Photovoltaic Modules Diagnosis Using Artificial Vision Techniques for Artifact Minimization

Abstract

Abstract:The installed capacity of solar photovoltaics has increased over the past two decades worldwide, evolving from a few small scale applications to a daily power source. Such growth involves a great impact over operating processes and maintenance practices. The RGB (red, green and blue) and infra-red monitoring of photovoltaic modules is a non-invasive inspection method which provides information of possible failures, by relating thermal behaviour of the modules to the operational status of solar panels. An adequate thermal measurement module strongly depends on the proper camera angle selection relative to panel's surface, since reflections and external radiation sources are common causes of misleading results with the unnecessary maintenance work. In this work, we test a portable ground-based system capable of detecting and classifying hot-spots related to photovoltaic module failures. The system characterizes in 3D thermal information from the panels structure to detect and classify hot-spots. Unlike traditional systems, our proposal detects false hot-spots associated with people or device reflections, and from external radiation sources. Experimental results show that the proposed diagnostic approach can provide of an adequate thermal monitoring of photovoltaic modules and improve existing methods in 12% of effectiveness, with the corresponding financial impact.

Measurement of Thermal and Electrical Parameters in Photovoltaic Systems for Predictive and Cross-Correlated Monitorization

“…The classification was based on the research of Buerhop et al [22]. The failure patterns of PV modules was determined with the IR image given by the International Energy Agency (IEA) [16], and the algorithm for fault diagnosis by Menendez et al [24], which discards all temperature differences that are not more than 5 • C, was based on empirical analysis.…”

“…As it is a less time-consuming and a relatively inexpensive technique compared to detailed electrical measurements, this approach is suitable for medium and large-scale PV systems. Fault diagnosis algorithms based on thermographic analysis were proposed by Buerhop et al [22], Salazar and Macabebe [23] and Menéndez et al [24]. An excellent summary of failure types and methods to identify and classify the type of failure was provided by the review compiled by the International Energy Agency [16].…”

Solar Panels String Predictive and Parametric Fault Diagnosis Using Low-Cost Sensors

“…They also present notable differences in the quality of the analyses depending on whether they are carried out in the outdoor or indoor environment and also restrictions to immediate detection when used manually and causing interruptions in normal operation [ 14 ]. The use of remotely piloted aircrafts RPA requires non-negligible periods of recharging their batteries [ 15 ], their effective use also requires special technical training [ 16 , 17 ], and the equipment is more expensive, cannot compete in terms of speed of detection and isolation with the online predictive diagnosis method based on the use of the electrical parameters of the PVMs.…”

Automatic Boundary Extraction for Photovoltaic Plants Using the Deep Learning U-Net Model

“…Traditional Image Processing (TIP) has been used extensively by other authors. In this study [13,[20][21][22][23][24], the authors used TIP to defect recognition in the inspection of photovoltaic plants. Furthermore, using HSV transformation, color filtering and segmentation, techniques have been implemented in many projects, especially for defect detection [25], to enumerate photovoltaic modules [20,26] and identification of limits [27].…”