Arc Fault and Flash Detection in Photovoltaic Systems Using Wavelet Transform and Support Vector Machines Conference Paper uri icon


  • 2016 IEEE. Arc faults pose significant reliability and safety issues in today's photovoltaic (PV) systems. This paper presents an effective method based on wavelet transform and support vector machines (SVM) for detection of arc faults in DC PV systems. Because of its advantages in time-frequency signal processing, wavelet transform is applied to extract the characteristic features from system voltage/current signals. SVM is then used to identify arc faults. The performance of the proposed technique is compared with traditional Fourier transform based approaches.

name of conference

  • 2016 IEEE 43rd Photovoltaic Specialists Conference (PVSC)

published proceedings


author list (cited authors)

  • Wang, Z., & Balog, R. S.

citation count

  • 21

complete list of authors

  • Wang, Zhan||Balog, Robert S

publication date

  • June 2016