Surface defect detection on rolling mill rolls: a transfer learning approach with improved YOLOv5

Abstract The roller is a crucial tool in the hot-rolled strip steel manufacturing process. Rapid and accurate detection of roll surface defects is essential for enhancing product surface quality, ensuring dimensional precision, and reducing scrap rates. Currently, industrial roll inspection primaril...

Full description

Saved in:
Bibliographic Details
Main Authors: Yulong Hu, Wen Peng, Shiyi Chen, Jinyun Liu, Xudong Li, Jie Sun, Dianhua Zhang
Format: Article
Language:English
Published: Springer 2025-06-01
Series:Discover Applied Sciences
Subjects:
Online Access:https://doi.org/10.1007/s42452-025-06920-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849329458661556224
author Yulong Hu
Wen Peng
Shiyi Chen
Jinyun Liu
Xudong Li
Jie Sun
Dianhua Zhang
author_facet Yulong Hu
Wen Peng
Shiyi Chen
Jinyun Liu
Xudong Li
Jie Sun
Dianhua Zhang
author_sort Yulong Hu
collection DOAJ
description Abstract The roller is a crucial tool in the hot-rolled strip steel manufacturing process. Rapid and accurate detection of roll surface defects is essential for enhancing product surface quality, ensuring dimensional precision, and reducing scrap rates. Currently, industrial roll inspection primarily relies on manual visual assessment, which is prone to subjectivity, low accuracy, and inefficiency. To overcome these limitations, this study introduces a defect detection method based on transfer learning and an enhanced YOLOv5 model.Given the lack of publicly available datasets for roll surface defects, a representative dataset was first constructed using defect images collected from a steel production line. To further optimize the detection model, the NEU-DET dataset—containing strip surface defect images—was employed to pre-train the improved YOLOv5 model, refining its parameters. The pre-trained model was then adapted for roll defect detection using transfer learning, where the learned parameters from strip surface defects served as initial weights for training on the roll defect dataset. Experimental results demonstrate that the proposed TR-CNF-YOLOv5 model, integrating transfer learning with an improved YOLOv5 architecture, outperforms existing models. Specifically, it achieves an mAP improvement of approximately 9.8% over the original YOLOv5 and 7.1% over YOLOv7 on the roll surface defect dataset.
format Article
id doaj-art-0e963bf6efea467f9936215c5c351d97
institution Kabale University
issn 3004-9261
language English
publishDate 2025-06-01
publisher Springer
record_format Article
series Discover Applied Sciences
spelling doaj-art-0e963bf6efea467f9936215c5c351d972025-08-20T03:47:16ZengSpringerDiscover Applied Sciences3004-92612025-06-017711410.1007/s42452-025-06920-7Surface defect detection on rolling mill rolls: a transfer learning approach with improved YOLOv5Yulong Hu0Wen Peng1Shiyi Chen2Jinyun Liu3Xudong Li4Jie Sun5Dianhua Zhang6State Key Laboratory of Digital Steel, Northeastern UniversityState Key Laboratory of Digital Steel, Northeastern UniversityZhongxing Telecom EquipmentCollege of Artificial Intelligence, North China University of Science and TechnologyResearch Institute of Technology Shougang Group Co. LtdState Key Laboratory of Digital Steel, Northeastern UniversityState Key Laboratory of Digital Steel, Northeastern UniversityAbstract The roller is a crucial tool in the hot-rolled strip steel manufacturing process. Rapid and accurate detection of roll surface defects is essential for enhancing product surface quality, ensuring dimensional precision, and reducing scrap rates. Currently, industrial roll inspection primarily relies on manual visual assessment, which is prone to subjectivity, low accuracy, and inefficiency. To overcome these limitations, this study introduces a defect detection method based on transfer learning and an enhanced YOLOv5 model.Given the lack of publicly available datasets for roll surface defects, a representative dataset was first constructed using defect images collected from a steel production line. To further optimize the detection model, the NEU-DET dataset—containing strip surface defect images—was employed to pre-train the improved YOLOv5 model, refining its parameters. The pre-trained model was then adapted for roll defect detection using transfer learning, where the learned parameters from strip surface defects served as initial weights for training on the roll defect dataset. Experimental results demonstrate that the proposed TR-CNF-YOLOv5 model, integrating transfer learning with an improved YOLOv5 architecture, outperforms existing models. Specifically, it achieves an mAP improvement of approximately 9.8% over the original YOLOv5 and 7.1% over YOLOv7 on the roll surface defect dataset.https://doi.org/10.1007/s42452-025-06920-7Steel industryObject detectionTransfer learningImage classification
spellingShingle Yulong Hu
Wen Peng
Shiyi Chen
Jinyun Liu
Xudong Li
Jie Sun
Dianhua Zhang
Surface defect detection on rolling mill rolls: a transfer learning approach with improved YOLOv5
Discover Applied Sciences
Steel industry
Object detection
Transfer learning
Image classification
title Surface defect detection on rolling mill rolls: a transfer learning approach with improved YOLOv5
title_full Surface defect detection on rolling mill rolls: a transfer learning approach with improved YOLOv5
title_fullStr Surface defect detection on rolling mill rolls: a transfer learning approach with improved YOLOv5
title_full_unstemmed Surface defect detection on rolling mill rolls: a transfer learning approach with improved YOLOv5
title_short Surface defect detection on rolling mill rolls: a transfer learning approach with improved YOLOv5
title_sort surface defect detection on rolling mill rolls a transfer learning approach with improved yolov5
topic Steel industry
Object detection
Transfer learning
Image classification
url https://doi.org/10.1007/s42452-025-06920-7
work_keys_str_mv AT yulonghu surfacedefectdetectiononrollingmillrollsatransferlearningapproachwithimprovedyolov5
AT wenpeng surfacedefectdetectiononrollingmillrollsatransferlearningapproachwithimprovedyolov5
AT shiyichen surfacedefectdetectiononrollingmillrollsatransferlearningapproachwithimprovedyolov5
AT jinyunliu surfacedefectdetectiononrollingmillrollsatransferlearningapproachwithimprovedyolov5
AT xudongli surfacedefectdetectiononrollingmillrollsatransferlearningapproachwithimprovedyolov5
AT jiesun surfacedefectdetectiononrollingmillrollsatransferlearningapproachwithimprovedyolov5
AT dianhuazhang surfacedefectdetectiononrollingmillrollsatransferlearningapproachwithimprovedyolov5