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

This article explains the use of supervised and unsupervised dictionary learning approaches on spread spectrum time domain (SSTDR) data to detect and locate disconnections in a PV array consisting of five panels. The aim is to decompose an SSTDR reflection signature into different components where each component has a physical interpretation, such as noise, environmental effects, and faults. In the unsupervised dictionary learning approach, the decomposed components are inspected to detect and localize faults. The maximum difference between actual and predicted location of the fault is 0.44 m on a system with five panels connected to an SSTDR box with a leader cable of 59.13 m and total length of 67.36 m including the effective length of the panels. In the supervised dictionary learning approach, the dictionary components are used to classify the SSTDR data to their respective fault types. Our results show a 97% accuracy using the supervised learning approach.

[1]  Siva Ramakrishna Madeti,et al.  A comprehensive study on different types of faults and detection techniques for solar photovoltaic system , 2017 .

[2]  M. Elad,et al.  $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation , 2006, IEEE Transactions on Signal Processing.

[3]  Terrence J. Sejnowski,et al.  Learning Overcomplete Representations , 2000, Neural Computation.

[4]  Mohammadreza Aghaei,et al.  Line-to-Line Faults Detection for Photovoltaic Arrays Based on I-V Curve Using Pattern Recognition , 2019, 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC).

[5]  Liang Zhao,et al.  Image de-noising based on learned dictionary , 2011, 2011 International Conference on Multimedia Technology.

[6]  Joseph F. Murray,et al.  Dictionary Learning Algorithms for Sparse Representation , 2003, Neural Computation.

[7]  N. Rajasekar,et al.  An MPPT-Based Sensorless Line–Line and Line–Ground Fault Detection Technique for PV Systems , 2019, IEEE Transactions on Power Electronics.

[8]  Yong-June Shin,et al.  Fault Diagnosis for Electrical Systems and Power Networks: A Review , 2021, IEEE Sensors Journal.

[9]  Bo Du,et al.  Image denoising based on learning over-complete dictionary , 2012, 2012 9th International Conference on Fuzzy Systems and Knowledge Discovery.

[10]  Pourya Shamsi,et al.  Dictionary learning for short-term prediction of solar PV production , 2015, 2015 IEEE Power & Energy Society General Meeting.

[11]  Maria Carmen Falvo,et al.  Secure faults detection for preventing fire risk in PV systems , 2014, 2014 International Carnahan Conference on Security Technology (ICCST).

[12]  Xilin Chen,et al.  Projection Metric Learning on Grassmann Manifold with Application to Video based Face Recognition , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Cynthia Furse,et al.  Spread Spectrum Time Domain Reflectometry for Complex Impedances: Application to PV Arrays , 2018, 2018 IEEE AUTOTESTCON.

[14]  Frede Blaabjerg,et al.  A Comparative Evaluation of Advanced Fault Detection Approaches for PV Systems , 2019, IEEE Journal of Photovoltaics.

[15]  Min Zhang,et al.  A image denoising algorithm based on sparse dictionary , 2017, 2017 7th IEEE International Conference on Electronics Information and Emergency Communication (ICEIEC).

[16]  Jay Johnson,et al.  PV arc-fault detection using spread spectrum time domain reflectometry (SSTDR) , 2014, 2014 IEEE Energy Conversion Congress and Exposition (ECCE).

[17]  Cynthia Furse,et al.  A critical comparison of reflectometry methods for location of wiring faults , 2006 .

[18]  V.P. Roychowdhury,et al.  An Information Theoretic Exploratory Method for Learning Patterns of Conditional Gene Coexpression from Microarray Data , 2008, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[19]  C. Furse,et al.  Analysis of spread spectrum time domain reflectometry for wire fault location , 2005, IEEE Sensors Journal.

[20]  Kjersti Engan,et al.  Method of optimal directions for frame design , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[21]  Joseph Kuitche,et al.  Quantification of Environmental Effects on PV Module Degradation: A Physics-Based Data-Driven Modeling Method , 2018, IEEE Journal of Photovoltaics.

[22]  Xiao-Yuan Jing,et al.  Super-resolution Person re-identification with semi-coupled low-rank discriminant dictionary learning , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Joel B. Harley,et al.  Spread Spectrum Time Domain Reflectometry With Lumped Elements on Asymmetric Transmission Lines , 2020, IEEE Sensors Journal.

[24]  Y. C. Pati,et al.  Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition , 1993, Proceedings of 27th Asilomar Conference on Signals, Systems and Computers.

[25]  Baoxin Li,et al.  Discriminative K-SVD for dictionary learning in face recognition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[26]  Michael Elad,et al.  Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries , 2006, IEEE Transactions on Image Processing.

[27]  A. Bruckstein,et al.  K-SVD : An Algorithm for Designing of Overcomplete Dictionaries for Sparse Representation , 2005 .

[28]  Fan Zhang,et al.  Detecting and localizing series arc fault in photovoltaic systems based on time and frequency characteristics of capacitor current , 2018, Solar Energy.

[29]  Joel B. Harley,et al.  Detection and Localization of Disconnections in PV Strings Using Spread-Spectrum Time-Domain Reflectometry , 2020, IEEE Journal of Photovoltaics.

[30]  Paul Smith,et al.  Spread spectrum sensors for critical fault location on live wire networks , 2005 .

[31]  Joel B. Harley,et al.  An Overview of Spread Spectrum Time Domain Reflectometry Responses to Photovoltaic Faults , 2020, IEEE Journal of Photovoltaics.

[32]  Bin Liu,et al.  Image Denoising Algorithm Based on Incoherent Dictionary Learning , 2016 .

[33]  Mehmet Koyutürk,et al.  Generalized and Mechanistic PV Module Performance Prediction From Computer Vision and Machine Learning on Electroluminescence Images , 2020, IEEE Journal of Photovoltaics.

[34]  David J. Kriegman,et al.  Acquiring linear subspaces for face recognition under variable lighting , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[35]  Shuying Yang,et al.  Automated Pipeline for Photovoltaic Module Electroluminescence Image Processing and Degradation Feature Classification , 2019, IEEE Journal of Photovoltaics.

[36]  Stéphane Mallat,et al.  Matching pursuits with time-frequency dictionaries , 1993, IEEE Trans. Signal Process..

[37]  Jay Johnson,et al.  PV ground-fault detection using spread spectrum time domain reflectometry (SSTDR) , 2013, 2013 IEEE Energy Conversion Congress and Exposition.

[38]  Jay Johnson,et al.  Photovoltaic ground fault detection recommendations for array safety and operation , 2016 .

[39]  Yuna Seo,et al.  Dictionary learning for dark image enhancement , 2012, 2012 9th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI).

[40]  Yu Wang,et al.  Impact of environmental variables on the degradation of photovoltaic components and perspectives for the reliability assessment methodology , 2020, Solar Energy.

[41]  Moussa Kafal,et al.  A Non Destructive Reflectometry Based Method for the Location and Characterization of Incipient Faults in Complex Unknown Wire Networks , 2018, 2018 IEEE AUTOTESTCON.

[42]  Maxime Mussard,et al.  Performance of solar photovoltaic modules under arid climatic conditions: A review , 2018, Solar Energy.

[43]  M. Elad,et al.  Improving the k-svd facial image compression using a linear deblocking method , 2008, 2008 IEEE 25th Convention of Electrical and Electronics Engineers in Israel.

[44]  Joel B. Harley,et al.  Measurement of Capacitance Using Spread Spectrum Time Domain Reflectometry (SSTDR) and Dictionary Matching , 2020, IEEE Sensors Journal.

[45]  Joel B. Harley,et al.  REFLECTOMETRY ON ASYMMETRIC TRANSMISSION LINE SYSTEMS , 2020, Progress In Electromagnetics Research M.

[46]  Rémi Gribonval,et al.  Learning unions of orthonormal bases with thresholded singular value decomposition , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..