Comparing Mamdani Sugeno fuzzy logic and RBF ANN network for PV fault detection

Abstract

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.

Novel Open-Circuit Photovoltaic Bypass Diode Fault Detection Algorithm

“…HOTOVOLTAIC (PV) systems are subject to diversity of failures, such as faults in the interconnection between PV modules [1], faults associated with cabling [2], converters [3], and inverters [4]. There are numerous PV fault detection algorithms, eventually detecting failure in all above listed components [5] - [8].…”

Fault diagnosis of Photovoltaic Modules

“…[85][86][87][88][89][90][91][92] When the suspicion on the wrong component is detected, the concrete strings are then evaluated using other methods. Usual configuration of large systems consists of string inverters with the middle power (about 5-10 kW) because of the problems with local shading caused by clouds movements.…”

“…The problem of data evaluation is out of range of this work and is described in many publications. [85][86][87][88][89][90][91][92] When the suspicion on the wrong component is detected, the concrete strings are then evaluated using other methods.…”

Photovoltaic Hot-Spots Fault Detection Algorithm Using Fuzzy Systems

“…In this article, we propose a suitable Mamdani FIS rather than strength of the Takgi-Sugeno-Kang (TSK) model, since Mamdani model can return output results which automatically express output results based on If-Then method; this method relies on determining whether an input parameter of the user belongs to the membership function using "If" and next convert the value into the fuzzy set using "Then". Adapting a direct interference between the measured inputs from the PV modules with the results of the detection system [24].…”