelli M et al. Towards automated fault detection and diagnosis in district heating customers: generation and analysis of a labeled dataset with ground truth. I Proceedings of Building Simulation 2023: 18th Conference of International Building Performance Simulation Association. Shanghai, China, 4-6 September 2023. Bind 18. International Building Performance Simulation Association. 2023. s. 3620-3628. 1576. (Building Simulation Conference proceedings, Bind 18). doi: 10.26868/25222708.2023.1576

Towards automated fault detection and diagnosis in district heating customers: generation and analysis of a labeled dataset with ground truth

Abstract

Konference

FN’s Verdensmål

Adgang til dokumentet

AUB Link

Andre filer og links

Fingeraftryk

Projekter

PRELUDE: Prescient building Operation utilizing Real Time data for Energy Dynamic Optimization

Aktiviteter

IBPSA Building Simulation 2023

Publikation

From Smart Heat Meters to Diagnostics: Data-Driven Methodologies for Building Efficiency Assessment within District Heating

Citationsformater