Performance Study of Artificial Neural Network Training Algorithms for Classifying PV Field Defects

Abstract

Diagnosis is an essential technique that fits into the field of industrial systems maintenance. In this article, the diagnosis is applied to the photovoltaic field to increase energy efficiency. The development of a diagnostic system based on intelligent approaches, such as an artificial neural network is necessary to ensure the efficiency and control of photovoltaic systems automatically and intelligently. Artificial neural network demonstrates their effectiveness in detecting and identifying faults in PV systems. In this paper, the neural network used for classification has been trained with different learning algorithms to show which is the most efficient and accurate algorithm for classifying PV field defects.