ANOMALY DETECTION IN PHOTOVOLTAIC PANELS USING ABNET, PSOM AND MLP
DOI:
https://doi.org/10.59627/cbens.2016.1957Keywords:
Photovoltaic panels, Artificial Neural Networks, Pattern ClassificationAbstract
This paper main goal is to detect anomalies in photovoltaic panels installed in power generation systems using thermographic images. It was used image processing techniques and pattern recognition by means of artificial neural network with supervised and adaptive training. In order to implement the anomaly detection system it was selected from the tutorial "Solar Cell Development" by FLIR systems, thermographic images of photovoltaic cells with defects. The language of technical computing, MATLAB©, was used to make the preprocessing of all the collected images and it was also used for the training of an ABNET network, a PSOM network and a MLP network. Through the cross-validation method, the hit rate of the ABNET’s network and PSOM’s network was 87.5% and for the MLP the hit rate was 96.0%. The results corroborate for the use of these neural networks on a bank of images that will be created through a Research and Development Project (R&D) in progress.
Downloads
References
C. M. Bishop, Neural networks for pattern recognition. 1rt ed., Oxford: Clarendon Press, 1995.
E. Upton, G. Halfacree. Raspberry Pi user guide. 3rd ed. Hoboken, New Jersey: John Wiley & Sons, 2014.
F. J. Rosenblatt, “The Perceptron: A probabilistic model for information storage and organization in the brain”, Psychological Review, vol. 65, pp. 386–408, Jun. 1958.
FLIR Systems, “FLIR Solution Series: Solar Cell Development”, FLIR Systems, Inc., MoviTHERM, Automation Technology GmbH, Irvine, CA, USA. Disponível em: <http://infraredsys.com/research.pdf>. Acesso em: 25 ago. 2015.
FLIR Systems, “MoviTHERM Solar-Check system”, FLIR Systems, Inc., MoviTHERM, Automation Technology GmbH, Irvine, CA, USA. Disponível em: < http://www.movitherm.com/solar-check-ndt-solar-cells.html>. Acesso em: 25 de ago. 2015.
G Blanchet, M Charbit, Digital signal and image processing using Matlab. 4th ed. London: Iste, 2006.
G. A. de Deus Júnior, L. N. de Castro, J. Portugheis, “Mapa Auto-Organizável Não-Paramétrica (PSOM) Aplicado À Decisão De Lógica Majoritária”, SBAI, pp. 100-155, 1999.
G. A. de Deus Júnior, “Sistemas FFH-CDMA Codificados”, Ph.D. diss., Universidade Estadual de Campinas, Campinas, SP, Brasil, 2002.
K Hornik, M Stinchcombe, H White, “Multilayer feedforward networks are universal approximators”, Neural networks, vol 2, pp. 359-366, May 1989.
L. N. de Castro, F. J. Von Zuben, G. A. de Deus Júnior, “The construction of a Boolean competitive neural network using ideas from immunology”, Neurocomputing, vol 5, pp. 51-85, 2003.
M. Minsky, P. Seymour. Perceptrons, Oxford, England: M.I.T. Press, 1969.
M. Stone, “Cross-validation: A review,” Statistics: A Journal of Theoretical and Applied Statistics, vol. 9, pp. 127–139, 1978.
M. Stone, “Cross-validatory choice and assessment of statistical predictions”, Journal of the Royal Statistical Society, vol. B36, pp. 111–133, 1974.
R. C. Gonzalez and R. E. Woods Processamento de Imagens Digitais. São Paulo: Editora Edgard Blücher Ltda., 1992.
S. S. Haykin, Neural networks and learning machines. 3rd ed., Upper Saddle River: Pearson Education, 2009.
M. Simon and E. L. Meyer, “Detection and analysis of hot-spot formationin solar cells,” Solar Energy Mater. Solar Cells, vol. 94, no. 2, pp. 106–113,2010.
