Abstract
The obtained results indicate that the fault detection algorithm can detect and locate accurately different types of faults such as, faulty PV module, two faulty PV modules and partial shading conditions affecting the PV system. In order to achieve high rate of detection accuracy, four various ANN networks have been tested. The maximum detection accuracy is equal to 92.1%. Furthermore, both examined fuzzy logic systems show approximately the same output during the experiments. However, there are slightly difference in developing each type of the fuzzy systems such as the output membership functions and the rules applied for detecting the type of the fault occurring in the PV plant.
| Language | English |
|---|---|
| Pages | 257-274 |
| Number of pages | 8 |
| Journal | Renewable Energy |
| Volume | 117 |
| Early online date | 24 Oct 2017 |
| DOIs | |
| Publication status | Published - Mar 2018 |
Fingerprint
Cite this
}
Comparing Mamdani Sugeno Fuzzy Logic and RBF ANN Network for PV Fault Detection. / Dhimish, Mahmoud; Holmes, Violeta; Mehrdadi, Behrooz; Dales, Mark.
In: Renewable Energy, Vol. 117, 03.2018, p. 257-274.Research output: Contribution to journal › Article
TY - JOUR
T1 - Comparing Mamdani Sugeno Fuzzy Logic and RBF ANN Network for PV Fault Detection
AU - Dhimish,Mahmoud
AU - Holmes,Violeta
AU - Mehrdadi,Behrooz
AU - Dales,Mark
PY - 2018/3
Y1 - 2018/3
N2 - This work proposes a new fault detection algorithm for photovoltaic (PV) systems based on artificial neural networks (ANN) and fuzzy logic system interface. There are few instances of machine learning techniques deployed in fault detection algorithms in PV systems, therefore, the main focus of this paper is to create a system capable to detect possible faults in PV systems using radial basis function (RBF) ANN network and both Mamdani, Sugeno fuzzy logic systems interface.The obtained results indicate that the fault detection algorithm can detect and locate accurately different types of faults such as, faulty PV module, two faulty PV modules and partial shading conditions affecting the PV system. In order to achieve high rate of detection accuracy, four various ANN networks have been tested. The maximum detection accuracy is equal to 92.1%. Furthermore, both examined fuzzy logic systems show approximately the same output during the experiments. However, there are slightly difference in developing each type of the fuzzy systems such as the output membership functions and the rules applied for detecting the type of the fault occurring in the PV plant.
AB - This work proposes a new fault detection algorithm for photovoltaic (PV) systems based on artificial neural networks (ANN) and fuzzy logic system interface. There are few instances of machine learning techniques deployed in fault detection algorithms in PV systems, therefore, the main focus of this paper is to create a system capable to detect possible faults in PV systems using radial basis function (RBF) ANN network and both Mamdani, Sugeno fuzzy logic systems interface.The obtained results indicate that the fault detection algorithm can detect and locate accurately different types of faults such as, faulty PV module, two faulty PV modules and partial shading conditions affecting the PV system. In order to achieve high rate of detection accuracy, four various ANN networks have been tested. The maximum detection accuracy is equal to 92.1%. Furthermore, both examined fuzzy logic systems show approximately the same output during the experiments. However, there are slightly difference in developing each type of the fuzzy systems such as the output membership functions and the rules applied for detecting the type of the fault occurring in the PV plant.
KW - Photovoltaic system
KW - Photovoltaic faults
KW - Fault detection
KW - ANN networks
KW - Fuzzy logic systems
UR - https://www.journals.elsevier.com/renewable-energy
U2 - 10.1016/j.renene.2017.10.066
DO - 10.1016/j.renene.2017.10.066
M3 - Article
VL - 117
SP - 257
EP - 274
JO - Renewable Energy
T2 - Renewable Energy
JF - Renewable Energy
SN - 0960-1481
ER -