A machine learning approach to fault detection in district heating substations

Sara Månsson; Per Olof Johansson Kallioniemi; Kerstin Sernhed; Marcus Thern

doi:10.1016/j.egypro.2018.08.187

A machine learning approach to fault detection in district heating substations

Sara Månsson, Per Olof Johansson Kallioniemi, Kerstin Sernhed, Marcus Thern

Flemish Institute for Technological Research

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

Abstract

The aim of this study is to develop a model capable of predicting the behavior of a district heating substation, including being able to distinguish datasets from well performing substations from datasets containing faults. The model developed in the study is based on machine learning algorithms and the model is trained on data from a Swedish district heating substation. A number of different models and input/output parameters are tested in the study. The results show that the model is capable of modelling the substation behavior, and that the fault detection capability of the model is high.

Original language	English
Title of host publication	16th International Symposium on District Heating and Cooling, DHC2018, 9–12 September 2018, Hamburg, Germany
Pages	226-235
Number of pages	10
Volume	149
DOIs	https://doi.org/10.1016/j.egypro.2018.08.187
Publication status	Published - 2018
Event	16th International Symposium on District Heating and Cooling, DHC 2018 - Hamburg, Germany Duration: 2018 Sept 9 → 2018 Sept 12

Publication series

Name	Energy Procedia
Publisher	Elsevier
ISSN (Print)	1876-6102

Conference

Conference	16th International Symposium on District Heating and Cooling, DHC 2018
Country/Territory	Germany
City	Hamburg
Period	2018/09/09 → 2018/09/12

Subject classification (UKÄ)

Energy Systems

Free keywords

District heating substations
fault detection
machine learning

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.egypro.2018.08.187

1 Doctoral Thesis (compilation)

Spot the difference! On the way towards automated fault handling in district heating buildings
Månsson, S., 2021, Energy Sciences, Lund University. 99 p.
Research output: Thesis › Doctoral Thesis (compilation)

Open Access
File

Cite this

@inproceedings{c4f2b0ac70094f04973b6b7b36415938,

title = "A machine learning approach to fault detection in district heating substations",

abstract = "The aim of this study is to develop a model capable of predicting the behavior of a district heating substation, including being able to distinguish datasets from well performing substations from datasets containing faults. The model developed in the study is based on machine learning algorithms and the model is trained on data from a Swedish district heating substation. A number of different models and input/output parameters are tested in the study. The results show that the model is capable of modelling the substation behavior, and that the fault detection capability of the model is high.",

keywords = "District heating substations, fault detection, machine learning",

author = "Sara M{\aa}nsson and Kallioniemi, {Per Olof Johansson} and Kerstin Sernhed and Marcus Thern",

year = "2018",

doi = "10.1016/j.egypro.2018.08.187",

language = "English",

volume = "149",

series = "Energy Procedia",

publisher = "Elsevier",

pages = "226--235",

booktitle = "16th International Symposium on District Heating and Cooling, DHC2018, 9–12 September 2018, Hamburg, Germany",

note = "16th International Symposium on District Heating and Cooling, DHC 2018 ; Conference date: 09-09-2018 Through 12-09-2018",

}

Månsson, S, Kallioniemi, POJ, Sernhed, K & Thern, M 2018, A machine learning approach to fault detection in district heating substations. in 16th International Symposium on District Heating and Cooling, DHC2018, 9–12 September 2018, Hamburg, Germany. vol. 149, Energy Procedia, pp. 226-235, 16th International Symposium on District Heating and Cooling, DHC 2018, Hamburg, Germany, 2018/09/09. https://doi.org/10.1016/j.egypro.2018.08.187

A machine learning approach to fault detection in district heating substations. / Månsson, Sara; Kallioniemi, Per Olof Johansson; Sernhed, Kerstin et al.
16th International Symposium on District Heating and Cooling, DHC2018, 9–12 September 2018, Hamburg, Germany. Vol. 149 2018. p. 226-235 (Energy Procedia).

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

TY - GEN

T1 - A machine learning approach to fault detection in district heating substations

AU - Månsson, Sara

AU - Kallioniemi, Per Olof Johansson

AU - Sernhed, Kerstin

AU - Thern, Marcus

PY - 2018

Y1 - 2018

N2 - The aim of this study is to develop a model capable of predicting the behavior of a district heating substation, including being able to distinguish datasets from well performing substations from datasets containing faults. The model developed in the study is based on machine learning algorithms and the model is trained on data from a Swedish district heating substation. A number of different models and input/output parameters are tested in the study. The results show that the model is capable of modelling the substation behavior, and that the fault detection capability of the model is high.

AB - The aim of this study is to develop a model capable of predicting the behavior of a district heating substation, including being able to distinguish datasets from well performing substations from datasets containing faults. The model developed in the study is based on machine learning algorithms and the model is trained on data from a Swedish district heating substation. A number of different models and input/output parameters are tested in the study. The results show that the model is capable of modelling the substation behavior, and that the fault detection capability of the model is high.

KW - District heating substations

KW - fault detection

KW - machine learning

U2 - 10.1016/j.egypro.2018.08.187

DO - 10.1016/j.egypro.2018.08.187

M3 - Paper in conference proceeding

AN - SCOPUS:85054087074

VL - 149

T3 - Energy Procedia

SP - 226

EP - 235

BT - 16th International Symposium on District Heating and Cooling, DHC2018, 9–12 September 2018, Hamburg, Germany

T2 - 16th International Symposium on District Heating and Cooling, DHC 2018

Y2 - 9 September 2018 through 12 September 2018

ER -

A machine learning approach to fault detection in district heating substations

Abstract

Publication series

Conference

Subject classification (UKÄ)

Free keywords

UN SDGs

Access to Document

Fingerprint

Research output

Spot the difference! On the way towards automated fault handling in district heating buildings

Cite this