改进YOLOv8n算法的船舶工业钢材表面缺陷检测

刘鹏; 侯博文; 王彩霞; 姜晓娇; 丛海芳

doi:10.12382/bgxb.2025.0145

您当前的位置：

首页 >

文章列表页 >

改进YOLOv8n算法的船舶工业钢材表面缺陷检测

更新时间：2026-04-24

- 改进YOLOv8n算法的船舶工业钢材表面缺陷检测
- Surface Defect Detection of Steel for Shipbuilding Based on Improved YOLOv8n Algorithm
- 兵工学报 2026年47卷第3期页码：250145
- 作者机构：
  
  长春理工大学电子信息工程学院，吉林长春 130022
  电磁空间安全全国重点实验室，天津 300000
- 作者简介：
  
  通信作者邮箱：liup@cust.edu.cn
- 基金信息：
  
  吉林省科技发展计划项目(20240302019GX)
- DOI：10.12382/bgxb.2025.0145
  中图分类号： TP391.4
- 收稿：2025-03-05，
  
  网络首发：2026-02-03，
  
  纸质出版：2026-03
- 稿件说明：
移动端阅览
刘鹏, 侯博文, 王彩霞, 等. 改进YOLOv8n算法的船舶工业钢材表面缺陷检测[J]. 兵工学报, 2026,47(3):250145.

LIU Peng, HOU Bowen, WANG Caixia, et al. Surface Defect Detection of Steel for Shipbuilding Based on Improved YOLOv8n Algorithm[J]. Acta Armamentarii, 2026, 47(3): 250145.
刘鹏, 侯博文, 王彩霞, 等. 改进YOLOv8n算法的船舶工业钢材表面缺陷检测[J]. 兵工学报, 2026,47(3):250145. DOI： 10.12382/bgxb.2025.0145.

LIU Peng, HOU Bowen, WANG Caixia, et al. Surface Defect Detection of Steel for Shipbuilding Based on Improved YOLOv8n Algorithm[J]. Acta Armamentarii, 2026, 47(3): 250145. DOI： 10.12382/bgxb.2025.0145.

摘要

为提高船舶工业中钢材表面缺陷检测的准确性，针对现有YOLOv8n算法在特征提取能力不足、检测精度低以及特征融合不充分等问题，提出一种基于改进YOLOv8n的钢材表面缺陷检测方法。构建高效视觉空间金字塔池化增强层聚合网络（Efficient Vision Transformer-Spatial Pyramid Pooling with Enhanced Layer Aggregation Network，EfficientViT-SPPELAN），以增强多维度特征提取能力；设计多尺度时空卷积（Multi-Scale Spatial-Temporal Convolution，MSSTConv）实现多尺度特征融合；在此基础上构建多尺度时空（Multi-Scale Spatial-Temporal，MSST）模块以获取丰富的上下文信息，提高缺陷定位精度并降低计算复杂度，从而提升算法的推理效率。基于东北大学表面缺陷数据集（Northeastern University Surface Defect Dataset，NEU-DET）和镀锌钢10类缺陷检测数据集（Galvanized Steel 10-category Defect Detection Dataset，GC10-DET）两个数据集的实验结果表明，所提方法的检测精准度相较于原始YOLOv8n算法分别提升6.8%和5.7%，均值平均精确率mAP@0.5分别提高3.7%和7.9%；每秒帧数（Frames Per Second，FPS）分别达到189帧/s和142帧/s。研究结果表明，该方法在提升检测精度的同时保持较高计算效率，能够有效完成船舶钢材表面缺陷的定位和类别识别，满足工业场景对检测精度与实时性的需求。

Abstract

In order to improve the accuracy of steel surface defect detection in the shipbuilding industry

a steel surface defect detection method based on an improved YOLOv8n algorithm is proposed to address the issues of insufficient feature extraction capability

low detection accuracy

and inadequate feature fusion of the existing YOLOv8n algorithm. In this method

an efficient vision transformer-spatial pyramid pooling with enhanced layer aggregation network（EfficientViT-SPPELAN）is constructed to enhance the multi-dimensional feature extraction capabilities. A multi-scale spatial-temporal convolution（MSSTConv）is designed to achieve multi-scale feature fusion. Additionally

a multi-scale spatial-temporal（MSST）module is constructed to capture rich contextual information

which improves the defect localization accuracy and reduces the computational complexity

thereby enhancing the inference efficiency of the algorithm. Experimental results based on the Northeastern University surface defect dataset（NEU-DET）and the galvanized steel 10-category defect detection dataset（GC10-DET）demonstrate that the proposed algorithm improves the detection accuracy by 6.8% and 5.7%

respectively

compared to the original YOLOv8n algorithm

and increase the mean average precision（mAP@ 0.5）by 3.7% and 7.9%

respectively. The frames per second（FPS）reach 189 and 142. These results show that the proposed algorithm not only enhances the detection accuracy but also maintains the high computational efficiency

and effectively complete the localization and classification of steel surface defects in shipbuilding

thus meeting the industrial requirements for detection precision and real-time performance.

关键词

Keywords

references

GUPAT M,KBAN M A,BUTOLA R,et al. Advances in applications of non-destructive testing (NDT): a review[J]. Advances in Materials and Processing Technologies,2022,8:2286-2307.

REN S Q, HE K M, GIRSHICK R,et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. Advances in Neural Information Processing Systems,2015,28.

WANG C Y,YE Y H,LIAO H P. YOLOv9:learning what you want to learn using programmable gradient information[C]∥Proceedings of European Conference on Computer Vision. Milan,Italy:Springer, 2024:1-21.

VARGHESE R,SAMBATH M. YOLOv8:a novel object detection algorithm with enhanced performance and robustness[C]∥Proceedings of 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems. Chennai, India:IEEE,2024:1-6.

惠康华,杨卫,刘浩翰,等.基于YOLOv5的增强多尺度目标检测方法[J].兵工学报,2023,44(9):2600-2610.

HUI K H,YANG W,LIU H H,et al. Enhanced multiscale object detection method based on YOLOv5[J]. Acta Armamentarii, 2023,44(9):2600-2610. (in Chinese)

LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]∥Proceedings of the Computer Vision ECCV 2016: 14th European Conference. Amsterdam, The Netherlands:Springer,2016,9905:21-37.

张博尧,冷雁冰.基于YOLOv4网络模型的金属表面划痕检测[J].兵工学报,2022,43(增刊1):214-221.

ZHANG B Y,LENG Y B. Metal surface scratch detection based on YOLOv4 network model[J]. Acta Armamentarii,2022,43(S1):214-221. (in Chinese)

WANG L,LIU X B,MA J T,et al. Real-time steel surface defect detection with improved multi-scale YOLO-v5[J]. Processes, 2023,11(5):1357.

LIU R Q, HUANG M, GAO Z M, et al. MSC-DNet: an efficient detector with multi-scale context for defect detection on strip steel surface[J]. Measurement,2023,209:112467.

YANG S X, XIE Y, WU J Q, et al. CFE-YOLOv8s: improved YOLOv8s for steel surface defect detection[J]. Electronics, 2024,13(14):2771.

BOCHKOVSKIY A,WANG C Y,LIAO H Y M. YOLOv4:optimal speed and accuracy of object detection[J]. Journal of Computer Vision and Pattern Recognition,2020,15(3):123-135.

XU J,LI Z S,DU B W,et al. Reluplex made more practical:leaky ReLU[C]∥Proceedings of the 2020 IEEE Symposium on Computers and Communications. Rennes, France: IEEE, 2020:1-7.

MA N, SU Y X, YANG L X, et al. Wheat seed detection and counting method based on improved YOLOv8 model[J]. Sensors, 2024,24:1654.

LIU X Y,PENG H W,ZHENG N X,et al. EfficientViT:memory efficient vision transformer with cascaded group attention[C]∥Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver, BC, Canada: IEEE, 2023:14420-14430.

WU Y T,LIAO T J,CHEN F,et al. Overhead power line damage detection:an innovative approach using enhanced YOLOv8[J]. Electronics,2024,13(4):739.

LIU G H,CHU M X,GONG R F,et al. Global attention module and cascade fusion network for steel surface defect detection[J]. Pattern Recognition,2025,158:110979.

LI H L,LI J,WEI H,et al. Slim-neck by GSConv:a lightweight design for real-time detector architectures[J]. Journal of Real-Time Image Processing,2024,21:62.

GAO Y,LV G,XIAO D,et al. Research on steel surface defect classification method based on deep learning[J]. Scientific Reports,2024,14:8254.

LV X M, DUAN F J, JIANG J J, et al. Deep metallic surface defect detection:the new benchmark and detection network[J]. Sensors (Basel),2020,20(6):1562.

龙阳,肖小玲.改进YOLOv8的金属表面缺陷检测模型[J].制造技术与机床,2024 (8):105-112.

LONG Y, XIAO X L. Improved YOLOv8 metal surface defect detection model[J]. Manufacturing Technology and Machine Tools,2024(8):105-112. (in Chinese)

JIANG X,CUI Y H,CUI Y C, et al. Optimization algorithm of steel surface defect detection based on YOLOv8n-SDEC[J]. IEEE Access,2024,12:95106-95117.

ZHANG T, PAN P F, ZHANG J, et al. Steel surface defect detection algorithm based on improved YOLOv8n[J]. Applied Sciences,2024,14:5325.

LI C F,XU A,ZHANG Q B,et al. Steel surface defect detection method based on improved YOLOX[J]. IEEE Access,2024,12:37643-37652.

LI X, ZHAO Y Z, JIAO X K, et al. PEYOLO a perception efficient network for multiscale surface defects detection[J]. Scientific Reports,2025,15:28804.

TIAN R S,JIA M P. DCC-CenterNet:a rapid detection method for steel surface defects[J]. Measurement,2022,187:110211.

浏览量

下载量

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据