Efficient Cell Segmentation from Electroluminescent Images of Single-Crystalline Silicon Photovoltaic Modules and Cell-Based Defect Identification Using Deep Learning with Pseudo-Colorization
Solar cells may possess defects during the manufacturing process in photovoltaic (PV) industries. To precisely evaluate the effectiveness of solar PV modules, manufacturing defects are required to be identified. Conventional defect inspection in industries mainly depends on manual defect inspection...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/13/4292 |
| _version_ | 1797529026029420544 |
|---|---|
| author | Horng-Horng Lin Harshad Kumar Dandage Keh-Moh Lin You-Teh Lin Yeou-Jiunn Chen |
| author_facet | Horng-Horng Lin Harshad Kumar Dandage Keh-Moh Lin You-Teh Lin Yeou-Jiunn Chen |
| author_sort | Horng-Horng Lin |
| collection | DOAJ |
| description | Solar cells may possess defects during the manufacturing process in photovoltaic (PV) industries. To precisely evaluate the effectiveness of solar PV modules, manufacturing defects are required to be identified. Conventional defect inspection in industries mainly depends on manual defect inspection by highly skilled inspectors, which may still give inconsistent, subjective identification results. In order to automatize the visual defect inspection process, an automatic cell segmentation technique and a convolutional neural network (CNN)-based defect detection system with pseudo-colorization of defects is designed in this paper. High-resolution Electroluminescence (EL) images of single-crystalline silicon (sc-Si) solar PV modules are used in our study for the detection of defects and their quality inspection. Firstly, an automatic cell segmentation methodology is developed to extract cells from an EL image. Secondly, defect detection can be actualized by CNN-based defect detector and can be visualized with pseudo-colors. We used contour tracing to accurately localize the panel region and a probabilistic Hough transform to identify gridlines and busbars on the extracted panel region for cell segmentation. A cell-based defect identification system was developed using state-of-the-art deep learning in CNNs. The detected defects are imposed with pseudo-colors for enhancing defect visualization using K-means clustering. Our automatic cell segmentation methodology can segment cells from an EL image in about <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2.71</mn></mrow></semantics></math></inline-formula> s. The average segmentation errors along the x-direction and y-direction are only <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.6</mn></mrow></semantics></math></inline-formula> pixels and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.4</mn></mrow></semantics></math></inline-formula> pixels, respectively. The defect detection approach on segmented cells achieves <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>99.8</mn><mo>%</mo></mrow></semantics></math></inline-formula> accuracy. Along with defect detection, the defect regions on a cell are furnished with pseudo-colors to enhance the visualization. |
| first_indexed | 2024-03-10T10:07:37Z |
| format | Article |
| id | doaj.art-85138d0140cd400397b6401bd044fb66 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T10:07:37Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-85138d0140cd400397b6401bd044fb662023-11-22T01:25:41ZengMDPI AGSensors1424-82202021-06-012113429210.3390/s21134292Efficient Cell Segmentation from Electroluminescent Images of Single-Crystalline Silicon Photovoltaic Modules and Cell-Based Defect Identification Using Deep Learning with Pseudo-ColorizationHorng-Horng Lin0Harshad Kumar Dandage1Keh-Moh Lin2You-Teh Lin3Yeou-Jiunn Chen4Department of Computer Science and Information Engineering, Southern Taiwan University of Science and Technology, Tainan 710301, TaiwanDepartment of Electrical Engineering, Southern Taiwan University of Science and Technology, Tainan 710301, TaiwanDepartment of Mechanical Engineering, Southern Taiwan University of Science and Technology, Tainan 710301, TaiwanDepartment of Mechanical Engineering, Southern Taiwan University of Science and Technology, Tainan 710301, TaiwanDepartment of Electrical Engineering, Southern Taiwan University of Science and Technology, Tainan 710301, TaiwanSolar cells may possess defects during the manufacturing process in photovoltaic (PV) industries. To precisely evaluate the effectiveness of solar PV modules, manufacturing defects are required to be identified. Conventional defect inspection in industries mainly depends on manual defect inspection by highly skilled inspectors, which may still give inconsistent, subjective identification results. In order to automatize the visual defect inspection process, an automatic cell segmentation technique and a convolutional neural network (CNN)-based defect detection system with pseudo-colorization of defects is designed in this paper. High-resolution Electroluminescence (EL) images of single-crystalline silicon (sc-Si) solar PV modules are used in our study for the detection of defects and their quality inspection. Firstly, an automatic cell segmentation methodology is developed to extract cells from an EL image. Secondly, defect detection can be actualized by CNN-based defect detector and can be visualized with pseudo-colors. We used contour tracing to accurately localize the panel region and a probabilistic Hough transform to identify gridlines and busbars on the extracted panel region for cell segmentation. A cell-based defect identification system was developed using state-of-the-art deep learning in CNNs. The detected defects are imposed with pseudo-colors for enhancing defect visualization using K-means clustering. Our automatic cell segmentation methodology can segment cells from an EL image in about <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2.71</mn></mrow></semantics></math></inline-formula> s. The average segmentation errors along the x-direction and y-direction are only <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.6</mn></mrow></semantics></math></inline-formula> pixels and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.4</mn></mrow></semantics></math></inline-formula> pixels, respectively. The defect detection approach on segmented cells achieves <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>99.8</mn><mo>%</mo></mrow></semantics></math></inline-formula> accuracy. Along with defect detection, the defect regions on a cell are furnished with pseudo-colors to enhance the visualization.https://www.mdpi.com/1424-8220/21/13/4292electroluminescence imagesingle-crystalline silicon photovoltaic modulecell segmentationdefect detectionpseudo-colorization |
| spellingShingle | Horng-Horng Lin Harshad Kumar Dandage Keh-Moh Lin You-Teh Lin Yeou-Jiunn Chen Efficient Cell Segmentation from Electroluminescent Images of Single-Crystalline Silicon Photovoltaic Modules and Cell-Based Defect Identification Using Deep Learning with Pseudo-Colorization Sensors electroluminescence image single-crystalline silicon photovoltaic module cell segmentation defect detection pseudo-colorization |
| title | Efficient Cell Segmentation from Electroluminescent Images of Single-Crystalline Silicon Photovoltaic Modules and Cell-Based Defect Identification Using Deep Learning with Pseudo-Colorization |
| title_full | Efficient Cell Segmentation from Electroluminescent Images of Single-Crystalline Silicon Photovoltaic Modules and Cell-Based Defect Identification Using Deep Learning with Pseudo-Colorization |
| title_fullStr | Efficient Cell Segmentation from Electroluminescent Images of Single-Crystalline Silicon Photovoltaic Modules and Cell-Based Defect Identification Using Deep Learning with Pseudo-Colorization |
| title_full_unstemmed | Efficient Cell Segmentation from Electroluminescent Images of Single-Crystalline Silicon Photovoltaic Modules and Cell-Based Defect Identification Using Deep Learning with Pseudo-Colorization |
| title_short | Efficient Cell Segmentation from Electroluminescent Images of Single-Crystalline Silicon Photovoltaic Modules and Cell-Based Defect Identification Using Deep Learning with Pseudo-Colorization |
| title_sort | efficient cell segmentation from electroluminescent images of single crystalline silicon photovoltaic modules and cell based defect identification using deep learning with pseudo colorization |
| topic | electroluminescence image single-crystalline silicon photovoltaic module cell segmentation defect detection pseudo-colorization |
| url | https://www.mdpi.com/1424-8220/21/13/4292 |
| work_keys_str_mv | AT hornghornglin efficientcellsegmentationfromelectroluminescentimagesofsinglecrystallinesiliconphotovoltaicmodulesandcellbaseddefectidentificationusingdeeplearningwithpseudocolorization AT harshadkumardandage efficientcellsegmentationfromelectroluminescentimagesofsinglecrystallinesiliconphotovoltaicmodulesandcellbaseddefectidentificationusingdeeplearningwithpseudocolorization AT kehmohlin efficientcellsegmentationfromelectroluminescentimagesofsinglecrystallinesiliconphotovoltaicmodulesandcellbaseddefectidentificationusingdeeplearningwithpseudocolorization AT youtehlin efficientcellsegmentationfromelectroluminescentimagesofsinglecrystallinesiliconphotovoltaicmodulesandcellbaseddefectidentificationusingdeeplearningwithpseudocolorization AT yeoujiunnchen efficientcellsegmentationfromelectroluminescentimagesofsinglecrystallinesiliconphotovoltaicmodulesandcellbaseddefectidentificationusingdeeplearningwithpseudocolorization |