Abstract
As the photovoltaic (PV) systems are universally utilized in power systems, the defect of solar cells, the core components of PV system requires to be detected in a low-cost and high-efficiency method, because of its wide application and direct influence on power generation efficiency and system stability. The principal aim of this study is to apply transfer learning in defect detection of polycrystalline cells with image-level labelled mono images and unlabelled poly images. The experiment was conducted with DAN models based on a MK-MMD to represent the distance between source domain and target domain and Resnet-50 backbone to learn transferable features. Three contrast methods were designed to make comparison with DAN. It has been proved that DAN model based on MK-MMD and Resnet-50 shows a promising performance on transferring from monocrystalline tasks to polycrystalline tasks.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
