Comparing multilayer perceptron and probabilistic neural network for PV systems fault detection

作者：

Highlights：

• Proposes a PV modules fault detection.

• Compare the results of a Multilayer Perceptron and a Probabilistic Neural Network.

• Detects short-circuited PV modules and disconnected strings on a PV system.

• The method does not require long datasets from pre-existing systems.

• The research also assesses the presence of noise on the training datasets.

摘要

•Proposes a PV modules fault detection.•Compare the results of a Multilayer Perceptron and a Probabilistic Neural Network.•Detects short-circuited PV modules and disconnected strings on a PV system.•The method does not require long datasets from pre-existing systems.•The research also assesses the presence of noise on the training datasets.

论文关键词：Solar Energy,Photovoltaic modules,String disconnection,Short-circuit,Fault detection,Neural network

论文评审过程：Received 4 May 2021, Revised 12 March 2022, Accepted 12 April 2022, Available online 16 April 2022, Version of Record 19 April 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117248