基于FDI-YOLOv10n的锂离子电池表面缺陷多通道图像融合检测算法研究

王阳阳; 王卫军; 王建; 黄祖成; 陈金源; 江旭耀

doi:10.19799/j.cnki.2095-4239.2025.0905

您当前的位置：

首页 >

文章列表页 >

基于FDI-YOLOv10n的锂离子电池表面缺陷多通道图像融合检测算法研究

储能测试与评价 | 更新时间：2026-04-29

- 基于FDI-YOLOv10n的锂离子电池表面缺陷多通道图像融合检测算法研究
- Research on a multi-channel image fusion detection algorithm for surface defects of lithium-ion batteries based on FDI-YOLOv10n
- 储能科学与技术 2026年15卷第4期页码：1396-1408
- 作者机构：
  
  1.西安建筑科技大学机电工程学院，陕西西安 710055
  2.广州中国科学院先进技术研究所，广东广州 511458
- 作者简介：
  
  王阳阳（2001—），女，硕士研究生，主要研究方向为智能检测技术应用开发，E-mail：18091656937@163.com；
  王卫军，正高级工程师，主要研究方向为自动化技术、机械工业、计算机软件及计算机应用等，E-mail：wj.wang@giat.ac.cn。
- 基金信息：
- DOI：10.19799/j.cnki.2095-4239.2025.0905
  中图分类号： TP 274
- 收稿：2025-10-14，
  
  修回：2025-11-05，
  
  纸质出版：2026-04-28
- 稿件说明：
移动端阅览
王阳阳, 王卫军, 王建, 等. 基于FDI-YOLOv10n的锂离子电池表面缺陷多通道图像融合检测算法研究[J]. 储能科学与技术, 2026, 15(4): 1396-1408.

WANG Yangyang, WANG Weijun, WANG Jian, et al. Research on a multi-channel image fusion detection algorithm for surface defects of lithium-ion batteries based on FDI-YOLOv10n[J]. Energy Storage Science and Technology, 2026, 15(4): 1396-1408.
王阳阳, 王卫军, 王建, 等. 基于FDI-YOLOv10n的锂离子电池表面缺陷多通道图像融合检测算法研究[J]. 储能科学与技术, 2026, 15(4): 1396-1408. DOI： 10.19799/j.cnki.2095-4239.2025.0905.

WANG Yangyang, WANG Weijun, WANG Jian, et al. Research on a multi-channel image fusion detection algorithm for surface defects of lithium-ion batteries based on FDI-YOLOv10n[J]. Energy Storage Science and Technology, 2026, 15(4): 1396-1408. DOI： 10.19799/j.cnki.2095-4239.2025.0905.

摘要

针对镍片连接片微小缺陷(划痕、凹坑等)在二维灰度和三维深度信息中均呈现对比度低、深度变化弱的检测难点，本研究提出一种基于FDI-YOLOv10n模型的多通道图像融合检测框架。首先通过通道级图像融合方法，将灰度图像2D纹理特征与深度图像3D空间特征在通道维度深度融合，增强模型对缺陷的表征能力。其次，为进一步提升特征提取效率，设计FasterCGLU-MANet混合聚合模块，结合改进型FasterBlock-CGLU单元与MANet架构，提升特征语义表达深度并加速推理；同时引入鲁棒特征下采样(RFD)机制，通过浅层与深层分级处理策略，有效缓解了图像冗余信息干扰问题；最后，设计Inner-MPDIoU复合损失函数，结合内部区域重叠约束与边界对齐优化，显著提升了边界框回归稳定性。实验结果表明，所提模型在自制数据集上达到96.1%的mAP@0.5及333.3 帧/s的检测速度，实现锂离子电池工业级高精度与实时性的检测需求。

Abstract

Micro-defects on nickel sheet connection pieces

such as scratches and pits

are challenging to detect due to their low contrast and weak depth variations in both two-dimensional grayscale images and three-dimensional depth data. To address this challenge

this study proposes a multi-channel image fusion detection framework based on the FDI-YOLOv10n model. First

a channel-level image fusion strategy is employed to deeply integrate two-dimensional texture information from grayscale images with three-dimensional spatial features from depth images at the channel level

thereby enhancing the ability of the model to extract discriminative defect features. Second

to further improve feature extraction efficiency

a FasterCGLU-MANet hybrid aggregation module is developed by combining an improved FasterBlock-CGLU unit with the MANet architecture

enabling richer semantic feature representation while accelerating inference. Additionally

a robust feature downsampling mechanism is introduced to mitigate interference from redundant image information through a hierarchical processing strategy spanning shallow and deep network layers. Finally

an Inner-MPDIoU composite loss function is designed by integrating internal-region overlap constraints with boundary alignment optimization

thereby substantially improving the stability of bounding-box regression. Experimental results demonstrate that the proposed model achieves a mAP@0.5 of 96.1% and a detection speed of 333.3 fps on a self-constructed dataset

satisfying industrial requirements for high-precision and real-time defect detection in lithium-ion battery manufacturing.

关键词

Keywords

references

MASIAS A, MARCICKI J, PAXTON W A. Opportunities and challenges of lithium ion batteries in automotive applications[J]. ACS Energy Letters, 2021, 6(2): 621-630.

王莉, 谢乐琼, 田光宇, 等. 锂离子电池安全事故: 安全性问题,还是可靠性问题[J]. 储能科学与技术, 2021, 10(1): 1-6.

WANG L, XIE L Q, TIAN G Y, et al. Safety accidents of Li-ion batteries: Reliability issues or safety issues[J]. Energy Storage Science and Technology, 2021, 10(1): 1-6.

甘露雨, 陈汝颂, 潘弘毅, 等. 锂电池安全性多尺度研究策略: 实验与模拟方法[J]. 储能科学与技术, 2022, 11(3): 852-865. DOI:10.19799/j.cnki.2095-4239.2022.0047.

GAN L Y, CHEN R S, PAN H Y, et al. Multiscale research strategy of lithium ion battery safety issue: Experimental and simulation methods[J]. Energy Storage Science and Technology, 2022, 11(3): 852-865. DOI:10.19799/j.cnki.2095-4239.2022.0047.

XU Y X, NIU L C, YANG H, et al. Optimization of lithium battery pole piece thickness control system based on GA-BP neural network[J]. Journal of Nanoelectronics and Optoelectronics, 2019, 14(7): 978-986. DOI:10.1166/jno.2019.2650.

邵瑞. 基于深度学习的工业产品缺陷检测研究与应用[D]. 济南: 齐鲁工业大学, 2024.SHAO R. Research and application of industrial product defect detection based on deep learning[D]. Jinan: Qilu University of Technology, 2024.

李博文, 杨续来, 葛肖尽, 等. 锂离子电池极片表面缺陷检测方法研究进展[J]. 仪器仪表学报, 2025, 46(1): 125-146. DOI:10.19650/j.cnki.cjsi.J2413335.

LI B W, YANG X L, GE X J, et al. Research progress on defect detection methods for electrode surface of lithium-ion battery[J]. Chinese Journal of Scientific Instrument, 2025, 46(1): 125-146. DOI:10.19650/j.cnki.cjsi.J2413335.

LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single shot MultiBox detector[C]//Computer Vision-ECCV 2016. Cham: Springer, 2016: 21-37. DOI:10.1007/978-3-319-46448-0_2.

REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). June 27-30, 2016. Las Vegas, NV, USA. IEEE, 2016: 779-788.. DOI:10.1109/cvpr.2016.91.

WANG C Y, YEH I H, MARK LIAO H Y. YOLOv9: Learning what you want to learn using programmable gradient information[C]//Computer Vision-ECCV 2024. Cham: Springer, 2025: 1-21. DOI:10.1007/978-3-031-72751-1_1.

CHEN H, CHEN K, DING G G, et al. YOLOv10: Real-time end-to-end object detection[C]//Advances in Neural Information Processing Systems 37. December 10-15, 2024. Vancouver, BC, Canada. Neural Information Processing Systems Foundation, Inc. (NeurIPS), 2024: 107984-108011. DOI:10.52202/079017-3429.

GIRSHICK R. Fast R-CNN[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV). ACM, 2015: 1440-1448. DOI:10.1109/ICCV.2015.169.

CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers[C]//Computer Vision-ECCV 2020. Cham: Springer, 2020: 213-229. DOI:10.1007/978-3-030-58452-8_13.

ZONG Z F, SONG G L, LIU Y. DETRs with collaborative hybrid assignments training[C ] //2023 IEEE/CVF International Conference on Computer Vision (ICCV). October 1-6, 2023 , Paris, France. IEEE, 2024: 6725-6735. DOI:10.1109/ICCV51070. 2023.00621.

邢远秀, 刘颛玮, 邢玉峰, 等. BDD-DETR: 高效感知小目标的锂电池表面缺陷检测[J]. 储能科学与技术, 2025, 14(1): 370-379.

XING Y X, LIU Z W, XING Y F, et al. BDD-DETR: An efficient algorithm for detecting small surface defects on lithium batteries[J]. Energy Storage Science and Technology, 2025, 14(1): 370-379.

朱永平, 程博, 熊聪, 等. 多尺度YOLOv5算法检测锂离子电池表面缺陷[J]. 电池, 2025, 55(1): 71-77. DOI:10.19535/j.1001-1579.2025.01.011.

ZHU Y P, CHENG B, XIONG C, et al. Multiscale YOLOv5 algorithm for surface defect detection of pouch Li-ion battery[J]. Battery Bimonthly, 2025, 55(1): 71-77. DOI:10.19535/j.1001-1579.2025.01.011.

何涛, 张成娟, 雷卓, 等. 软包装锂离子电池表面凹坑缺陷检测方法[J]. 电池, 2024, 54(3): 358-363. DOI:10.19535/j.1001-1579. 2024.03.014.

HE T, ZHANG C J, LEI Z, et al. Surface pit defects detecting method of pouch Li-ion battery[J]. Battery Bimonthly, 2024, 54(3): 358-363. DOI:10.19535/j.1001-1579.2024.03.014.

孙浩然, 李雅雯, 韩有军, 等. 基于拓扑滤波与改进Canny算子的锂离子电池电极缺陷检测[J]. 储能科学与技术, 2022, 11(10): 3297-3305. DOI:10.19799/j.cnki.2095-4239.2022.0167.

SUN H R, LI Y W, HAN Y J, et al. Lithium-ion battery electrode defect detection based on topological filtering and improved Canny operator[J]. Energy Storage Science and Technology, 2022, 11(10): 3297-3305. DOI:10.19799/j.cnki.2095-4239.2022.0167.

DAI X Y, CHEN Y P, XIAO B, et al. Dynamic head: Unifying object detection heads with attentions[C ] //2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 20-25, 2021 , Nashville, TN, USA. IEEE, 2021: 7369-7378. DOI:10.1109/CVPR46437.2021.00729.

LI H, WU X J, KITTLER J. Infrared and visible image fusion using a deep learning framework[C ] //2018 24th International Conference on Pattern Recognition (ICPR). August 20-24, 2018 , Beijing, China. IEEE, 2018: 2705-2710. DOI:10.1109/ICPR. 2018.8546006.

WANG X H, LI S, CHEN C, et al. Data-level recombination and lightweight fusion scheme for RGB-D salient object detection[J]. IEEE Transactions on Image Processing, 2021, 30: 458-471. DOI:10.1109/TIP.2020.3037470.

CHEN Y X, YAN F W, YIN Z S, et al. Robust LiDAR-camera 3-D object detection with object-level feature fusion[J]. IEEE Sensors Journal, 2024, 24(18): 29108-29120. DOI:10.1109/JSEN. 2024.3436834.

LYU G H, SIMA C, GAO Y B, et al. SIGFusion: Semantic information-guided infrared and visible image fusion[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 5032218. DOI:10.1109/TIM.2024.3457951.

谢雨欣, 龚烨飞, 谷心浩, 等. 基于RGB-D特征融合的焊缝表面缺陷检测方法[J]. 焊接学报, 2024, 45(12): 72-78. DOI:10.12073/j.hjxb.20230712002.

XIE Y X, GONG Y F, GU X H, et al. Research on weld surface defect detection method based on RGB-D feature fusion[J]. Transactions of the China Welding Institution, 2024, 45(12): 72-78. DOI:10.12073/j.hjxb.20230712002.

李明, 鹿朋, 朱龙, 等. 基于RGB-D融合的密集遮挡抓取检测[J]. 控制与决策, 2023, 38(10): 2867-2874.

LI M, LU P, ZHU L, et al. Densely occluded grasping objects detection based on RGB-D fusion[J]. Control and Decision, 2023, 38(10): 2867-2874.

ZHENG Z H, WANG P, LIU W, et al. Distance-IoU loss: Faster and better learning for bounding box regression[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7): 12993-13000. DOI:10.1609/aaai.v34i07.6999.

BAVIRISETTI D P, DHULI R. Two-scale image fusion of visible and infrared images using saliency detection[J]. Infrared Physics & Technology, 2016, 76: 52-64. DOI:10.1016/j.infrared.2016.01.009.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据