Using CNNs for Photovoltaic Panel Defect Detection via Infrared Thermography to Support Industry 4.0

Authors

DOI:

https://doi.org/10.2478/bsrj-2024-0003

Keywords:

Convolutional Neural Networks, Photovoltaic Panels, Defect Detection, Infrared Thermography, Solar Energy

Abstract

Background: This study demonstrates how convolutional neural networks (CNNs), supported by open-source software and guided by corporate social responsibility (CSR), can enhance photovoltaic (PV) panel maintenance. Connecting industrial informatics with sustainable practices underscores the potential for more efficient and responsible energy systems within Industry 4.0. The rapid expansion of solar power necessitates effective maintenance and inspection of PV panels to ensure optimal performance and longevity. CNNs have emerged as potent tools for detecting defects in PV panels through infrared thermography (IRT). Objectives: The review aims to evaluate CNNs' effectiveness in detecting PV panel defects, align their capabilities with the IEC TS 62446-3:2017 standard, and assess their economic benefits. Methods/Approach: A systematic review of literature focused on studies using CNNs and IRT for PV panel defect detection. The analysis compared performance metrics, economic benefits, and alignment with industry standards. Results: CNN models demonstrated high accuracy in defect detection, with most achieving above 90%. Integrating UAVs for image acquisition significantly reduced inspection times and costs. Conclusions: CNNs are highly effective in detecting PV panel defects, offering substantial economic benefits and potential for industry-wide standardisation. Further research is needed to enhance model robustness across diverse conditions and PV technologies.

Author Biographies

Mislav Spajić, Algebra University

Mislav Spajić holds a degree in computer engineering. He completed a Professional Graduate study program in Applied Computer Engineering, sub-specialisation in Data Science at Algebra University in 2022. He works full-time for Hrvatska poštanska banka p.l.c. as a senior data architect for the development of advanced analytical models and reporting systems. Besides that, he works part-time for Algebra University as an assistant lecturer. He also works as an external consultant in the field of data science for the company Airspect Ltd., focusing on the development of deep learning models in the domain of computer vision. His areas of professional interest are data warehousing and business intelligence, cloud computing, machine learning, computer vision, remote sensing, and unmanned aerial systems. The author can be contacted at mislav@airspect.hr

Mirko Talajić, Algebra University

Mislav Spajić holds a degree in computer engineering. He completed a Professional Graduate study program in Applied Computer Engineering, sub-specialisation in Data Science at Algebra University in 2022. He works full-time for Hrvatska poštanska banka p.l.c. as a senior data architect for the development of advanced analytical models and reporting systems. Besides that, he works part-time for Algebra University as an assistant lecturer. He also works as an external consultant in the field of data science for the company Airspect Ltd., focusing on the development of deep learning models in the domain of computer vision. His areas of professional interest are data warehousing and business intelligence, cloud computing, machine learning, computer vision, remote sensing, and unmanned aerial systems. The author can be contacted at mislav@airspect.hr

Leo Mršić, Algebra University

Prof. Dr. Leo Mršić is a full professor and scientist in the field of computing and information sciences with international experience in designing, implementing, and applying data-driven and artificial intelligence solutions. He is the Vice-Rector for Science and Research at Algebra University, head of the Center for Digital Transformation at the Rudolfovo Public Research Center, and head of the Data, AI, and Robotics (DAIRO) Silver i-Space Data Center at Algebra LAB. He is a permanent court expert in finance, accounting, bookkeeping, and informatics, holds an IPMA A certification, is a senior member of IEEE (R8), and serves as the Vice President for Technological Development and Innovation at the National Council for Higher Education, Science, and Technological Development. He is the author and co-author of over 75 scientific papers, holds 4 international patents, and has led more than 100 scientific research and commercial projects. Additionally, he has mentored over 40 undergraduate, graduate, and doctoral theses. The author can be contacted at leo.mrsic@algebra.hr

Downloads

Published

2024-09-27