Abstract
This paper develops an automatic defect detection mechanism using texture feature analysis and supervised machine learning method to classify the failures in photovoltaic (PV) modules. The proposed technique adopts infrared thermography for identifying the anomalies on PV modules, and a fuzzy-based edge detection technique for detecting the orientation of PV modules with anomalies. Further, the gray level co-occurrence matrix is used for extracting texture features of the image. These extracted features are labelled and trained with the support vector machine classifier to classify the failure type in the PV modules. The classifier is trained with 99.9% accuracy and tested with multiple samples for three different scenarios to monitor the defects in modules. The average testing accuracy is 94.4% for all the samples in the testing scenario. The results show the advantage of the developed algorithm with early failure detection to prevent the catastrophes that would happen in the future.
Similar content being viewed by others
References
Alajmi M, Aljahdali S, Alsaheel S, Fattah M, Alshehri M (2019) Machine learning as an efficient diagnostic tool for fault detection and localization in solar photovoltaic arrays, pp 21–27. https://doi.org/10.29007/34bz
Alawad AM, Rahman FDA, Khalifa OO, Malek NA (2018) Fuzzy logic based edge detection method for image processing. Int J Electr Comput Eng 8(3):1863. https://doi.org/10.11591/ijece.v8i3.pp1863-1869
Aleem SA, Hussain SMS, Ustun TS (2020) A review of strategies to increase PV penetration level in smart grids. Energies 13(3):636. https://doi.org/10.3390/en13030636
Balasubramani G, Thangavelu V, Chinnusamy M, Subramaniam U, Padmanaban S, Mihet-Popa L (2020) Infrared thermography based defects testing of solar photovoltaic panel with fuzzy rule-based evaluation. Energies 13(6):1343. https://doi.org/10.3390/en13061343
Bartolucci F, Bacci S, Gnaldi M (2015) Statistical analysis of questionnaires a unified approach based on R and stata. Chapman and Hall/CRC, London
Bhoopathy R, Kunz O, Juhl M, Trupke T, Hameiri Z (2018) Outdoor photoluminescence imaging of photovoltaic modules with sunlight excitation. Prog Photovolt Res Appl 26(1):69–73. https://doi.org/10.1002/pip.2946
Deitsch S et al (2018) Automatic classification of defective photovoltaic module cells in electroluminescence images. Math Z. https://doi.org/10.1007/s00209-007-0206-4
Derive statistics from GLCM and plot correlation: MATLAB & Simulink—MathWorks India. https://in.mathworks.com/help/images/derive-statistics-from-glcm-and-plot-correlation.html. Accessed 26 May 2021
Devie A, Baure G, Dubarry M (2018) Intrinsic variability in the degradation of a batch of commercial 18650 lithium-ion cells. Energies 11(5):1031. https://doi.org/10.3390/en11051031
Dhimish M, Holmes V, Dales M (2016) Grid-connected PV virtual instrument system (GCPV-VIS) for detecting photovoltaic failure. In: 4th international symposium environment-friendly energies and applications EFEA 2016. https://doi.org/10.1109/EFEA.2016.7748777
Fadhel S et al (2019) PV shading fault detection and classification based on I-V curve using principal component analysis: application to isolated PV system. Sol. Energy 179:1–10. https://doi.org/10.1016/j.solener.2018.12.048
Ferroni F, Hopkirk RJ (2016) Energy return on energy invested (ERoEI) for photovoltaic solar systems in regions of moderate insolation. Energy Policy 94:336–344. https://doi.org/10.1016/j.enpol.2016.03.034
Fluke Corporation (2019) Fluke TiS45 infrared camera | Fluke. https://www.fluke.com/en-us/product/thermal-cameras/tis45. Accessed 23 Nov 2019
Gallardo-Saavedra S, Hernández-Callejo L, Duque-Perez O (2019) Analysis and characterization of PV module defects by thermographic inspection. Rev Fac Ing Univ Antioquia 93:92–104. https://doi.org/10.17533/udea.redin.20190517
Gallardo-Saavedra S et al (2020) Nondestructive characterization of solar PV cells defects by means of electroluminescence, infrared thermography, I–V curves and visual tests: experimental study and comparison. Energy 205:117930. https://doi.org/10.1016/j.energy.2020.117930
Gharakhani Siraki A, Pillay P (2012) Study of optimum tilt angles for solar panels in different latitudes for urban applications. Sol Energy 86(6):1920–1928. https://doi.org/10.1016/j.solener.2012.02.030
Global Market Outlook 2018–2022: SolarPower Europe. http://www.solarpowereurope.org/global-market-outlook-2018-2022/. Accessed 18 Jul 2019
Gotlieb CC, Herbert EK (2014) Texture descriptors based on co-occurrence matrices CALVIN. Comput Vis Graph Image Process 86:92741R. https://doi.org/10.1016/S0734-189X(05)80063-5
Gupta RP (1991) Digital image processing. In: Gupta RP (ed) Remote sensing geology. Springer, Berlin, pp 183–221
Haq I, Anwar S, Shah K, Khan MT, Shah SA (2015) Fuzzy logic based edge detection in smooth and noisy clinical images. PLoS ONE 10(9):e0138712. https://doi.org/10.1371/journal.pone.0138712
Haque A, Bharath KVS, Khan MA, Khan I, Jaffery ZA (2019) Fault diagnosis of photovoltaic modules. Energy Sci Eng 7(3):622–644. https://doi.org/10.1002/ese3.255
Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern SMC-3(6):610–621. https://doi.org/10.1109/TSMC.1973.4309314
Hu T, Zheng M, Tan J, Zhu L, Miao W (2015) Intelligent photovoltaic monitoring based on solar irradiance big data and wireless sensor networks. Ad Hoc Netw 35:127–136. https://doi.org/10.1016/j.adhoc.2015.07.004
International Electrotechnical Commission (2017) IEC TS 62446-3 (technical specification) photovoltaic (PV) systems: requirements for testing, documentation and maintenance—part 3: photovoltaic modules and plants—outdoor infrared thermography, 2017
Jäger-Waldau A (2019) Snapshot of photovoltaics—February 2019. Energies 12(5):769. https://doi.org/10.3390/en12050769
Karimi AM et al (2019) Automated pipeline for photovoltaic module electroluminescence image processing and degradation feature classification. IEEE J Photovolt 9(5):1324–1335. https://doi.org/10.1109/JPHOTOV.2019.2920732
Karmakar BK, Pradhan AK (2020) Detection and classification of faults in solar PV array using thevenin equivalent resistance. IEEE J. Photovolt 10(2):644–654. https://doi.org/10.1109/JPHOTOV.2019.2959951
Käsewieter J, Haase F, Larrodé MH, Köntges M (2014) Cracks in solar cell metallization leading to module power loss under mechanical loads. Energy Procedia 55:469–477. https://doi.org/10.1016/j.egypro.2014.08.011
Köntges M et al (2014) Review of failures of photovoltaic modules
Mercer J (1909) Functions of positive and negative type, and their connection with the theory of integral equations. Philos Trans R Soc A Math Phys Eng Sci 209(441–458):415–446. https://doi.org/10.1098/rsta.1909.0016
Milovanović B, Banjad Pečur I (2016) Review of active IR thermography for detection and characterization of defects in reinforced concrete. J Imaging 2(2):11. https://doi.org/10.3390/jimaging2020011
Morabito FC, Simone G, Cacciola M (2008) Image fusion techniques for non-destructive testing and remote sensing applications. In: Stathaki T (ed) Image fusion. Elsevier, Amsterdam, pp 367–392
Muttillo M, Nardi I, Stornelli V, de Rubeis T, Pasqualoni G, Ambrosini D (2020) On field infrared thermography sensing for PV system efficiency assessment: results and comparison with electrical models. Sensors 20(4):1055. https://doi.org/10.3390/s20041055
Naveen Venaktesh S, Sugumaran V (2021) Fault diagnosis of visual faults in photovoltaic modules: a review. Int J Green Energy 18(1):37–50. https://doi.org/10.1080/15435075.2020.1825443
Omazic A et al (2019) Relation between degradation of polymeric components in crystalline silicon PV module and climatic conditions: a literature review. Sol Energy Mater Sol Cells 192:123–133. https://doi.org/10.1016/j.solmat.2018.12.027
Ortega E, Aranguren G, Jimeno JC (2019) New monitoring method to characterize individual modules in large photovoltaic systems. Sol Energy 193:906–914. https://doi.org/10.1016/j.solener.2019.09.099
Orujov F, Maskeliūnas R, Damaševičius R, Wei W (2020) Fuzzy based image edge detection algorithm for blood vessel detection in retinal images. Appl Soft Comput 94:106452. https://doi.org/10.1016/j.asoc.2020.106452
TÜV Rheinland (2015) Quality monitor solar 2015
Sangwongwanich A, Yang Y, Sera D, Blaabjerg F (2018) Lifetime evaluation of grid-connected PV inverters considering panel degradation rates and installation sites. IEEE Trans. Power Electron. 33(2):1125–1236. https://doi.org/10.1109/TPEL.2017.2678169
Savas C, Dovis F (2019) The impact of different kernel functions on the performance of scintillation detection based on support vector machines. Sensors 19(23):5219. https://doi.org/10.3390/s19235219
Solar PV module faults and failings—EE Publishers. https://www.ee.co.za/article/solar-pv-module-faults-failings.html. Accessed 18 Jul 2019
Sovetkin E, Steland A (2019) Automatic processing and solar cell detection in photovoltaic electroluminescence images. Integr Comput Aided Eng 26(2):123–137. https://doi.org/10.3233/ICA-180588
Swanson R et al (2005) The surface polarization effect in high- efficiency silicon solar cells. In: 15th international photovoltaic science & engineering conference (PVSEC-15), 2005, pp 4–7
Tang Xiaoou (1998) Texture information in run-length matrices. IEEE Trans Image Process 7(11):1602–1609. https://doi.org/10.1109/83.725367
Texture analysis using the gray-level co-occurrence matrix (GLCM): MATLAB & Simulink—MathWorks India. https://in.mathworks.com/help/images/texture-analysis-using-the-gray-level-co-occurrence-matrix-glcm.html. Accessed 26 May 2021
Train Classification Models in Classification Learner App: MATLAB & Simulink—MathWorks India. https://in.mathworks.com/help/stats/train-classification-models-in-classification-learner-app.html#bu3xete. Accessed 26 May 2021
Tsanakas JA, Chrysostomou D, Botsaris PN, Gasteratos A (2015) Fault diagnosis of photovoltaic modules through image processing and Canny edge detection on field thermographic measurements. Int J Sustain Energy 34(6):351–372. https://doi.org/10.1080/14786451.2013.826223
Usamentiaga R, Venegas P, Guerediaga J, Vega L, Molleda J, Bulnes F (2014) Infrared thermography for temperature measurement and non-destructive testing. Sensors 14(7):12305–12348. https://doi.org/10.3390/s140712305
Zhang P, Wang Y, Xiao W, Li W (2012) Reliability evaluation of grid-connected photovoltaic power systems. IEEE Trans Sustain Energy 3(3):379–389. https://doi.org/10.1109/TSTE.2012.2186644
Zhang K, Zhang Y, Wang P, Tian Y, Yang J (2018) An improved Sobel edge algorithm and FPGA implementation. Procedia Comput Sci 131:243–248. https://doi.org/10.1016/j.procs.2018.04.209
Zheng Z, Zha B, Xuchen Y, Yuan H, Gao Y, Zhang H (2019) Adaptive edge detection algorithm based on grey entropy theory and textural features. IEEE Access 7:92943–92954. https://doi.org/10.1109/ACCESS.2019.2927655
Funding
There is no funding associated with this research.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
There are no potential conflicts of interest to be disclosed with this research.
Ethical approval
This research doesn’t involve human participants and/or animals.
Informed consent
There is no informed consent associated with this research.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Kurukuru, V.S.B., Haque, A., Tripathy, A.K. et al. Machine learning framework for photovoltaic module defect detection with infrared images. Int J Syst Assur Eng Manag 13, 1771–1787 (2022). https://doi.org/10.1007/s13198-021-01544-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13198-021-01544-7