Surface Defect Detection of Lithium Battery Electrodes Based on Improved Unet Network

Chen Xiao-rong; Yang Xue-rong; Cheng Si-yuan; Liu Guo-dong

doi:10.12052/gdutxb.220161

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Surface Defect Detection of Lithium Battery Electrodes Based on Improved Unet Network

更新时间：2026-05-27

- Surface Defect Detection of Lithium Battery Electrodes Based on Improved Unet Network
- Vol. 40, Issue 4, Pages: 60-66, 93(2023)
- 作者机构：
  
  广东工业大学机电工程学院,广东,广州,510006
- 作者简介：
- 基金信息：
- DOI：10.12052/gdutxb.220161
  CLC： TP391.41;TM912
- Online First：25 July 2023，
  
  Published：2023
- 稿件说明：
移动端阅览
陈晓荣, 杨雪荣, 成思源, 刘国栋. 基于改进Unet网络的锂电池极片表面缺陷检测[J]. 广东工业大学学报, 2023, 40(4): 60-66, 93.

Chen Xiao-rong, Yang Xue-rong, Cheng Si-yuan, et al. Surface Defect Detection of Lithium Battery Electrodes Based on Improved Unet Network[J]. 2023, 40(4): 60-66, 93.
陈晓荣, 杨雪荣, 成思源, 刘国栋. 基于改进Unet网络的锂电池极片表面缺陷检测[J]. 广东工业大学学报, 2023, 40(4): 60-66, 93. DOI： 10.12052/gdutxb.220161.

Chen Xiao-rong, Yang Xue-rong, Cheng Si-yuan, et al. Surface Defect Detection of Lithium Battery Electrodes Based on Improved Unet Network[J]. 2023, 40(4): 60-66, 93. DOI： 10.12052/gdutxb.220161.

摘要

为避免锂电池由于极片表面缺陷导致寿命缩短或出现安全事故等问题，需要研究高效准确的锂电池极片缺陷检测方法。本文使用结构简单的Unet语义分割网络对锂电池进行缺陷分割。为提高分割精度，首先用与Unet编码结构相似的VGG16替换原网络中的编码结构，以获取训练好的预训练权重；然后将简易的融合金字塔网络(Simply Fusion Pyramid Network，SFPN)的特征融合模块加入Unet网络的跳跃连接上，避免特征图之间出现较大的信息差异；最后运用标签平滑来优化损失函数，防止网络出现过拟合现象。通过实验验证，本文方法优化后的语义分割网络准确率提升至93.70%，误分割、分割不连续等现象出现概率明显降低，该优化流程具有一定实用价值。

Abstract

In order to avoid the problems of life shortening or safety accidents caused by the surface defects of lithium batteries

it is necessary to study an efficient and accurate methods for lithium battery electrode plate defect detection. In this research

the simple Unet semantic segmentation network is used to detect defects of lithium battery. In order to improve the segmentation accuracy

first the coding structure in the original network is replaced with VGG16

which is similar to the Unet coding structure

to obtain the pre-training weights had been trained. Then

feature fusion module of the simply fusion pyramid network (SFPN) is added to the skip connection of the Unet network to avoid large information differences between feature maps. Finally

label smoothing is applied to optimize the loss function to prevent the network from overfitting. Through experimental verification

the accuracy of the semantic segmentation network optimized by the proposed method is improved to 93.70%

and the probability of false segmentation and segmentation discontinuity is significantly reduced. This optimization process has certain practical value.

关键词

Keywords

references

WANG D W, LUO Y Q. Problems faced by electric vehicles [J]. Automotive Digest, 2019(8): 22-31.

TANG B, KONG J Y, WU S Q. Review of surface defect detection based on machine vision [J]. Journal of Image and Graphics, 2017, 22(12): 1640-1663.

谢永杰, 智贺宁. 基于机器视觉的图像识别技术研究综述[J]. 科学技术创新, 2018 (7) : 74-75

吴凯, 杨新志. 浅述人工智能的深度学习[J]. 石河子科技, 2020 (6) : 44-45

KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM, 2017, 60(6): .84-90.

ZHOU J H, GONG Y J, Detection of electrode defects in lithium batteries based on convolutional neural networks[J]. Electronic Measurement Technology, 2019, 42(19) : 182-186.

ZHOU J H, GONG L F, WANG S Y. Research on detection of electrode fold of spirally wound flattened lithium batteries [J]. Instrument Technique and Sensor, 2021(5): 107-111.

HUANG M T, LIAN Y X. Lithium battery electrode plate surface defect detection based on improved Canny operator [J]. Chinese Journal of Scientific Instrument, 2021, 42(10): 199-209.

张旭. 基于深度卷积神经网络的铝材表面缺陷检测[D]. 上海: 华东理工大学, 2020.

ZHANG Y, WANG X D. A review and thinking of deep learning with a restricted number of samples [J]. Journal of Guangdong University of Technology, 2022, 39(5): 1-8.

ZEILER M D, FERGUS R. Visualizing and understanding convolutional networks[C]//Fleet D. European Conference on Computer Vision. Cham: Springer, 2014: 818-833.

SANDLER M, HOWARD A, ZHU M, et al. Mobilenetv2: inverted residuals and linear bottlenecks[C]//The IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 4510-4520.

HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]// The IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.

HUANG J H, WANG Z Y. A research on deep learning object detection algorithm based on feature fusion. [J]. Journal of Guangdong University of Technology, 2021, 38(4): 52-58.

DENG J, DONG W, SOCHER R, et al. Imagenet: a large-scale hierarchical image database[C]//2009 IEEE Conference On Computer Vision and Pattern Recognition. Miami, FL: IEEE, 2009: 248-255.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

High-resolution Feature Network for 3D Point Cloud Segmentation and Classification

Pathology Image Segmentation Network Based on Multiscale Convolution and Attention Mechanism

Local Orthogonal Feature Fusion for Few-Shot Image Classification

Super-resolution Reconstruction of Images Based on Blueprint Separable Residual Distillation Network

An Insulator Burst Defect Detection Method Based on YOLOv4-MP

Related Author

Liu Dongfeng

Zhu Junjie

Pan Dan

Yang Baoyao

Lai Junhao

Zeng An

Huang Guo-heng

Cheng Liang-lun

Related Institution

School of Information Engineering, Guangdong University of Technology

School of Computer Science and Technology, Guangdong University of Technology

School of Electronics and Information, Guangdong Polytechnic Normal University

Yunnan Electric Power Research Institute, Yunnan Power Grid Co., Ltd

School of Applied Mathematics, Guangdong University of Technology

AI问答

⁰