PHOTOVOLTAIC MODULE FAILURE DETECTION USING MACHINE VISION AND A LAZY LEARNING TECHNIQUE

Judith Jancy*
Periodicity:January - June'2024

Abstract

By conducting detection of faults and condition monitoring, solar module efficiency and dependability can be raised. The limitations and challenges of diagnosing solar module malfunctions are examined in this study. The many issues connected to solar module failure have been well discussed. A monitoring tool that uses the thermography and computers with intelligence to discover various issues with photovoltaic cells while also filtering out trivial anomalies is developed after reviewing pertinent studies. Given the increasing expansion of solar energy, the photovoltaic (or PV) component detects faults plays a critical role in understanding how to increase the dependability of the total solar power system and detecting the fault type any time a system issue emerges. As a result, this paper presented a hybrid strategy employing the chaotic synchronisation detection approach (CSDM) and a convolutional neural network (CNN) for investigating PV module fault detection. Problem identification and treatment in PV systems have become equally important with the global photovoltaic (PV) market's explosive growth. Identifying issues early will improve a solar system's efficiency, measurement outcomes, and lifespan. The plant's production of electricity will suffer greatly if these PV flaws are not quickly identified and fixed. Both on-site and online monitoring and identification of defects are possible. In addition, a few flaws including ground faults, arc faults, line-to-line errors, and points of ignition may pose a fire hazard. Researchers have recently proposed several methods for diagnosing and detecting PV issues. In-depth discussions of significant photovoltaic defects are provided in this work. The distinctions, benefits, and drawbacks of the various approaches for finding faults in PV systems that have been suggested in the available research are also highlighted. A brief discussion of various solar cell modelling models is also provided.

Keywords

PHOTOVOLTAIC DEFECTS,PROBLEM IDENTIFICATION,FAULT DETECTION,LAZY LEARNING TECHNIQUE

How to Cite this Article?

References

If you have access to this article please login to view the article or kindly login to purchase the article

Purchase Instant Access

Single Article

North Americas,UK,
Middle East,Europe
India Rest of world
USD EUR INR USD-ROW
Pdf 35 35 200 20
Online 35 35 200 15
Pdf & Online 35 35 400 25

Options for accessing this content:
  • If you would like institutional access to this content, please recommend the title to your librarian.
    Library Recommendation Form
  • If you already have i-manager's user account: Login above and proceed to purchase the article.
  • New Users: Please register, then proceed to purchase the article.