Enhanced Fault Identification in Solar Panels through Binary Cascaded Convolutional Classifiers with Thermal-Visual Image Augmentation

PDF (2232KB), PP.1-13

Views: 0 Downloads: 0

Author(s)

Sujata P. Pathak 1,* Sonali A. Patil 1

1. K J Somaiya School of Engineering (formerly known as K J Somaiya College of Engineering), Somaiya Vidyavihar University, Vidyavihar, Mumbai, 400077, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijigsp.2025.04.01

Received: 14 Apr. 2024 / Revised: 20 Jun. 2024 / Accepted: 3 May 2025 / Published: 8 Aug. 2025

Index Terms

Binary Cascaded Convolutional Neural Network, CNN, Image Augmentation, Solar Energy, Solar Panel Fault Detection

Abstract

Solar power stands as a pivotal renewable energy source for the twenty-first century. However, the optimal functioning of solar panels is often hindered by various faults, necessitating accurate and early defect detection to maximize energy production. Existing solar panel fault identification models encounter challenges such as low precision, difficulty in distinguishing fault types, and poor generalization due to limited and unbalanced data samples. This paper introduces a novel and effective approach, leveraging a Binary Cascaded Convolutional Classifier augmented with visual and thermal image combinations to address these limitations. The proposed model adeptly classifies five distinct types of solar panel faults, including single cell hotspots, diode hotspots, dust/ shadow hotspots, multicell hotspots, and Potential-Induced Degradation (PID) hotspots. Through image augmentation techniques like rotation, shifting, sheering, resizing, jittering, and blurring applied to visual and thermal images, inter-class feature variance is increased. Binary Cascaded Convolutional Neural Network (BCCNN) classifiers are trained using an enriched dataset, each specifically designed to differentiate between dust/ shadow hotspots and other fault categories. The adoption of a binary method significantly enhances precision, allowing for focused fault identification and classification. The proposed model surpasses existing literature in terms of precision (99.8%), accuracy (98.5%) and recall (98.4%), underscoring its effectiveness across all five fault classes. In summary, this research marks a substantial advancement in the realm of solar panel fault identification, presenting a more precise and effective fault detection methodology that has the potential to significantly enhance the maintenance and longevity of solar energy systems.

Cite This Paper

Sujata P. Pathak, Sonali A. Patil, "Enhanced Fault Identification in Solar Panels through Binary Cascaded Convolutional Classifiers with Thermal-Visual Image Augmentation", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.17, No.4, pp. 1-13, 2025. DOI:10.5815/ijigsp.2025.04.01

Reference

[1]V., M. C., and P. P. S. Jamuna, “Fault Detection for Photovoltaic Panels in Solar Power Plants by Using Linear Iterative Fault Diagnosis (LIFD) Technique Based on Thermal Imaging System,” Journal of Electrical Engineering & Technology, vol. 18, no. 4, pp. 3091–3103, Jul. 2023.
[2]A. Bouzaher, A. Terki, and M. T. Bouzaher, “Photovoltaic Panel Faults Diagnosis: Based on the Fill Factor Analysis and Use of Artificial Intelligence Techniques,” Arab J Sci Eng, vol. 48, no. 5, pp. 6471–6487, May 2023, doi: 10.1007/s13369-022-07409-w.
[3]S. Ganesan, P. W. David, P. K. Balachandran, and T. Senjyu, “Fault identification scheme for solar photovoltaic array in bridge and honeycomb configuration,” Electrical Engineering, vol. 105, no. 4, pp. 2443–2460, Aug. 2023, doi: 10.1007/s00202-023-01816-4.
[4]V. Arunachalam, J. Karthickraja, and S. Senthamizh Selvan, “Wavelet transform based detection, classification and location of faults in a PV array,” J Ambient Intell Humaniz Comput, vol. 14, no. 8, pp. 11227–11237, Aug. 2023, doi: 10.1007/s12652-023-04628-3.
[5]K. , D. P. K. & S. M. Anjaiah, “Analysis of Arc Faults and Utility Disturbances in a Multiple Photovoltaic-Based DC Ring Microgrid by Using Improved MFDFA,” ran J Sci Technol Trans Electr Eng, vol. 47, pp. 1343–1363, Jul. 2023.
[6]C. R. Manoj and S. E. Jose, “An Integrated EMVO and ARBFN Algorithms for Output Power Forecasting and Fault Prediction in Solar PV Systems,” Journal of Electrical Engineering & Technology, vol. 18, no. 5, pp. 3443–3455, Sep. 2023, doi: 10.1007/s42835-023-01429-8.
[7]A. S. Maihulla and I. Yusuf, “Reliability and performance prediction of a small serial solar photovoltaic system for rural consumption using the Gumbel-Hougaard family copula,” Life Cycle Reliability and Safety Engineering, vol. 10, no. 4, pp. 347–354, Dec. 2021, doi: 10.1007/s41872-021-00176-x.
[8]H. Akinci and A. Y. Özalp, “Optimal site selection for solar photovoltaic power plants using geographical information systems and fuzzy logic approach: a case study in Artvin, Turkey,” Arabian Journal of Geosciences, vol. 15, no. 9, May 2022, doi: 10.1007/s12517-022-10129-y.
[9]M. A. Günen, “Determination of the suitable sites for constructing solar photovoltaic (PV) power plants in Kayseri, Turkey using GIS-based ranking and AHP methods,” Environmental Science and Pollution Research, vol. 28, no. October 2021, pp. 57232–57247, 2021, doi: 10.1007/s11356-021-14622-x/Published.
[10]S. S. R. Moustafa, A. Mohamed, H. E. Abdelhafiez, K. El-Faragawy, and S. Ali, “A fusion approach for evaluating ground conditions for seismic microzoning at the Egyptian Solar Park in Benban, Aswan,” Environ Earth Sci, vol. 82, no. 12, Jun. 2023, doi: 10.1007/s12665-023-10968-2.
[11]V. S. B. Kurukuru, A. Haque, A. K. Tripathy, and M. A. Khan, “Machine learning framework for photovoltaic module defect detection with infrared images,” International Journal of System Assurance Engineering and Management, vol. 13, no. 4, pp. 1771–1787, Aug. 2022, doi: 10.1007/s13198-021-01544-7.
[12]P. D. Muthusamy, G. Velusamy, S. Thandavan, B. R. Govindasamy, and N. Savarimuthu, “Industrial Internet of things-based solar photo voltaic cell waste management in next generation industries,” Environmental Science and Pollution Research, vol. 29, no. 24. Springer Science and Business Media Deutschland GmbH, pp. 35542–35556, May 01, 2022. doi: 10.1007/s11356-022-19411-8.
[13]W. Junchao and Z. Chang, “Defect detection on solar cells using mathematical morphology and fuzzy logic techniques,” Journal of Optics (India), 2023, doi: 10.1007/s12596-023-01162-5.
[14]J. J. Bommer, “Earthquake hazard and risk analysis for natural and induced seismicity: towards objective assessments in the face of uncertainty,” Bulletin of Earthquake Engineering, vol. 20, no. 6, pp. 2825–3069, Apr. 2022, doi: 10.1007/s10518-022-01357-4.
[15]E. A. Attia, A. Mahmoud, M. Fedawy, and Y. H. El-Sharkawy, “Instant testing and non-contact diagnosis for photovoltaic cells using K-means clustering and associated hyperspectral imaging,” SN Appl Sci, vol. 5, no. 8, Aug. 2023, doi: 10.1007/s42452-023-05431-7.
[16]S. Shapsough, M. Takrouri, R. Dhaouadi, and I. A. Zualkernan, “Using IoT and smart monitoring devices to optimize the efficiency of large-scale distributed solar farms,” Wireless Networks, vol. 27, no. 6, pp. 4313–4329, Aug. 2021, doi: 10.1007/s11276-018-01918-z.
[17]M. Naseri, M. S. Hussaini, M. W. Iqbal, H. A. Jawadi, and M. Puya, “Spatial modeling of solar photovoltaic power plant in Kabul, Afghanistan,” J Mt Sci, vol. 18, no. 12, pp. 3291–3305, Dec. 2021, doi: 10.1007/s11629-021-7035-5.
[18]G. Zhang, S. Qiu, and F. Wang, “Adaptive Fuzzy Fault-Tolerant Control of Flexible Spacecraft with Rotating Appendages,” International Journal of Fuzzy Systems, vol. 25, no. 1, pp. 326–337, Feb. 2023, doi: 10.1007/s40815-022-01338-4.
[19]B.-G. Chae and H.-U. Oh, “Development of Power Plant Trio CanSat Platform Powered by Solar, Wind and Piezo Energy Harvesting Systems,” International Journal of Aeronautical and Space Sciences, vol. 22, no. 6, pp. 1464–1480, Dec. 2021, doi: 10.1007/s42405-021-00382-y.
[20]Y. S. Shugay and K. B. Kaportseva, “Forecast of the Quasi-Stationary and Transient Solar Wind Streams Based on Solar Observations in 2010,” Geomagnetism and Aeronomy, vol. 61, no. 2, pp. 158–168, Mar. 2021, doi: 10.1134/S001679322102016X.
[21]S. Beroual and M. Hrairi, “Electromechanical Impedance Simulation-Based Evaluation of Cracks in Photovoltaic Solar Cells,” Arab J Sci Eng, vol. 48, no. 9, pp. 12313–12329, Sep. 2023, doi: 10.1007/s13369-023-07733-9.
[22]S. Orsini et al., “SERENA: Particle Instrument Suite for Determining the Sun-Mercury Interaction from BepiColombo,” Space Science Reviews, vol. 217, no. 1. Springer Science and Business Media B.V., Feb. 01, 2021. doi: 10.1007/s11214-020-00787-3.
[23]M. A. El-Rashidy, “An efficient and portable solar cell defect detection system,” Neural Comput Appl, vol. 34, no. 21, pp. 18497–18509, Nov. 2022, doi: 10.1007/s00521-022-07464-2.
[24]S. Ndjakomo Essiane, P. J. Gnetchejo, P. Ele, and Z. Chen, “Faults detection and identification in PV array using kernel principal components analysis,” International Journal of Energy and Environmental Engineering, vol. 13, no. 1, pp. 153–178, Mar. 2022, doi: 10.1007/s40095-021-00416-x.
[25]N. P. Sebi, “Intelligent Solar Irradiance Forecasting Using Hybrid Deep Learning Model: A Meta-Heuristic-Based Prediction,” Neural Process Lett, vol. 55, no. 2, pp. 1247–1280, Apr. 2023, doi: 10.1007/s11063-022-10935-1.
[26]A. Sohail, N. Ul Islam, A. Ul Haq, S. Ul Islam, I. Shafi, and J. Park, “Fault detection and computation of power in PV cells under faulty conditions using deep-learning,” Energy Reports, vol. 9, pp. 4325–4336, Dec. 2023, doi: 10.1016/j.egyr.2023.03.094.
[27]S. Lee, K. E. An, B. D. Jeon, K. Y. Cho, S. J. Lee, and D. Seo, “Detecting faulty solar panels based on thermal image processing,” in 2018 IEEE International Conference on Consumer Electronics (ICCE), IEEE, Jan. 2018, pp. 1–2. doi: 10.1109/ICCE.2018.8326228.
[28]V. Kirubakaran et al., “Infrared Thermal Images of Solar PV Panels for Fault Identification Using Image Processing Technique,” International Journal of Photoenergy, vol. 2022, 2022, doi: 10.1155/2022/6427076.
[29]T. G. Amaral, V. F. Pires, and A. J. Pires, “Fault detection in pv tracking systems using an image processing algorithm based on pca,” Energies (Basel), vol. 14, no. 21, Nov. 2021, doi: 10.3390/en14217278.
[30]K. Natarajan, B. Praveen Kumar, V. Sampath Kumar, and P. Kumar, “Fault Detection of Solar PV system using SVM and Thermal Image Processing,” 2020.