| Title |
Giliais neuroniniais tinklais grįstas automatizuotas įrankis fotomodulių gamybos kokybės kontrolei / |
| Translation of Title |
Development of automated tool for solar module quality control using deep neural network. |
| Authors |
Vizgirda, Rytis |
| Full Text |
|
| Pages |
42 |
| Keywords [eng] |
artificial intelligence ; machine learning ; image recognition ; solar photovoltaic modules ; solar photovoltaic module’s quality |
| Abstract [eng] |
This master’s thesis explores the possibility of applying artificial intelligence to improve the quality control parameters for the production of solar photovoltaic modules. The project presents a study that uses machine learning and image recognition algorithms trained to determine the quality of a solar photovoltaic module by classifying the module as bad or good. In order to create the model, data from the solar photovoltaic modules manufacturing plant, which is based in Lithuania were used. Data are presented in electroluminescent images. The study showed that the classification tool for solar photovoltaic modules based on deep neural networks is able to accurately and quickly identify and classify the manufactured module. In order to make sure that the appropriate model of artificial intelligence was chosen to solve the set problem, a comparison of the developed model with a simple linear classifier was performed. The model based on deep neural networks has been found to be significantly more accurate and reliable. |
| Dissertation Institution |
Kauno technologijos universitetas. |
| Type |
Master thesis |
| Language |
Lithuanian |
| Publication date |
2022 |
