Novel Features Extraction for Fault Detection Using Thermography Characteristics and IV Measurements of CIGS Thin-Film Module Reham A. Eltuhamy 1,5* , Mohamed Rady 2 , Khaled H. Ibrahim 3 , Haitham A. Mahmoud 1,4 1 Mechanical Engineering Department, Faculty of Engineering, Helwan University, Cairo 11795, Egypt 2 Mechanical Engineering Department, Faculty of Engineering at Rabigh, King Abdulaziz University, Rabigh 21911, Saudi Arabia 3 Electrical Power Department, Faculty of Engineering, Fayoum University, El-Fayoum 63514, Egypt 4 Industrial Engineering Department, College of Engineering, King Saud University, P. O. Box 800, Riyadh 11421, Saudi Arabia 5 Manufacturing Engineering and Production Technology Department, Modern Academy for Engineering and Technology, Cairo 11571, Egypt Corresponding Author Email: RIHAM.AHMED@eng.modern-academy.edu.eg https://doi.org/10.18280/i2m.190501 ABSTRACT Received: 28 July 2020 Accepted: 11 October 2020 Regarding the fault diagnosis of Copper Indium Gallium Selenide (CIGS) PV modules, previously published articles focused on employing statistical analysis of thermography images. This approach failed in many cases to distinguish among fault types. This article presents a novel methodology to diagnose and predict faults of thin-film CIGS PV modules using infrared thermography analysis combined with measurements of I-V characteristics. The proposed methodology encompasses a comprehensive site work to capture images that cover many fault types of the PV module under study. The novelty of the technique depends on utilizing processing and analysis of the captured images using new proposed mathematical parameters to extract different faults’ features. Using I-V measurements combined with thermography analysis, the differences between different types of faults are detected. Then, a general classification matrix of CIGS fault detection and diagnosis, using features based on mathematical parameters and IV measurements has been established. Results show that the analysis of the temperature distribution is proved to be insufficient to identify specific modes of different faults. In addition, the proposed procedure for fault detection and classification, which depends on the pattern of faults, can be used for any type of PV module. This results in more reliance on the proposed technique to increase the confidence level of fault detection. Keywords: PV, CIGS, fault classification, thermography, IV, fault detection, features extraction, mathematical parameters 1. INTRODUCTION Power generation from solar PV is continuously increasing all over the world. In 2018, a 30% increase in PV energy production corresponding to 570 TWh has been recorded. In 2018, the increase in solar PV capacity additions globally reached 97 gigawatts (GW) corresponding to around half of total net renewable capacity growth. Solar PV capacity additions have been doubled from 2016 to 2017 [1]. The common photovoltaic module (PVM) technologies include; Monocrystalline silicon PV modules, Polycrystalline silicon PV modules, Amorphous silicon PV modules, and Thin-film PV modules. Even though monocrystalline silicon PV and polycrystalline silicon PV are used more than other technologies, the thin-film module production grows at the rate of 24% from 2009 to reach 22,214 MW production by 2020. One type of thin-film technology is CIGS which is getting more popular than different thin-film technologies because of its higher efficiency and reduced manufacturing costs. The success of CIGS cells is supported by continuous improvement in efficiency, faster and cheaper manufacturing processes, and favorable payback time. The rapid development of solar energy applications in residential, commercial, and industrial sectors is making photovoltaic energy an integral component of new green facilities. To achieve high performance, efficiency, and reliability of photovoltaic plants, the early detection of PV faults is recommended. One of the most effective techniques is the infrared thermography method (IRT), as it provides fast, contactless, nondestructive, and real-time fault detection and diagnosis (FDD). The early studies that investigate the detection of photovoltaic faults using IRT are addressed in the studies [2-4]. The factors that should be carefully considered while using thermography measurements for photovoltaic modules in the outdoor conditions include qualified personnel, emissivity adjustment, distance of the object being inspected, angle of capturing, and ambient meteorological conditions [5-9]. Field IR imaging of PV modules provides a useful tool to identify different PV faults via the analysis of their thermal effects. The infrared image of the faulty module has thermal signatures that appear as regions with different temperatures in the captured image. However, these effects are difficult to interpret without careful anslysis of the interconnection between thermal anomalies and electrical operation behavior. The analysis of Instrumentation Mesure Métrologie Vol. 19, No. 5, October, 2020, pp. 311-325 Journal homepage: http://iieta.org/journals/i2m 311