Health Monitoring and Fault Detection in Photovoltaic Systems in Central Greece Using Artificial Neural Networks
Source abstract
Abstract
The operation and maintenance of a photovoltaic system is a challenging task that requires scientific soundness, and has significant economic impact. Faults in photovoltaic systems are a common phenomenon that demands fast diagnosis and repair. The effective and accurate diagnosis and categorization of faults is based on information received from the photovoltaic plant monitoring and energy management system. This paper presents the application of machine learning techniques in the processing of monitoring datasets of grid connected systems in order to diagnose faults. In particular, monitoring data from four photovoltaic parks located in Central Greece are analyzed. The existing data are divided for training and validation procedures. Different scenarios are examined first, in order to observe and quantify the behavior of artificial neural networks in already known faults. In this process, the faults are divided in three main categories. The system’s performance deviation against the prediction of the trained artificial neural network in each fault category is processed by health monitoring methodology in order to specify it quantitatively.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Photovoltaic System Optimization Techniques · Solar Radiation and Photovoltaics · Power System Reliability and Maintenance
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Mechanical Engineering, University of Thessaly, 383 34 Volos, Greece
References (37)
Show source-provided references
1. (2022, July 11). DAPEEP_SA. Greek Renewable Energy Sources Operator & Issuer of Guarantees of Origin. Available online: https://www.dapeep.gr/.
2. Romero, H.F.M., Rebollo, M.G., Cardeñoso-Payo, V., Gómez, V.A., Plaza, A.R., Moyo, R.T., and Hernández-Callejo, L. (2022). Applications of Artificial Intelligence to Photovoltaic Systems: A Review. Appl. Sci., 12.10.3390/app121910056 ↗
3. A comprehensive study on different types of faults and detection techniques for solar photovoltaic system10.1016/j.solener.2017.08.069 ↗
4. Jaen-Cuellar, A.Y., Elvira-Ortiz, D.A., Osornio-Rios, R.A., and Antonino-Daviu, J.A. (2022). Advances in Fault Condition Monitoring for Solar Photovoltaic and Wind Turbine Energy Generation: A Review. Energies, 15.10.3390/en15155404 ↗
5. Kumaradurai, A., Teekaraman, Y., Coosemans, T., and Messagie, M. (2020, January 18–21). Fault Detection in Photovoltaic Systems Using Machine Learning Algorithms: A Review. Proceedings of the 2020 8th International Conference on Orange Technology (ICOT), Daegu, Republic of Korea.10.1109/ICOT51877.2020.9468768 ↗
6. Statistical fault detection in photovoltaic systems10.1016/j.solener.2017.04.043 ↗
7. Stamatelos Anastassios, On-site Inspection of PV Panels, Aided by Infrared Thermography
8. Machine Learning Platform for Profiling and Forecasting at Microgrid Level10.2478/ecce-2019-0004 ↗
9. Automatic fault detection in grid connected PV systems10.1016/j.solener.2013.05.001 ↗
10. Fault detection algorithm for grid-connected photovoltaic plants10.1016/j.solener.2016.08.021 ↗
11. Hopwood, M.W., Patel, L., and Gunda, T. (2022). Classification of Photovoltaic Failures with Hidden Markov Modeling, an Unsupervised Statistical Approach. Energies, 15.10.3390/en15145104 ↗
12. Fault detection method for grid-connected photovoltaic plants10.1016/j.renene.2013.11.073 ↗
13. Damage Identification of Bridge Structures Considering Temperature Variations-Based SVM and MFO10.1061/(ASCE)AS.1943-5525.0001225 ↗
14. Damage Identification of a Steel Frame Based on Integration of Time Series and Neural Network under Varying Temperatures10.1155/2020/4284381 ↗
15. Suresh, V., Janik, P., Rezmer, J., and Leonowicz, Z. (2020). Forecasting Solar PV Output Using Convolutional Neural Networks with a Sliding Window Algorithm. Energies, 13.10.3390/en13030723 ↗
16. Performance analysis and modelling of a 50 MW grid-connected photovoltaic plant in Spain after 12 years of operation10.1016/j.rser.2022.112968 ↗
17. Hichri, A., Hajji, M., Mansouri, M., Harkat, M.-F., Kouadri, A., Nounou, H., and Nounou, M. (2020, January 20–23). Fault detection and diagnosis in grid-connected photovoltaic systems. Proceedings of the 2020 17th International Multi-Conference on Systems, Signals & Devices (SSD), Sfax, Tunisia.10.1109/SSD49366.2020.9364235 ↗
18. Fault detection in a grid-connected photovoltaic system using adaptive thresholding method10.1016/j.solener.2018.09.024 ↗
19. Cui, F., Tu, Y., and Gao, W. (2022). A Photovoltaic System Fault Identification Method Based on Improved Deep Residual Shrinkage Networks. Energies, 15.10.3390/en15113961 ↗
20. Development of a multi-output feed-forward neural network for fault detection in Photovoltaic Systems10.1016/j.egyr.2022.06.107 ↗
21. Burbano, R.A.G., Petrone, G., and Manganiello, P. (2021). Early Detection of Photovoltaic Panel Degradation through Artificial Neural Network. Appl. Sci., 11.10.3390/app11198943 ↗
22. Hopwood, M.W., Stein, J.S., Braid, J.L., and Seigneur, H.P. (2022). Physics-Based Method for Generating Fully Synthetic IV Curve Training Datasets for Machine Learning Classification of PV Failures. Energies, 15.10.3390/en15145085 ↗
23. Hichri, A., Hajji, M., Mansouri, M., Abodayeh, K., Bouzrara, K., Nounou, H., and Nounou, M. (2022). Genetic-Algorithm-Based Neural Network for Fault Detection and Diagnosis: Application to Grid-Connected Photovoltaic Systems. Sustainability, 14.10.3390/su141710518 ↗
24. Aljafari, B., Madeti, S.R.K., Satpathy, P.R., Thanikanti, S.B., and Ayodele, B.V. (2022). Automatic Monitoring System for Online Module-Level Fault Detection in Grid-Tied Photovoltaic Plants. Energies, 15.10.3390/en15207789 ↗
25. Hussain, I., Khalil, I.U., Islam, A., Ahsan, M.U., Iqbal, T., Chowdhury, S., Techato, K., and Ullah, N. (2022). Unified Fuzzy Logic Based Approach for Detection and Classification of PV Faults Using I-V Trend Line. Energies, 15.10.3390/en15145106 ↗
26. Wang, L., Lodhi, E., Yang, P., Qiu, H., Rehman, W.U., Lodhi, Z., Tamir, T.S., and Khan, M.A. (2022). Adaptive Local Mean Decomposition and Multiscale-Fuzzy Entropy-Based Algorithms for the Detection of DC Series Arc Faults in PV Systems. Energies, 15.10.3390/en15103608 ↗
27. Early detection of photovoltaic system inverter faults10.1016/j.microrel.2022.114594 ↗
28. Artificial neural network based photovoltaic fault detection algorithm integrating two bi-directional input parameters10.1016/j.renene.2020.04.023 ↗
29. Tkachenko, R., Izonin, I., Vitynskyi, P., Lotoshynska, N., and Pavlyuk, O. (2018). Development of the Non-Iterative Supervised Learning Predictor Based on the Ito Decomposition and SGTM Neural-Like Structure for Managing Medical Insurance Costs. Data, 3.10.3390/data3040046 ↗
30. Álvarez-Tey, G., and García-López, C. (2022). Strategy Based on Two Stages for IR Thermographic Inspections of Photovoltaic Plants. Appl. Sci., 12.10.3390/app12136331 ↗
31. Kim, B., Juan, R.O.S., Lee, D.-E., and Chen, Z. (2021). Importance of Image Enhancement and CDF for Fault Assessment of Photovoltaic Module Using IR Thermal Image. Appl. Sci., 11.10.3390/app11188388 ↗
32. Prediction of a Grid-Connected Photovoltaic Park’s Output with Artificial Neural Networks Trained by Actual Performance Data10.3390/app12136458 ↗
33. Correlation of actual efficiency of photovoltaic panels with air mass10.1016/j.renene.2014.07.051 ↗
34. Hagan, M.T., Demuth, H.B., Beale, M.H., and De Jesứs, O. (2014). Neural Network Design, [2nd ed.]. Available online: https://hagan.okstate.edu/NNDesign.pdf.
35. A review and evaluation of the state-of-the-art in PV solar power forecasting: Techniques and optimization10.1016/j.rser.2020.109792 ↗
36. Day-ahead probabilistic PV generation forecast for buildings energy management systems10.1016/j.solener.2018.06.100 ↗
37. A day-ahead PV power forecasting method based on LSTM-RNN model and time correlation modification under partial daily pattern prediction framework10.1016/j.enconman.2020.112766 ↗