Anomaly Detection of Disconnects Using SSTDR and Variational Autoencoders

Edun, Ayobami S.; LaFlamme, Cody; Kingston, Samuel R.; Furse, Cynthia M.; Scarpulla, Michael A.; Harley, Joel B.

doi:10.1109/jsen.2022.3140922

Title: Anomaly Detection of Disconnects Using SSTDR and Variational Autoencoders

Journal Article · 05 January 2022 · IEEE Sensors Journal

DOI: https://doi.org/10.1109/jsen.2022.3140922 · OSTI ID:2234308

^[1];

^[2]; Kingston, Samuel R. ^[3];

^[4];

^[3];

^[2]

University of Florida, Gainesville, FL (United States); University of Florida
University of Florida, Gainesville, FL (United States)
University of Utah, Salt Lake City, UT (United States)
University of Utah, Salt Lake City, UT (United States); LiveWire Test Labs, Inc., Salt Lake City, UT (United States)

This article utilizes variational autoencoder (VAE) and spread spectrum time domain reflectometry (SSTDR) to detect, isolate, and characterize anomalous data (or faults) in a photovoltaic (PV) array. The goal is to learn the distribution of non-faulty input signals, inspect the reconstruction error of test signals, flag anomalies, and then locate or characterize the anomalous data using a predicted baseline rather than a fixed baseline that might be too rigid. The use of VAE handles imbalanced data better than other methods used for classification of PV faults because of its unsupervised nature. Here, we consider only disconnects in this work, and our results show an overall accuracy of 96% for detecting true negatives (non-faulty data), a 99% true positive rate of detecting anomalies, 0.997 area under the ROC curve, 0.99 area under the precision-recall curve, and a maximum percentage absolute relative error of 0.40% in locating the faults on a 5-panel setup with a 59.13 m leader cable.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: University of Utah, Salt Lake City, UT (United States)

Sponsoring Organization:: USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Solar Energy Technologies Office

Grant/Contract Number:: EE0008169

OSTI ID:: 2234308

Journal Information:: IEEE Sensors Journal, Journal Name: IEEE Sensors Journal Journal Issue: 4 Vol. 22; ISSN 1530-437X

Publisher:: IEEECopyright Statement

Country of Publication:: United States

Language:: English

References (24)

Latent Space Expanded Variational Autoencoder for Sentence Generation Song, Tianbao; Sun, Jingbo; Chen, Bo IEEE Access, Vol. 7 https://doi.org/10.1109/ACCESS.2019.2944630	journal	January 2019
Online Fault Diagnosis for Photovoltaic Arrays Based on Fisher Discrimination Dictionary Learning for Sparse Representation Xi, Peng; Lin, Peijie; Lin, Yaohai IEEE Access, Vol. 9 https://doi.org/10.1109/ACCESS.2021.3059431	journal	January 2021
Detection of Degraded/Aged Cell in a Li-ion Battery Pack using Spread Spectrum Time Domain Reflectometry (SSTDR) Roy, Sourov; Khan, Faisal 2020 IEEE Applied Power Electronics Conference and Exposition (APEC) https://doi.org/10.1109/APEC39645.2020.9124341	conference	March 2020
A Non Destructive Reflectometry Based Method for the Location and Characterization of Incipient Faults in Complex Unknown Wire Networks Kafal, Moussa; Mustapha, Fatme; Ben Hassen, Wafa 2018 IEEE AUTOTESTCON https://doi.org/10.1109/AUTEST.2018.8532500	conference	September 2018
Variational Autoencoder Based Fault Detection and Location Method for Power Distribution Network Wang, Xuhong; Cui, Ping; Du, Ying 2020 8th International Conference on Condition Monitoring and Diagnosis (CMD) https://doi.org/10.1109/CMD48350.2020.9287286	conference	October 2020
A Recurrent Variational Autoencoder for Speech Enhancement Leglaive, Simon; Alameda-Pineda, Xavier; Girin, Laurent ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) https://doi.org/10.1109/ICASSP40776.2020.9053164	conference	May 2020
Transfer Learning from Synthetic to Real Images Using Variational Autoencoders for Precise Position Detection Inoue, Tadanobu; Choudhury, Subhajit; De Magistris, Giovanni 2018 25th IEEE International Conference on Image Processing (ICIP) https://doi.org/10.1109/ICIP.2018.8451064	conference	October 2018
Improving clustering based anomaly detection with concave hull: An application in fault diagnosis of wind turbines Li, Peng; Niggemann, Oliver 2016 IEEE 14th International Conference on Industrial Informatics (INDIN) https://doi.org/10.1109/INDIN.2016.7819205	conference	July 2016
Anomaly Warning and Fault Detection in DC Pico-grid with enhanced k-Nearest Neighbours Technique Quek, Y. T.; Woo, W. L.; Logenthiran, T. 2018 IEEE Innovative Smart Grid Technologies - Asia (ISGT Asia) https://doi.org/10.1109/ISGT-Asia.2018.8467961	conference	May 2018
Detection and Localization of Disconnections in PV Strings Using Spread-Spectrum Time-Domain Reflectometry Saleh, Mashad Uddin; Deline, Chris; Kingston, Samuel IEEE Journal of Photovoltaics, Vol. 10, Issue 1 https://doi.org/10.1109/JPHOTOV.2019.2953392	journal	January 2020
An Overview of Spread Spectrum Time Domain Reflectometry Responses to Photovoltaic Faults Saleh, Mashad Uddin; Deline, Chris; Benoit, Evan IEEE Journal of Photovoltaics, Vol. 10, Issue 3 https://doi.org/10.1109/JPHOTOV.2020.2972356	journal	May 2020
A Shadow Fault Diagnosis Method Based on the Quantitative Analysis of Photovoltaic Output Prediction Error Zhou, Siyu; Mao, Mingxuan; Zhou, Lin IEEE Journal of Photovoltaics, Vol. 10, Issue 4 https://doi.org/10.1109/JPHOTOV.2020.2995041	journal	July 2020
Detection and Localization of Disconnections in a Large-Scale String of Photovoltaics Using SSTDR Edun, Ayobami; Kingston, Samuel; LaFlamme, Cody IEEE Journal of Photovoltaics, Vol. 11, Issue 4 https://doi.org/10.1109/JPHOTOV.2021.3081437	journal	July 2021
Quantifying the Environmental Sensitivity of SSTDR Signals for Monitoring PV Strings LaFlamme, Cody; Benoit, Evan; Edun, Ayobami IEEE Journal of Photovoltaics, Vol. 12, Issue 1 https://doi.org/10.1109/JPHOTOV.2021.3127465	journal	January 2022
The invisible fray: a critical analysis of the use of reflectometry for fray location Griffiths, L. A.; Parakh, R.; Furse, C. IEEE Sensors Journal, Vol. 6, Issue 3 https://doi.org/10.1109/JSEN.2006.874017	journal	June 2006
A New Algorithm for Wire Fault Location Using Time-Domain Reflectometry Shi, Qinghai; Kanoun, Olfa IEEE Sensors Journal, Vol. 14, Issue 4 https://doi.org/10.1109/JSEN.2013.2294193	journal	April 2014
Spread Spectrum Time Domain Reflectometry With Lumped Elements on Asymmetric Transmission Lines Edun, Ayobami S.; Tumkur Jayakumar, Naveen Kumar; Kingston, Samuel R. IEEE Sensors Journal, Vol. 21, Issue 2 https://doi.org/10.1109/JSEN.2020.2967894	journal	January 2021
Finding Faults in PV Systems: Supervised and Unsupervised Dictionary Learning With SSTDR Edun, Ayobami S.; LaFlamme, Cody; Kingston, Samuel R. IEEE Sensors Journal, Vol. 21, Issue 4 https://doi.org/10.1109/JSEN.2020.3029707	journal	February 2021
Detecting Microcracks in Photovoltaics Silicon Wafers using Varitional Autoencoder Liu, Zhe; Oviedo, Felipe; Sachs, Emanuel M. 2020 47th IEEE Photovoltaic Specialists Conference (PVSC) https://doi.org/10.1109/PVSC45281.2020.9300366	conference	June 2020
Online Two-Section PV Array Fault Diagnosis With Optimized Voltage Sensor Locations Hu, Yihua; Zhang, Jiangfeng; Cao, Wenping IEEE Transactions on Industrial Electronics, Vol. 62, Issue 11 https://doi.org/10.1109/TIE.2015.2448066	journal	November 2015
Fault Diagnosis in Photovoltaic Arrays Using GBSSL Method and Proposing a Fault Correction System Momeni, Hosna; Sadoogi, Nasser; Farrokhifar, Meisam IEEE Transactions on Industrial Informatics, Vol. 16, Issue 8 https://doi.org/10.1109/TII.2019.2908992	journal	August 2020
Degradation Detection of Thermally Aged SiC and Si Power MOSFETs using Spread Spectrum Time Domain Reflectometry (SSTDR) Hanif, Abu; Khan, Faisal 2018 IEEE 6th Workshop on Wide Bandgap Power Devices and Applications (WiPDA) https://doi.org/10.1109/WiPDA.2018.8569099	conference	October 2018
On Information and Sufficiency Kullback, S.; Leibler, R. A. The Annals of Mathematical Statistics, Vol. 22, Issue 1 https://doi.org/10.1214/aoms/1177729694	journal	March 1951
Short-Term Forecasting of Photovoltaic Solar Power Production Using Variational Auto-Encoder Driven Deep Learning Approach Dairi, Abdelkader; Harrou, Fouzi; Sun, Ying Applied Sciences, Vol. 10, Issue 23 https://doi.org/10.3390/app10238400	journal	November 2020

Similar Records

A Model for SSTDR Signal Propagation Through Photovoltaic Strings

Journal Article · 2020 · IEEE Journal of Photovoltaics · OSTI ID:2234339

Ellis, Hunter D.; Saleh, Mashad Uddin; Kingston, Samuel R.; +4 more

Finding Faults in PV Systems: Supervised and Unsupervised Dictionary Learning With SSTDR

Journal Article · 2020 · IEEE Sensors Journal · OSTI ID:2234298

Edun, Ayobami S.; LaFlamme, Cody; Kingston, Samuel R.; +5 more

Quantifying the Environmental Sensitivity of SSTDR Signals for Monitoring PV Strings

Journal Article · 2021 · IEEE Journal of Photovoltaics · OSTI ID:2234307

LaFlamme, Cody; Benoit, Evan; Edun, Ayobami; +4 more

Related Subjects

14 SOLAR ENERGY
SSTDR
Variational autoencoders
disconnects
faults
reflectometry

Title: Anomaly Detection of Disconnects Using SSTDR and Variational Autoencoders

Citation Formats

References (24)

Similar Records

Related Subjects