Fault Detection of Supermarket Refrigeration Systems Using Convolutional Neural Network

Zahra Soltani; Kresten Kjaer Soerensen; John Leth; Jan Dimon Bendtsen

doi:10.1109/IECON43393.2020.9254485

Fault Detection of Supermarket Refrigeration Systems Using Convolutional Neural Network

Zahra Soltani, Kresten Kjaer Soerensen, John Leth, Jan Dimon Bendtsen

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

3 Citationer (Scopus)

106 Downloads (Pure)

Abstract

The functionality of supermarket refrigeration systems (SRS) has a significant impact on the quality of food products and potentially human health. Automatic fault detection and diagnosis of SRS is desired by manufacturers and customers as performance is improved, and energy consumption and cost is lowered. In this work, Convolutional Neural Networks (CNN) are applied for fault detection and diagnosis of SRS. The network is found to be able to classify the fault with 99% accuracy. The sensitivity of the designed model to data quality is also assessed. The results show that the model can classify faults at low sample rates if the training set is large enough. Moreover, the model displays low sensitivity to data quality such as noisy and perturbed validation data, and the frequency of false positives is satisfactorily low as well.

Originalsprog	Engelsk
Titel	IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society
Antal sider	8
Forlag	IEEE Computer Society Press
Publikationsdato	18 okt. 2020
Sider	231-238
Artikelnummer	9254485
ISBN (Trykt)	978-1-7281-5415-2
ISBN (Elektronisk)	978-1-7281-5414-5
DOI	https://doi.org/10.1109/IECON43393.2020.9254485
Status	Udgivet - 18 okt. 2020
Begivenhed	46th Annual Conference of the IEEE Industrial Electronics Society, IECON 2020 - Virtual, Singapore, Singapore Varighed: 18 okt. 2020 → 21 okt. 2020 http://www.conferences.academicjournals.org/cat/physical-sciences/46th-annual-conference-of-the-ieee-industrial-electronics-society

Konference

Konference	46th Annual Conference of the IEEE Industrial Electronics Society, IECON 2020
Land/Område	Singapore
By	Virtual, Singapore
Periode	18/10/2020 → 21/10/2020
Sponsor	IEEE Industrial Electronics Society (IES), SPECS - Smart Grid + Power Electronics Consortium Singapore, The Institute of Electrical and Electronics Engineers (IEEE)
Internetadresse	http://www.conferences.academicjournals.org/cat/physical-sciences/46th-annual-conference-of-the-ieee-industrial-electronics-society

Navn	Proceedings of the Annual Conference of the IEEE Industrial Electronics Society
ISSN	1553-572X

Bibliografisk note

Funding Information:
This work is partially funded by Innovations fund Denmark and supported by Bitzer electronics A/S, Denmark.

Publisher Copyright:
© 2020 IEEE.

Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.

Adgang til dokumentet

10.1109/IECON43393.2020.9254485

Accepted manuscriptAccepteret manuskript, 928 KB

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

Andre filer og links

Link to publication in Scopus

3 Citationer
1 Ph.d.-afhandling

Automatic fault detection and diagnosis in refrigeration systems, A data-driven approach
Soltani, Z., 2023, Aalborg Universitetsforlag. 161 s.
Publikation: Ph.d.-afhandling

Åben adgang
Fil

118 Downloads (Pure)

Citationsformater

@inproceedings{2b63ba3f8517438692c9a4fba9e07591,

title = "Fault Detection of Supermarket Refrigeration Systems Using Convolutional Neural Network",

abstract = "The functionality of supermarket refrigeration systems (SRS) has a significant impact on the quality of food products and potentially human health. Automatic fault detection and diagnosis of SRS is desired by manufacturers and customers as performance is improved, and energy consumption and cost is lowered. In this work, Convolutional Neural Networks (CNN) are applied for fault detection and diagnosis of SRS. The network is found to be able to classify the fault with 99% accuracy. The sensitivity of the designed model to data quality is also assessed. The results show that the model can classify faults at low sample rates if the training set is large enough. Moreover, the model displays low sensitivity to data quality such as noisy and perturbed validation data, and the frequency of false positives is satisfactorily low as well.",

keywords = "classification, convolutioal, data quality, evaporation, fault, machine learning, neural network, refrigeration",

author = "Zahra Soltani and Soerensen, {Kresten Kjaer} and John Leth and Bendtsen, {Jan Dimon}",

note = "Funding Information: This work is partially funded by Innovations fund Denmark and supported by Bitzer electronics A/S, Denmark. Publisher Copyright: {\textcopyright} 2020 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; 46th Annual Conference of the IEEE Industrial Electronics Society, IECON 2020 ; Conference date: 18-10-2020 Through 21-10-2020",

year = "2020",

month = oct,

day = "18",

doi = "10.1109/IECON43393.2020.9254485",

language = "English",

isbn = "978-1-7281-5415-2",

series = "Proceedings of the Annual Conference of the IEEE Industrial Electronics Society",

publisher = "IEEE Computer Society Press",

pages = "231--238",

booktitle = "IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society",

address = "United States",

url = "http://www.conferences.academicjournals.org/cat/physical-sciences/46th-annual-conference-of-the-ieee-industrial-electronics-society",

}

Soltani, Z, Soerensen, KK, Leth, J & Bendtsen, JD 2020, Fault Detection of Supermarket Refrigeration Systems Using Convolutional Neural Network. i IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society., 9254485, IEEE Computer Society Press, Proceedings of the Annual Conference of the IEEE Industrial Electronics Society, s. 231-238, 46th Annual Conference of the IEEE Industrial Electronics Society, IECON 2020, Virtual, Singapore, Singapore, 18/10/2020. https://doi.org/10.1109/IECON43393.2020.9254485

Fault Detection of Supermarket Refrigeration Systems Using Convolutional Neural Network. / Soltani, Zahra; Soerensen, Kresten Kjaer; Leth, John et al.
IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society. IEEE Computer Society Press, 2020. s. 231-238 9254485 (Proceedings of the Annual Conference of the IEEE Industrial Electronics Society).

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

TY - GEN

T1 - Fault Detection of Supermarket Refrigeration Systems Using Convolutional Neural Network

AU - Soltani, Zahra

AU - Soerensen, Kresten Kjaer

AU - Leth, John

AU - Bendtsen, Jan Dimon

N1 - Funding Information: This work is partially funded by Innovations fund Denmark and supported by Bitzer electronics A/S, Denmark. Publisher Copyright: © 2020 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.

PY - 2020/10/18

Y1 - 2020/10/18

N2 - The functionality of supermarket refrigeration systems (SRS) has a significant impact on the quality of food products and potentially human health. Automatic fault detection and diagnosis of SRS is desired by manufacturers and customers as performance is improved, and energy consumption and cost is lowered. In this work, Convolutional Neural Networks (CNN) are applied for fault detection and diagnosis of SRS. The network is found to be able to classify the fault with 99% accuracy. The sensitivity of the designed model to data quality is also assessed. The results show that the model can classify faults at low sample rates if the training set is large enough. Moreover, the model displays low sensitivity to data quality such as noisy and perturbed validation data, and the frequency of false positives is satisfactorily low as well.

AB - The functionality of supermarket refrigeration systems (SRS) has a significant impact on the quality of food products and potentially human health. Automatic fault detection and diagnosis of SRS is desired by manufacturers and customers as performance is improved, and energy consumption and cost is lowered. In this work, Convolutional Neural Networks (CNN) are applied for fault detection and diagnosis of SRS. The network is found to be able to classify the fault with 99% accuracy. The sensitivity of the designed model to data quality is also assessed. The results show that the model can classify faults at low sample rates if the training set is large enough. Moreover, the model displays low sensitivity to data quality such as noisy and perturbed validation data, and the frequency of false positives is satisfactorily low as well.

KW - classification

KW - convolutioal

KW - data quality

KW - evaporation

KW - fault

KW - machine learning

KW - neural network

KW - refrigeration

UR - http://www.scopus.com/inward/record.url?scp=85097780696&partnerID=8YFLogxK

U2 - 10.1109/IECON43393.2020.9254485

DO - 10.1109/IECON43393.2020.9254485

M3 - Article in proceeding

AN - SCOPUS:85097780696

SN - 978-1-7281-5415-2

T3 - Proceedings of the Annual Conference of the IEEE Industrial Electronics Society

SP - 231

EP - 238

BT - IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society

PB - IEEE Computer Society Press

T2 - 46th Annual Conference of the IEEE Industrial Electronics Society, IECON 2020

Y2 - 18 October 2020 through 21 October 2020

ER -

Soltani Z, Soerensen KK, Leth J , Bendtsen JD. Fault Detection of Supermarket Refrigeration Systems Using Convolutional Neural Network. I IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society. IEEE Computer Society Press. 2020. s. 231-238. 9254485. (Proceedings of the Annual Conference of the IEEE Industrial Electronics Society). doi: 10.1109/IECON43393.2020.9254485

Fault Detection of Supermarket Refrigeration Systems Using Convolutional Neural Network

Abstract

Konference

Bibliografisk note

Adgang til dokumentet

AUB Link

Andre filer og links

Fingeraftryk

Publikation

Automatic fault detection and diagnosis in refrigeration systems, A data-driven approach

Citationsformater