Research on a Photovoltaic Panel Dust Detection Algorithm Based on 3D Data Generation

Chengzhi Xie, Qifen Li, Yongwen Yang, Liting Zhang and Xiaojing Liu ()
Additional contact information
Chengzhi Xie: College of Energy and Mechanical Engineering, Shanghai University of Electric Power, Shanghai 201306, China
Qifen Li: College of Energy and Mechanical Engineering, Shanghai University of Electric Power, Shanghai 201306, China
Yongwen Yang: College of Energy and Mechanical Engineering, Shanghai University of Electric Power, Shanghai 201306, China
Liting Zhang: College of Energy and Mechanical Engineering, Shanghai University of Electric Power, Shanghai 201306, China
Xiaojing Liu: College of Energy and Mechanical Engineering, Shanghai University of Electric Power, Shanghai 201306, China

Energies, 2024, vol. 17, issue 20, 1-16

Abstract: With the rapid advancements in AI technology, UAV-based inspection has become a mainstream method for intelligent maintenance of PV power stations. To address limitations in accuracy and data acquisition, this paper presents a defect detection algorithm for PV panels based on an enhanced YOLOv8 model. The PV panel dust dataset is manually extended using 3D modeling technology, which significantly improves the model’s ability to generalize and detect fine dust particles in complex environments. SENetV2 is introduced to improve the model’s perception of dust features in cluttered backgrounds. AKConv replaces traditional convolution in the neck network, allowing for more flexible and accurate feature extraction through arbitrary kernel parameters and sampling shapes. Additionally, a DySample dynamic upsampler accelerates processing by 8.73%, improving the frame rate from 87.58 FPS to 95.23 FPS while maintaining efficiency. Experimental results show that the 3D image expansion method contributes to a 4.6% increase in detection accuracy, an 8.4% improvement in recall, a 5.7% increase in mAP@50, and a 15.1% improvement in mAP@50-95 compared to the original YOLOv8. The expanded dataset and enhanced model demonstrate the effectiveness and practicality of the proposed approach.

Keywords: dust detection; YOLOv8; SENetV2; adaptive convolution; 3D generation (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/17/20/5222/pdf (application/pdf)
https://www.mdpi.com/1996-1073/17/20/5222/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:17:y:2024:i:20:p:5222-:d:1502703

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().