REAL-TIME DIAGNOSIS OF BATTERY CELLS FOR STAND-ALONE PHOTOVOLTAIC SYSTEM USING MACHINE LEARNING TECHNIQUES
Keywords:
Stand-alone photovoltaic system, Battery, Anomaly detection, Support vector machine, Diagnosis, AccuracyAbstract
Battery as a critical element in the stand-alone photovoltaic system remains without an appropriate protection fuse for short- circuit failure inside it. Therefore the safety is threatened and the lifetime of the battery is reduced. To address this problem, supervision of battery internal short-circuit is proposed using a machine learning anomaly detection and support vector machine (SVM) as fault detection and diagnosis respectively. Simulation of Stand-alone photovoltaic system with battery is carried-out to obtain data learning. In addition, a real profile of irradiance and temperature captured from Centre de Development des Energies Renouvelables (CDER), Algeria, during nine days is used as input of the system simulation. The developed anomaly detection and SVM diagnosis model show their ability to detect and diagnose the faults with high accuracy in test real-time data.
References
(1) IEA, Trends 2016 in photovoltaic applications, Report IEA-PVPS T1- 30 (2016).
(2) L. Barote, C. Marinescu, I. Şerban, Energy storage for a stand-alone wind energy conversion system, Rev. Roum. Sci. Techn. – Électrotechn. Et Énerg, 55, 3, pp. 235–242 (2010).
(3) RL.Nailen, Battery protection-where do we stand ?, IEEE Transactions on Industry Applications, 27, 4, pp. 658–667 (1991).
(4) IEA, A user guide to simple monitoring and sustainable operation of PV-diesel hybrid systems, Repport IEA-PVPS T9-16 (2015).
(5) M. Kim, E. Hwang, Monitoring the battery for photovoltaic systems, J. Power Sources, 64, 1-2, pp. 193–196 (1997).
(6) M. Tadj, K. Benmouiza, A. Cheknane, An innovative method based on satellite image analysis to check fault in a PV system lead-acid battery, Simulation Modelling Practice and Theory, 47, pp. 236– 247 (2014).
(7) D. Mayer, M. Heidenreich, Performance analysis of stand alone PV systems from a rational use of energy point of view, Photovoltaic Energy Conversion,2003 Proceedings of 3rd World Conference, 3, pp. 2155–2158 (2003).
(8) F.J. Muñoz, G. Almonacid, G. Nofuentes, F. Almonacid, A new method based on charge parameters to analyse the performance of stand- alone photovoltaic system, Solar Energy Materials and Solar Cells, 90, 12, pp. 1750–1763 (2006).
(9) F.J. Muñoz, I. Echbarthi, G. Nofuentes, M. Fuentes, J. Aguilera, Estimation of the potential array output charge in the perfor- mance analysis of stand-alone photovoltaic systems without MPPT (Case study:Mediterranean Climate), Solar Energy, 83, 11, pp. 1985–1997 (2009).
(10) M. Torres, F.J. Muñoz, J.V. Muñoz, C. Rus, Online Monitoring System for Stand-alone Photovoltaic Applications Analysis of System Performance From Monitored Data, J. Solar Energy Engineering, 134, pp. 034502-8 (2012).
(11) A. Purarjomandlangrudi, A.H. Ghapanchi, M. Esmalifalak, A data mining approach for fault diagnosis: An application of anomaly detection algorithm, Measurement, 55, pp. 343-352 (2014).
(12) Y. Zhao, B. Lehman, J. Mosesian, J.F.d. Palma, Outlier detection rules for fault detection in solar photovoltaic arrays, 2013 Twenty- Eighth annual IEEE Applied Power Electronics Conference and Exposition (APEC), pp. 2913-2920, March 17–24, 2013.
(13) Y. Zhao, F. Balboni, T. Arnaud, J. Mosesian, R. Ball, B. Lehman, Fault experiments in a commercial-scale PV laboratory and fault detection using local outlier factor, 2014 IEEE 40th Photovoltaic Specialist Conference (PVSC), pp. 3398-3403, June 8–13, 2014.
(14) L. Ren, W. Lv, S. Jiang, Y. Xiao, Fault Diagnosis Using a Joint Model Based on Sparse Representation and svm, IEEE Trans. on Instrumentation and Measurement, 65, 10, pp. 2313–2320 (2016).
(15) D. You, X. Gao, S. Katayama, WPD-PCA-Based Laser Welding Process Monitoring and Defects Diagnosis by Using FNN and SVM, IEEE Trans. on Industrial Electronics, 62, 1, pp. 628–636 (2015).
(16) W. Rezgui, L.H. Mouss, N.K. Mouss, M.D. Mouss, M. Benbouzid, A smart algorithm for the diagnosis of short-circuit faults in a photovoltaic generator, 2014 First International Conference on Green Energy ICGE, pp. 139–143, March 25–27, 2014.
(17) L. Zhongliang, R. Outbib, S. Giurgea, D. Hissel, S. Jemie, A. Giraud, S. Rosini, Online implementation of svm based fault diagnosis strategy for PEMFC systems, Applied Energy, 164, pp. 284–293 (2016).
(18) A. Widodo, B.S. Yang, Support vector machine in machine condition monitoring and fault diagnosis, Mechanical Systems and Signal Processing, 21, 6, pp. 2560–2574 (2007).
(19) S. Mirić, M. Nedeljković, The solar photovoltaic panel simulator, Rev. Roum. Sci. Techn. – Électrotechn. Et Énerg, 60, 3, pp. 273–281 (2015).
(20) M.G. Villalva, J.R. Gazoli, E.R. Filho, Comprehensive Approach to Modeling and Simulation of Photovoltaic Arrays, IEEE trans. on Power Electronics, 24, 5, pp. 1198 –1208 (2009).
(21) O. Tremblay, A. Louis-Dessaint, Experimental Validation of a Battery Dynamic Model for EV Applications, World Electric Vehicle Journal, 3, pp. 1–10 (2009).
(22) A. Chouder, S. Silvestre, Automatic supervision and fault detection of PV systems based on power losses analysis, Energy Conversion and Management, 51, 10, pp. 1929–1937 (2010).
(23) M. Markou, S. Singh, Novelty detection: a review-part 1: statistical approaches, Signal processing, 83, 12, pp. 2481–2497 (2003).
(24) J. Platt, Sequential minimal optimization: a fast algorithm for training support vector machines, Technical report MSR-TR-98-14, Microsoft research, pp. 1–21 (1998).
Downloads
Published
Issue
Section
License
Copyright (c) 2021 Romanian Journal of Technical Sciences, Electrical and Energy Series
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
