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.

No abstract

We now differentiate between the requirements for new and revised submissions. You may choose to submit your manuscript as a single Word or PDF file to be used in the refereeing process. Only when your paper is at the revision stage, will you be requested to put your paper in to a 'correct format' for acceptance and provide the items required for the publication of your article. To find out more, please visit the Preparation section below. Highlights Highlights are mandatory for this journal as they help increase the discoverability of your article via search engines. They consist of a short collection of bullet points that capture the novel results of your research as well as new methods that were used during the study (if any). Please have a look at the examples here: example Highlights. Highlights should be submitted in a separate editable file in the online submission system. Please use 'Highlights' in the file name and include 3 to 5 bullet points (maximum 85 characters, including spaces, per bullet point).

7Hot spotting is a reliability problem in photovoltaic (PV) panels where a mismatched cell heats up 8 significantly and degrades PV panel output power performance. High PV cell temperature due to 9 hot spotting can damage the cell encapsulate and lead to second breakdown, where both cause 10 permanent damage to the PV panel. Therefore, the design and development of two hot spot 11 mitigation techniques are proposed using a simple, costless and reliable method. The hot spots in 12 the examined PV system was carried out using FLIER i5 thermal imaging camera. 13 Several experiments have been examined during various environmental conditions, where the PV 14 module I-V curve was evaluated in each observed test to analyze the output power performance 15 before and after the activation of the proposed hot spot mitigation techniques. One PV module 16 affected by hot spot was tested. The output power during high irradiance levels is increased by 17 approximate to 1.25 W after the activation of the first hot spot mitigation technique. However, the 18 second mitigation technique guarantee an increase of the power equals to 3.96 W. Additional test 19 has been examined during partial shading condition. Both proposed techniques ensure a decrease 20 in the shaded PV cell temperature, thus an increase in the output measured power. 21 Keywords: Hot spot protection; photovoltaic (PV) hot spotting analysis; solar cells; thermal imaging. 22 23Photovoltaic (PV) hot spots are a well-known phenomenon, described as early as in 1969 [1] and 24 still present in PV modules [2 and 3]. PV hot spots occur when a cell, or group of cells, operates 25 at reverse-bias, dissipating power instead of delivering it and, therefore, operating at abnormally 26 high temperatures. This increase in the cells temperature will gradually degrade the output power 27 generated by the PV module as explained by M. Simon & L. Meyer [4]. Hot spots are relatively 28 frequent in current PV modules and this situation will likely persist as the PV module technology 29 is evolving to thinner wafers, which are prone to developing micro-cracks during the manipulation 30 process such as manufacturing, transportation and installation [5 and 6]. 31PV hot spots can be easily detected using IR inspection, which has become a common practice in 32 current PV applications as shown in [7]. However, the impact of hot spots on operational efficiency 33 and PV lifetime have been scarcely addressed, which helps to explain why there is lack of widely 34 accepted procedures which deals with hot spots in practice as well as specific criteria referring to 35 acceptance or rejection of affected PV module in commercial frameworks as described by R. 36Moretón et al [8]. Thus, this paper demonstrates two mitigation techniques which will improve the 37 output power performance of the hot spotted PV modules.In the past, the increase in the number of bypass diodes (up to one diode for each cell) has been 39 proposed as a possible solution [9 and 10]. However, this approach has not encounte...

No abstract