I-V Curve Differences Image Classification by CNN for Failure Factor Determination in PV system

Shunya Hasegawa; Yuzuru Ueda

doi:10.1109/PVSC45281.2020.9300586

I-V Curve Differences Image Classification by CNN for Failure Factor Determination in PV system

Shunya Hasegawa, Yuzuru Ueda

Department of Electrical Engineering

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

2 Citations (Scopus)

Abstract

With a widespread of photovoltaic (PV) systems, a long-term use of the systems is expected. Since the amount of power generation can be decreased due to failures by various causes in the system, a practical way to detect the cause of the failure is needed for long-term uses of the system. This paper proposes a method to determine the cause of the failure in the PV system using convolutional neural network (CNN) by classifying the image of measured I-V curves which might have some failures. As a result, a case of the I-V curves which were caused by a stepped defect in a string unit was detected 100% correctly.

Original language	English
Title of host publication	2020 47th IEEE Photovoltaic Specialists Conference, PVSC 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	683-688
Number of pages	6
ISBN (Electronic)	9781728161150
DOIs	https://doi.org/10.1109/PVSC45281.2020.9300586
Publication status	Published - 14 Jun 2020
Event	47th IEEE Photovoltaic Specialists Conference, PVSC 2020 - Calgary, Canada Duration: 15 Jun 2020 → 21 Aug 2020

Publication series

Name	Conference Record of the IEEE Photovoltaic Specialists Conference
Volume	2020-June
ISSN (Print)	0160-8371

Conference

Conference	47th IEEE Photovoltaic Specialists Conference, PVSC 2020
Country/Territory	Canada
City	Calgary
Period	15/06/20 → 21/08/20

Keywords

CNN
I-V curve
PV system
failure determination

Access to Document

10.1109/PVSC45281.2020.9300586

Cite this

Hasegawa, S., & Ueda, Y. (2020). I-V Curve Differences Image Classification by CNN for Failure Factor Determination in PV system. In 2020 47th IEEE Photovoltaic Specialists Conference, PVSC 2020 (pp. 683-688). Article 9300586 (Conference Record of the IEEE Photovoltaic Specialists Conference; Vol. 2020-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PVSC45281.2020.9300586

@inproceedings{5285f803d4df4b4895f83261b234a201,

title = "I-V Curve Differences Image Classification by CNN for Failure Factor Determination in PV system",

abstract = "With a widespread of photovoltaic (PV) systems, a long-term use of the systems is expected. Since the amount of power generation can be decreased due to failures by various causes in the system, a practical way to detect the cause of the failure is needed for long-term uses of the system. This paper proposes a method to determine the cause of the failure in the PV system using convolutional neural network (CNN) by classifying the image of measured I-V curves which might have some failures. As a result, a case of the I-V curves which were caused by a stepped defect in a string unit was detected 100% correctly.",

keywords = "CNN, I-V curve, PV system, failure determination",

author = "Shunya Hasegawa and Yuzuru Ueda",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 47th IEEE Photovoltaic Specialists Conference, PVSC 2020 ; Conference date: 15-06-2020 Through 21-08-2020",

year = "2020",

month = jun,

day = "14",

doi = "10.1109/PVSC45281.2020.9300586",

language = "English",

series = "Conference Record of the IEEE Photovoltaic Specialists Conference",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "683--688",

booktitle = "2020 47th IEEE Photovoltaic Specialists Conference, PVSC 2020",

}

Hasegawa, S & Ueda, Y 2020, I-V Curve Differences Image Classification by CNN for Failure Factor Determination in PV system. in 2020 47th IEEE Photovoltaic Specialists Conference, PVSC 2020., 9300586, Conference Record of the IEEE Photovoltaic Specialists Conference, vol. 2020-June, Institute of Electrical and Electronics Engineers Inc., pp. 683-688, 47th IEEE Photovoltaic Specialists Conference, PVSC 2020, Calgary, Canada, 15/06/20. https://doi.org/10.1109/PVSC45281.2020.9300586

I-V Curve Differences Image Classification by CNN for Failure Factor Determination in PV system. / Hasegawa, Shunya; Ueda, Yuzuru.
2020 47th IEEE Photovoltaic Specialists Conference, PVSC 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 683-688 9300586 (Conference Record of the IEEE Photovoltaic Specialists Conference; Vol. 2020-June).

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

TY - GEN

T1 - I-V Curve Differences Image Classification by CNN for Failure Factor Determination in PV system

AU - Hasegawa, Shunya

AU - Ueda, Yuzuru

PY - 2020/6/14

Y1 - 2020/6/14

N2 - With a widespread of photovoltaic (PV) systems, a long-term use of the systems is expected. Since the amount of power generation can be decreased due to failures by various causes in the system, a practical way to detect the cause of the failure is needed for long-term uses of the system. This paper proposes a method to determine the cause of the failure in the PV system using convolutional neural network (CNN) by classifying the image of measured I-V curves which might have some failures. As a result, a case of the I-V curves which were caused by a stepped defect in a string unit was detected 100% correctly.

AB - With a widespread of photovoltaic (PV) systems, a long-term use of the systems is expected. Since the amount of power generation can be decreased due to failures by various causes in the system, a practical way to detect the cause of the failure is needed for long-term uses of the system. This paper proposes a method to determine the cause of the failure in the PV system using convolutional neural network (CNN) by classifying the image of measured I-V curves which might have some failures. As a result, a case of the I-V curves which were caused by a stepped defect in a string unit was detected 100% correctly.

KW - CNN

KW - I-V curve

KW - PV system

KW - failure determination

UR - http://www.scopus.com/inward/record.url?scp=85099590812&partnerID=8YFLogxK

U2 - 10.1109/PVSC45281.2020.9300586

DO - 10.1109/PVSC45281.2020.9300586

M3 - Conference contribution

AN - SCOPUS:85099590812

T3 - Conference Record of the IEEE Photovoltaic Specialists Conference

SP - 683

EP - 688

BT - 2020 47th IEEE Photovoltaic Specialists Conference, PVSC 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 47th IEEE Photovoltaic Specialists Conference, PVSC 2020

Y2 - 15 June 2020 through 21 August 2020

ER -

I-V Curve Differences Image Classification by CNN for Failure Factor Determination in PV system

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this