Efficient fault diagnosis approach for solar photovoltaic array using a convolutional neural network in combination of generative adversarial network under small dataset

Lu, X; Lin, Y; Lin, P; He, X; Fang, G; Cheng, S; Chen, Z; Wu, L

Efficient fault diagnosis approach for solar photovoltaic array using a convolutional neural network in combination of generative adversarial network under small dataset

Lu, X Lin, Y Lin, P He, X Fang, G

Cheng, S Chen, Z Wu, L

Permalink

Publisher:: Elsevier
Publication Type:: Journal Article
Citation:: Solar Energy, 2023, 253, pp. 360-374
Issue Date:: 2023-03-15

Closed Access

	Filename	Description	Size
	1-s2.0-S0038092X22009082-main.pdf	Published version	8.84 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Lu, X
dc.contributor.author	Lin, Y
dc.contributor.author	Lin, P
dc.contributor.author	He, X
dc.contributor.author	Fang, G https://orcid.org/0000-0003-0845-6718
dc.contributor.author	Cheng, S
dc.contributor.author	Chen, Z
dc.contributor.author	Wu, L
dc.date.accessioned	2024-04-23T21:50:32Z
dc.date.available	2024-04-23T21:50:32Z
dc.date.issued	2023-03-15
dc.identifier.citation	Solar Energy, 2023, 253, pp. 360-374
dc.identifier.issn	0038-092X
dc.identifier.uri	http://hdl.handle.net/10453/178305
dc.description.abstract	Accurate faults diagnosis for photovoltaic (PV) array is one of the vital factors that guarantee the reliable operation of PV power plant. Artificial intelligence (AI) based fault detection and diagnosis (FDD) models are promising techniques. In order to automatically extract the faults features from the raw electrical data of PV array and create efficient FDD model with small dataset, a FDD scheme using Wasserstein generative adversarial network (WGAN) and convolutional neural network (CNN) is designed. The proposed FDD model is consisting of three modules, a discriminator, a generator and a classifier for fault diagnosis. By analyzing sequential PV data in a 2-Dimension way, the proposed discriminator and generator learn the distribution of PV data under various PV system operations. Then they are utilized to generate more labeled samples to improve the performance of the CNN based classifier. Thus, the proposed FDD model can be trained only requiring minor labeled samples. A laboratory grid-connected PV system is established to experimentally investigate the performance of the developed method. The results demonstrate that the designed FDD model can accurately diagnose line-line and open circuit faults.
dc.language	en
dc.publisher	Elsevier
dc.relation.ispartof	Solar Energy
dc.relation.isbasedon	10.1016/j.solener.2022.12.037
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	09 Engineering, 12 Built Environment and Design
dc.subject.classification	Energy
dc.subject.classification	33 Built environment and design
dc.subject.classification	40 Engineering
dc.title	Efficient fault diagnosis approach for solar photovoltaic array using a convolutional neural network in combination of generative adversarial network under small dataset
dc.type	Journal Article
utslib.citation.volume	253
utslib.for	09 Engineering
utslib.for	12 Built Environment and Design
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Strength - GBDTC - Global Big Data Technologies
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
utslib.copyright.status	closed_access	*
dc.date.updated	2024-04-23T21:49:58Z
pubs.publication-status	Published
pubs.volume	253

Abstract:

Accurate faults diagnosis for photovoltaic (PV) array is one of the vital factors that guarantee the reliable operation of PV power plant. Artificial intelligence (AI) based fault detection and diagnosis (FDD) models are promising techniques. In order to automatically extract the faults features from the raw electrical data of PV array and create efficient FDD model with small dataset, a FDD scheme using Wasserstein generative adversarial network (WGAN) and convolutional neural network (CNN) is designed. The proposed FDD model is consisting of three modules, a discriminator, a generator and a classifier for fault diagnosis. By analyzing sequential PV data in a 2-Dimension way, the proposed discriminator and generator learn the distribution of PV data under various PV system operations. Then they are utilized to generate more labeled samples to improve the performance of the CNN based classifier. Thus, the proposed FDD model can be trained only requiring minor labeled samples. A laboratory grid-connected PV system is established to experimentally investigate the performance of the developed method. The results demonstrate that the designed FDD model can accurately diagnose line-line and open circuit faults.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/178305