融合空间-频域特征的轻量化 RT-DETR 单晶硅电池缺陷检测算法
DOI:
CSTR:
作者:
作者单位:

湖州师范大学

作者简介:

通讯作者:

中图分类号:

基金项目:

湖州市科技计划项目-公益性应用研究项目(2025GY009)


Defect detection algorithm for monocrystalline silicon solar cell EL images based on improved RT-DETR
Author:
Affiliation:

Fund Project:

Public Welfare Applied Research Project of Huzhou Science and Technology Plan (Grant No. 2025GY009)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对单晶硅太阳能电池电致发光(EL)图像中缺陷形态多样、对比度低、尺度差异大等问题,提出一种基于改进RT-DETR的缺陷检测算法GAE-DETR。首先设计了GDSANet主干网络模块,通过动态空间注意力机制实现缺陷显著区域的自适应聚焦,并引入频域增强前馈网络来捕获EL图像周期性栅格结构的异常变化。提出了ESA-PGE轻量化Transformer编码器,采用部分通道自注意力与动态稀疏门控机制,在降低计算复杂度的同时保持全局上下文建模能力。而所构建的DHAF双层次注意力特征融合模块,实现了跨尺度特征的精细化整合。实验结果表明,在自建的单晶硅电池EL图像数据集上,GAE-DETR的mAP50达到93.6%、mAP50-95达到71.2%,相比基准模型分别提升5.2和8.9个百分点,参数量减少17.4%,计算量降低19.2%,实现了检测精度与计算效率的双重优化。

    Abstract:

    Aiming at the challenges of diverse defect morphologies, low contrast, and large scale variations in electroluminescence (EL) images of monocrystalline silicon solar cells, this paper proposes an improved RT-DETR-based defect detection algorithm, namely GAE-DETR. First, a GDSANet backbone module is designed, which adaptively focuses on salient defect regions through a dynamic spatial attention mechanism, and introduces a frequency-domain enhanced feed-forward network to capture abnormal changes in the periodic grid structure of EL images. Second, an ESA-PGE lightweight Transformer encoder is proposed, which employs partial channel self-attention and dynamic sparse gating mechanisms to reduce computational complexity while preserving global context modeling capability. Furthermore, a DHAF dual-level attention feature fusion module is constructed to achieve fine-grained integration of cross-scale features. Experimental results on a self-built monocrystalline silicon solar cell EL image dataset show that GAE-DETR achieves 93.6% mAP50 and 71.2% mAP50-95, which are 5.2 and 8.9 percentage points higher than the baseline model, respectively. Meanwhile, the number of parameters is reduced by 17.4% and the computational complexity (FLOPs) is reduced by 19.2%, realizing the dual optimization of detection accuracy and computational efficiency.

    参考文献
    相似文献
    引证文献
引用本文
分享
相关视频

文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2026-04-24
  • 最后修改日期:2026-05-19
  • 录用日期:2026-05-19
  • 在线发布日期:
  • 出版日期:
文章二维码