Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon openaccess Fault diagnosis of PV array based on optimised BP neural network by improved adaptive genetic algorithm

  • Author(s): Yawei Liu 1 ; Xiaorong Zhu 1 ; Jin Yang 2
    • View affiliations
  • Source: Volume 2017, Issue 13, 2017, p. 1427 – 1431
    DOI:  10.1049/joe.2017.0567 , Online ISSN 2051-3305
This is an open access article published by the IET under the Creative Commons Attribution-NonCommercial-NoDerivs License (http://creativecommons.org/licenses/by-nc-nd/3.0/)
Received 10/10/2017, Accepted 02/11/2017, Published 01/01/2017

The fault diagnosis model based on back propagation (BP) neural network is especially suitable for multi-fault and complex pattern recognition. However, the selection of initial weights and thresholds of BP neural network is lack of basis and it is easy to fall into the local optimum. Genetic algorithm (GA) can be used to optimise the initial weights and thresholds of the BP neural network. However, the selection process of GA based on roulette wheel selection is a random operation and the parameters of GA, the crossover probability and the mutation probability, are given a constant value which reduces the efficiency. Thus improved adaptive GA provides improvement in the selection, crossing and mutation process of GA, which prevents the neural network from falling into local optimum more effectively. Results of cases study show that this method can determine the fault types of photovoltaic array effectively.

Inspec keywords: backpropagation; genetic algorithms; power engineering computing; neural nets; photovoltaic cells; fault diagnosis; probability

Other keywords: optimised BP neural network; fault diagnosis model; fault types; photovoltaic array; adaptive GA; back propagation neural network; random operation; multifault complex pattern recognition; roulette wheel selection; PV array; mutation process; improved adaptive genetic algorithm; crossing process; BP neural network

Subjects: Neural computing techniques; Photoelectric devices; Other topics in statistics; Optimisation techniques; Optimisation techniques; Power engineering computing

References

    1. 1)
      • 2. Peizhen, W., Shicheng, Z.: ‘Fault analysis of solar PV array based on infrared image’, J. Sol. Energy, 2010, 31, (2), pp. 197–202.
    2. 2)
      • 5. Ze, C., Yong, X., Mengnan, D.: ‘A new fault diagnosis and location method for PV array’, Sens. Microsyst., 2013, 32, (7), pp. 26–28.
    3. 3)
      • 14. Qiang, Z.: ‘Research on fault diagnosis method based on fuzzy neural network and genetic algorithm’, Dalian University of Technology, 2006.
    4. 4)
      • 6. Yuanzhang, E., Chunhua, W., Diqing, Z., et al: ‘Research on fault diagnosis of PV array based on BP neural network’, Power Syst. Prot. Control, 2013, 60, (16), pp. 108–114.
    5. 5)
      • 3. Bei, N., Fu, Z., Wang, L., et al: ‘Automatic detection of defects in solar modules: image processing in detecting’. IEEE Int. Conf. Wireless Communications NETWORKING and Mobile Computing, 2010, pp. 1–4.
    6. 6)
      • 15. Wei, Y.: ‘Study on fault detection and diagnosis method of photovoltaic power plant’, University of Electronic Science and Technology, 2013.
    7. 7)
      • 12. Mei, Y., Xiaoxia, Q., Bo, W.: ‘Neural network optimization method based on improved genetic algorithm’, Comput. Simul., 2009, 26, (5), pp. 198–201.
    8. 8)
      • 8. Xiaomin, M., Xin, W.: ‘Improvement of BP neural network based on genetic algorithm’, J. Yunnan Univ. Nat. Sci. Ed., 2013, 95, (s2), pp. 34–38.
    9. 9)
      • 13. Zhang, Y., Jing, L.U., Tian, H.: ‘A novel improved adaptive genetic algorithm for the solution to optimal assignment problem’, Int. J. Syst. Control, 2007, 185, (03), pp. 253–261.
    10. 10)
    11. 11)
      • 1. Yuanzhang, W., Zhihua, L., Chunhua, W.: ‘Summarization of fault diagnosis methods for PV system’, Power Technol., 2013, 37, (9), pp. 1700–1705.
    12. 12)
      • 9. Yingjie, L., Shanwen, Z.: ‘MATLAB genetic algorithm toolbox and its application’ (Xi'an University of Electronic Science and Technology Press, 2014).
    13. 13)
      • 4. Tang, J., Zhu, Y, Wang, W.: ‘Fault diagnosis method and simulation analysis for photovoltaic array’. IEEE Int. Conf. Electrical and Control Engineering, 2011, pp. 1569–1573.
    14. 14)
      • 10. Dehu, Q., Jichang, K.: ‘Design of BP neural network’, Comput. Eng. Des., 1998, 130, (2), pp. 48–50.
    15. 15)
      • 16. Huayu, S., Zhaoxia, W., Yaocheng, G., et al: ‘Determination of the number of implied layer units in BP neural network’, J. Tianjin Univ. Sci. Technol., 2008, 24, (5), pp. 13–15.
    16. 16)
      • 7. Qinli, L., Leduo, Z.: ‘Application of BP neural network in fault diagnosis of photovoltaic power generation system’, Commun. Power Technol., 2011, 28, (4), pp. 38–40.
http://iet.metastore.ingenta.com/content/journals/10.1049/joe.2017.0567
Loading

Related content

content/journals/10.1049/joe.2017.0567
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address