Robust Detection, Classification and Localization of Defects in Large Photovoltaic Plants Based on Unmanned Aerial Vehicles and Infrared Thermography

Abstract

The efficiency and profitability of photovoltaic (PV) plants are highly controlled by their operation and maintenance (O&M) procedures. Today, the effective diagnosis of any possible fault of PV plants remains a technical and economic challenge, especially when dealing with large-scale PV plants. Currently, PV plant monitoring is carried out by either electrical performance measurements or image processing. The first approach presents limited fault detection ability, it is costly and time-consuming, and it is incapable of fast identification of the physical location of the fault. In the second approach, Infrared Thermography (IRT) imaging has been used for the characterization of PV module failures, but their setup and processing are rather complex and an experienced technician is required. The use of Unmanned Aerial Vehicles (UAVs) for IRT imaging of PV plants for health status monitoring of PV modules has been identified as a cost-effective approach that offers 10–-15 fold lower inspection times than conventional techniques. However, previous works have not performed a comprehensive approach in the context of automated UAV inspection using IRT. This work provides a fully automated approach for the: (a) detection, (b) classification, and (c) geopositioning of the thermal defects in the PV modules. The system has been tested on a real PV plant in Spain. The obtained results indicate that an autonomous solution can be implemented for a full characterization of the thermal defects.

Using UAV to Detect Solar Module Fault Conditions of a Solar Power Farm with IR and Visual Image Analysis

“…Alsafasfeh, M., et al [2] yes yes Hwang, M.-H., et al [4] yes bypass diode Libra, M., et al [8] yes yes Niccolai, A., et al [9] yes digital map Vieira, R.G., et al [10] yes bypass diode Navid, Q., et al [11] yes Henry, C., et al [12] yes yes Pierdicca, R., et al [13] yes yes deep learning Jeong, H., et al [14] yes yes diagnosis Boulhidja, S., et al [15] yes Tsanakas, J.A., et al [16] yes yes Tsanakas, J.A., et al [17] yes Gallardo-Saavedra, S., et al [18] yes Ballestín-Fuertes, J., et al [19] EL 1 Herraiz, Á.H., et al [20] yes yes Fernández, A., et al [21] yes yes 1 Electroluminescence Technique.…”

Automatic Detection of Linear Thermal Bridges from Infrared Thermal Images Using Neural Network

“…In addition to architecture, a wide variety of studies have been performed to automatically detect problems, using thermal images in objects such as pipelines [16], turbojet engines [17], photovoltaic module [18,19], and belt conveyors [20]. In particular, some of these studies have proposed an intelligent method, such as machine learning, to increase the accuracy of detection.…”

Preliminary Results of a Hybrid Thermoelectric Propulsion System for a Multirotor UAS with Active Rectifying, Electronic Throttle Control and Supercapacitors

“…This statement can be checked by simply reviewing the graphs provided by the manufacturer, where the curves of flight-time vs. payload are calculated for a complete discharge of the set of batteries while, in actual use, an emergency Return to Home (RTH) happens when the battery is at around 20% of its remaining capacity. Our own experience in solar plant inspection, [6], with intensive use of a M210RTK-V2™, has shown us that the maximum flight time in real conditions is around 18 min. This short autonomy implies the use of six sets of batteries, at more than EUR 1000 each, a fast-charging station capable of simultaneously charging four sets of batteries and splitting up flight missions into small sections, with one section for each battery set.…”