International Journal of Electrical and Computer Engineering (IJECE) Vol. 13, No. 5, October 2023, pp. 5674~5680 ISSN: 2088-8708, DOI: 10.11591/ijece.v13i5.pp5674-5680  5674 Journal homepage: http://ijece.iaescore.com Ensembling techniques in solar panel quality classification Trong Hieu Luu 1 , Phan Nguyen Ky Phuc 2 , Tran Lam 3 , Zhi-qiu Yu 4 , Van Tinh Lam 5 1 College of Engineering, Can Tho University, Can Tho City, Vietnam 2 School of industrial engineering and management, International University-Vietnam National University, Ho Chi Minh City, Vietnam 3 School of Mechanical Engineering, Hanoi University of Science and Technology, Ha Noi City, Vietnam 4 Department of Industrial Management, National Taiwan University of Science and Technology, Taipei, Taiwan 5 Department of Electrical Engineering, Bac Lieu Vocational College, Bac Lieu, Vietnam Article Info ABSTRACT Article history: Received Nov 15, 2022 Revised Feb 11, 2023 Accepted Mar 9, 2023 Solar panel quality inspection is a time consuming and costly task. This study tries to develop as reliable method for evaluating the panels quality by using ensemble technique based on three machine learning models namely logistic regression, support vector machine and artificial neural network. The data in this study came from infrared camera which were captured in dark room. The panels are supplied with direct current (DC) power while the infrared camera is located perpendicular with panel surface. Dataset is divided into four classes where each class represent for a level of damage percentage. The approach is suitable for systems which has limited resources as well as number of training images which is very popular in reality. Result shows that the proposed method performs with the accuracy is higher than 90%. Keywords: Electroluminescence image Ensembling Image processing Machine learning Solar panel quality This is an open access article under the CC BY-SA license. Corresponding Author: Phan Nguyen Ky Phuc School of industrial engineering and management, International University-Vietnam National University Quarter 6, Linh Trung Ward, Thu Duc District, Ho Chi Minh City, Vietnam Email: pnkphuc@hcmiu.edu.vn 1. INTRODUCTION To reduce the negative impacts on climate as well as obtain a sustainable development at the energy field, many researchers around the world are focusing on finding the new energy resources for substituting traditional ones which often emit large quantities of CO2 to the environment. In tropical countries like Vietnam where the number of sunshine hours is about 2,000-2,600 per year, solar energy is an ideal and #promising renewable energy source which is encouraged by government for expansion and investment [1]. Photovoltaic panels are the most important component of a solar energy system. Under ideal conditions, the lifecycle of panels typically varies from 25 to 30 years [2]. However, this cycle is significantly shortened due to several environmental factors such as rain, wind, temperature, and radiation from the sun according to [3]. To limit the undesirable effects of these factors on lifespan of solar panels, material quality improvement [4], [5] is the approach which is studies by most companies. However, this approach is expensive and require strict conditions for experiment as well as costly facility. Currently to verify quality of panels and detect the crack before selling them to the market, the solar industry has applied technique, namely resonance ultrasonic vibration (RUV) to screen them [6]. According to [7], photovoltaic cell is a p-n semiconductor layer which is similar to ordinary diodes. The characteristics of these cells include absorbing sunlight and producing infrared electroluminescence (EL) when they are supplied with direct current (DC) power. Infrared light falls just outside the visible spectrum but can be observed with proper cameras. According to [8]–[10], electroluminescence image are valuable data which can be used to predict the conditions of panels. However, in their studies information of experiment preparation was not fully provided and the approaches differed