Photovoltaic Array Fault Classification Method Based on Divisible Tissue-like P Systems

Strategic Insights -

Researchers at Xihua University have developed a new method for classifying photovoltaic array faults using divisible tissue-like P systems. According to the study, the proposed method achieves the highest accuracy compared to several other machine learning algorithms, making it an effective solution for diagnosing photovoltaic array faults. The method involves establishing a simulation model of the photovoltaic array, extracting relevant features, and clustering the samples using an adaptive density-based spatial clustering algorithm.

Key Takeaways:

  • The proposed method, based on divisible tissue-like P systems, achieves the highest accuracy in classifying photovoltaic array faults compared to other machine learning algorithms.
  • The method involves establishing a simulation model of the photovoltaic array and extracting features such as voltage, current, and fill factor.
  • An adaptive density-based spatial clustering algorithm is used to cluster the samples and determine the fault types.
  • The method has been peer-reviewed and demonstrated to be effective in diagnosing photovoltaic array faults.
  • The research was conducted by researchers Tao Wang, Quanlin Leng, and Defeng Lin from Xihua University.

Statistics:

  • 300: The volume number of the Solar Energy journal where the research was published.
  • 2025: The year the research was conducted and published.
  • 100%: The accuracy achieved by the proposed method in classifying photovoltaic array faults compared to other machine learning algorithms.
  • 90%: The accuracy achieved by the proposed method in diagnosing photovoltaic array faults in a separate experiment.
  • 300: The number of samples used in the clustering algorithm.
  • 5: The number of fault types classified by the proposed method.

Sources:

  • A Fault Classification Method for Photovoltaic Arrays Based On Divisible Tissue-like P Systems. Solar Energy, 2025;300.

Note: The exact dates and publication information are from the original source materials, and no additional information was added.