Copper Nodule Defect Detection in Industrial Processes Using Deep Learning

Copper electrolysis is a crucial process in copper smelting. The surface of cathodic copper plates is often affected by various electrolytic process factors, resulting in the formation of nodule defects that significantly impact surface quality and disrupt the downstream production process, making t...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhicong Zhang, Xiaodong Huang, Dandan Wei, Qiqi Chang, Jinping Liu, Qingxiu Jing
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Information
Subjects:
Online Access:https://www.mdpi.com/2078-2489/15/12/802
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846104274037112832
author Zhicong Zhang
Xiaodong Huang
Dandan Wei
Qiqi Chang
Jinping Liu
Qingxiu Jing
author_facet Zhicong Zhang
Xiaodong Huang
Dandan Wei
Qiqi Chang
Jinping Liu
Qingxiu Jing
author_sort Zhicong Zhang
collection DOAJ
description Copper electrolysis is a crucial process in copper smelting. The surface of cathodic copper plates is often affected by various electrolytic process factors, resulting in the formation of nodule defects that significantly impact surface quality and disrupt the downstream production process, making the prompt detection of these defects essential. At present, the detection of cathode copper plate nodules is performed by manual identification. In order to address the issues with manual convex nodule identification on the surface of industrial cathode copper plates in terms of low accuracy, high effort, and low efficiency in the manufacturing process, a lightweight YOLOv5 model combined with the BiFormer attention mechanism is proposed in this paper. The model employs MobileNetV3, a lightweight feature extraction network, as its backbone, reducing the parameter count and computational complexity. Additionally, an attention mechanism is introduced to capture multi-scale information, thereby enhancing the accuracy of nodule recognition. Meanwhile, the F-EIOU loss function is employed to strengthen the model’s robustness and generalization ability, effectively addressing noise and imbalance issues in the data. Experimental results demonstrate that the improved YOLOv5 model achieves a precision of 92.71%, a recall of 91.24%, and a mean average precision (mAP) of 92.69%. Moreover, a single-frame detection time of 4.61 ms is achieved by the model, which has a size of 2.91 MB. These metrics meet the requirements of practical production and provide valuable insights for the detection of cathodic copper plate surface quality issues in the copper electrolysis production process.
format Article
id doaj-art-35371a0b6940480591395fa74fdc528f
institution Kabale University
issn 2078-2489
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Information
spelling doaj-art-35371a0b6940480591395fa74fdc528f2024-12-27T14:30:51ZengMDPI AGInformation2078-24892024-12-01151280210.3390/info15120802Copper Nodule Defect Detection in Industrial Processes Using Deep LearningZhicong Zhang0Xiaodong Huang1Dandan Wei2Qiqi Chang3Jinping Liu4Qingxiu Jing5Faculty of Materials Metallurgy and Chemistry, Jiangxi University of Science and Technology, Ganzhou 341000, ChinaSchool of Economics and Management, Jiangxi University of Science and Technology, Ganzhou 341000, ChinaFaculty of Materials Metallurgy and Chemistry, Jiangxi University of Science and Technology, Ganzhou 341000, ChinaFaculty of Materials Metallurgy and Chemistry, Jiangxi University of Science and Technology, Ganzhou 341000, ChinaFaculty of Materials Metallurgy and Chemistry, Jiangxi University of Science and Technology, Ganzhou 341000, ChinaFaculty of Materials Metallurgy and Chemistry, Jiangxi University of Science and Technology, Ganzhou 341000, ChinaCopper electrolysis is a crucial process in copper smelting. The surface of cathodic copper plates is often affected by various electrolytic process factors, resulting in the formation of nodule defects that significantly impact surface quality and disrupt the downstream production process, making the prompt detection of these defects essential. At present, the detection of cathode copper plate nodules is performed by manual identification. In order to address the issues with manual convex nodule identification on the surface of industrial cathode copper plates in terms of low accuracy, high effort, and low efficiency in the manufacturing process, a lightweight YOLOv5 model combined with the BiFormer attention mechanism is proposed in this paper. The model employs MobileNetV3, a lightweight feature extraction network, as its backbone, reducing the parameter count and computational complexity. Additionally, an attention mechanism is introduced to capture multi-scale information, thereby enhancing the accuracy of nodule recognition. Meanwhile, the F-EIOU loss function is employed to strengthen the model’s robustness and generalization ability, effectively addressing noise and imbalance issues in the data. Experimental results demonstrate that the improved YOLOv5 model achieves a precision of 92.71%, a recall of 91.24%, and a mean average precision (mAP) of 92.69%. Moreover, a single-frame detection time of 4.61 ms is achieved by the model, which has a size of 2.91 MB. These metrics meet the requirements of practical production and provide valuable insights for the detection of cathodic copper plate surface quality issues in the copper electrolysis production process.https://www.mdpi.com/2078-2489/15/12/802electrolytic cathodic copper plateYOLOv5attention mechanismdeep learningmobilenetv3object detection
spellingShingle Zhicong Zhang
Xiaodong Huang
Dandan Wei
Qiqi Chang
Jinping Liu
Qingxiu Jing
Copper Nodule Defect Detection in Industrial Processes Using Deep Learning
Information
electrolytic cathodic copper plate
YOLOv5
attention mechanism
deep learning
mobilenetv3
object detection
title Copper Nodule Defect Detection in Industrial Processes Using Deep Learning
title_full Copper Nodule Defect Detection in Industrial Processes Using Deep Learning
title_fullStr Copper Nodule Defect Detection in Industrial Processes Using Deep Learning
title_full_unstemmed Copper Nodule Defect Detection in Industrial Processes Using Deep Learning
title_short Copper Nodule Defect Detection in Industrial Processes Using Deep Learning
title_sort copper nodule defect detection in industrial processes using deep learning
topic electrolytic cathodic copper plate
YOLOv5
attention mechanism
deep learning
mobilenetv3
object detection
url https://www.mdpi.com/2078-2489/15/12/802
work_keys_str_mv AT zhicongzhang coppernoduledefectdetectioninindustrialprocessesusingdeeplearning
AT xiaodonghuang coppernoduledefectdetectioninindustrialprocessesusingdeeplearning
AT dandanwei coppernoduledefectdetectioninindustrialprocessesusingdeeplearning
AT qiqichang coppernoduledefectdetectioninindustrialprocessesusingdeeplearning
AT jinpingliu coppernoduledefectdetectioninindustrialprocessesusingdeeplearning
AT qingxiujing coppernoduledefectdetectioninindustrialprocessesusingdeeplearning