A Lightweight Deep Learning Network with an Optimized Attention Module for Aluminum Surface Defect Detection

Aluminum is extensively utilized in the aerospace, aviation, automotive, and other industries. The presence of surface defects on aluminum has a significant impact on product quality. However, traditional detection methods fail to meet the efficiency and accuracy requirements of industrial practices...

Full description

Saved in:
Bibliographic Details
Main Authors: Yizhe Li, Yidong Xie, Hu He
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/23/7691
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849220410648821760
author Yizhe Li
Yidong Xie
Hu He
author_facet Yizhe Li
Yidong Xie
Hu He
author_sort Yizhe Li
collection DOAJ
description Aluminum is extensively utilized in the aerospace, aviation, automotive, and other industries. The presence of surface defects on aluminum has a significant impact on product quality. However, traditional detection methods fail to meet the efficiency and accuracy requirements of industrial practices. In this study, we propose an innovative aluminum surface defect detection method based on an optimized two-stage Faster R-CNN network. A 2D camera serves as the image sensor, capturing high-resolution images in real time. Optimized lighting and focus ensure that defect features are clearly visible. After preprocessing, the images are fed into a deep learning network incorporated with a multi-scale feature pyramid structure, which effectively enhances defect recognition accuracy by integrating high-level semantic information with location details. Additionally, we introduced an optimized Convolutional Block Attention Module (CBAM) to further enhance network efficiency. Furthermore, we employed the genetic K-means algorithm to optimize prior region selection, and a lightweight Ghost model to reduce network complexity by 14.3%, demonstrating the superior performance of the Ghost model in terms of loss function optimization during training and validation as well as in terms of detection accuracy, speed, and stability. The network was trained on a dataset of 3200 images captured by the image sensor, split in an 8:1:1 ratio for training, validation, and testing, respectively. The experimental results show a mean Average Precision (mAP) of 94.25%, with individual Average Precision (AP) values exceeding 80%, meeting industrial standards for defect detection.
format Article
id doaj-art-e935c8e2261944149b244ce90ede39b3
institution Kabale University
issn 1424-8220
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-e935c8e2261944149b244ce90ede39b32024-12-13T16:32:27ZengMDPI AGSensors1424-82202024-11-012423769110.3390/s24237691A Lightweight Deep Learning Network with an Optimized Attention Module for Aluminum Surface Defect DetectionYizhe Li0Yidong Xie1Hu He2State Key Laboratory of Precision Manufacturing for Extreme Service Performance, College of Mechanical and Electrical Engineering, Central South University, Changsha 410083, ChinaState Key Laboratory of Precision Manufacturing for Extreme Service Performance, College of Mechanical and Electrical Engineering, Central South University, Changsha 410083, ChinaState Key Laboratory of Precision Manufacturing for Extreme Service Performance, College of Mechanical and Electrical Engineering, Central South University, Changsha 410083, ChinaAluminum is extensively utilized in the aerospace, aviation, automotive, and other industries. The presence of surface defects on aluminum has a significant impact on product quality. However, traditional detection methods fail to meet the efficiency and accuracy requirements of industrial practices. In this study, we propose an innovative aluminum surface defect detection method based on an optimized two-stage Faster R-CNN network. A 2D camera serves as the image sensor, capturing high-resolution images in real time. Optimized lighting and focus ensure that defect features are clearly visible. After preprocessing, the images are fed into a deep learning network incorporated with a multi-scale feature pyramid structure, which effectively enhances defect recognition accuracy by integrating high-level semantic information with location details. Additionally, we introduced an optimized Convolutional Block Attention Module (CBAM) to further enhance network efficiency. Furthermore, we employed the genetic K-means algorithm to optimize prior region selection, and a lightweight Ghost model to reduce network complexity by 14.3%, demonstrating the superior performance of the Ghost model in terms of loss function optimization during training and validation as well as in terms of detection accuracy, speed, and stability. The network was trained on a dataset of 3200 images captured by the image sensor, split in an 8:1:1 ratio for training, validation, and testing, respectively. The experimental results show a mean Average Precision (mAP) of 94.25%, with individual Average Precision (AP) values exceeding 80%, meeting industrial standards for defect detection.https://www.mdpi.com/1424-8220/24/23/7691image sensorsdeep learning networkdefect detection
spellingShingle Yizhe Li
Yidong Xie
Hu He
A Lightweight Deep Learning Network with an Optimized Attention Module for Aluminum Surface Defect Detection
Sensors
image sensors
deep learning network
defect detection
title A Lightweight Deep Learning Network with an Optimized Attention Module for Aluminum Surface Defect Detection
title_full A Lightweight Deep Learning Network with an Optimized Attention Module for Aluminum Surface Defect Detection
title_fullStr A Lightweight Deep Learning Network with an Optimized Attention Module for Aluminum Surface Defect Detection
title_full_unstemmed A Lightweight Deep Learning Network with an Optimized Attention Module for Aluminum Surface Defect Detection
title_short A Lightweight Deep Learning Network with an Optimized Attention Module for Aluminum Surface Defect Detection
title_sort lightweight deep learning network with an optimized attention module for aluminum surface defect detection
topic image sensors
deep learning network
defect detection
url https://www.mdpi.com/1424-8220/24/23/7691
work_keys_str_mv AT yizheli alightweightdeeplearningnetworkwithanoptimizedattentionmoduleforaluminumsurfacedefectdetection
AT yidongxie alightweightdeeplearningnetworkwithanoptimizedattentionmoduleforaluminumsurfacedefectdetection
AT huhe alightweightdeeplearningnetworkwithanoptimizedattentionmoduleforaluminumsurfacedefectdetection
AT yizheli lightweightdeeplearningnetworkwithanoptimizedattentionmoduleforaluminumsurfacedefectdetection
AT yidongxie lightweightdeeplearningnetworkwithanoptimizedattentionmoduleforaluminumsurfacedefectdetection
AT huhe lightweightdeeplearningnetworkwithanoptimizedattentionmoduleforaluminumsurfacedefectdetection