1.哈尔滨理工大学 自动化学院,黑龙江 哈尔滨 150080
2.哈尔滨工业大学 机电学院,黑龙江 哈尔滨 150080
[ "于智龙(1979-),男,黑龙江哈尔滨人,博士,副教授,硕士生导师,2002年于深圳大学获得学士学位,2007年于哈尔滨理工大学获得硕士学位,2013年于东北林业大学获得博士学位,主要研究方向为输配电系统的状态检测、人工智能、机器学习。E-mail:zlyu@hrbust.edu.cn" ]
[ "张雪寒(1999-),女,黑龙江哈尔滨人,硕士研究生,2021年于哈尔滨理工大学获得学士学位,主要从事工件分类、图像处理的研究。E-mail:Zxh990802@163.com" ]
收稿:2025-04-13,
修回:2025-06-18,
纸质出版:2025-10-10
移动端阅览
于智龙,张雪寒,齐丽华等.基于SDFSN-HiFuse网络的减速器工件分类[J].光学精密工程,2025,33(19):3093-3105.
YU Zhilong,ZHANG Xuehan,QI Lihua,et al.Reducer workpiece classification based on SDFSN-HiFuse network[J].Optics and Precision Engineering,2025,33(19):3093-3105.
于智龙,张雪寒,齐丽华等.基于SDFSN-HiFuse网络的减速器工件分类[J].光学精密工程,2025,33(19):3093-3105. DOI: 10.37188/OPE.20253319.3093. CSTR: 32169.14.OPE.20253319.3093.
YU Zhilong,ZHANG Xuehan,QI Lihua,et al.Reducer workpiece classification based on SDFSN-HiFuse network[J].Optics and Precision Engineering,2025,33(19):3093-3105. DOI: 10.37188/OPE.20253319.3093. CSTR: 32169.14.OPE.20253319.3093.
减速器相似工件的准确分类对于其精密装配至关重要。现有视觉分类方法在面对高度相似的工件时存在特征判别性不足、抗复杂背景干扰能力弱等问题,性能表现不佳,在精密装配中容易引入误差。针对减速器工件类内差异大、类间差异小的特点,提出一种基于HiFuse的空域双焦协同网络(Spatial Dual-Focus Synergy Network,SDFSN)减速器工件分类方法。设计多分支空间自适应的膨胀率选择机制,使模型对形变区域自动选择最合适的感受野。构思双阶段几何-局部协同注意力机制,对每个膨胀分支的输出特征施加逐级精细的注意力引导,动态调整特征权重,有效增强模型对重要区域的判别能力,实现由粗到细的特征提取。引入可变形几何图,实现与几何拓扑适配的图结构,突破传统固定网格限制,在可变形卷积后引入曲率门控机制,继承几何形变的适应性特征,显著提升对复杂曲面区域的响应能力与表达精度。实验结果表明,SDFSN-HiFuse在自制数据集上的准确率比基线提高3.57%,精确度提高2.99%,而且满足工件分类的实时性要求,FPS达到300.39 frame/ms。
Accurate classification of visually similar reducer parts is essential for precise assembly. Existing visual classification methods struggle with highly similar parts due to limited discriminative features and low robustness to complex background interference, which can introduce errors in assembly. To address these challenges, a HiFuse-based Spatial Dual-Focus Synergy Network (SDFSN-HiFuse) is proposed for classification of reducer workpieces, targeting scenarios with large intra-class variance and small inter-class variance. A multi-branch spatially adaptive dilation-rate selection mechanism is introduced to enable automatic determination of appropriate receptive fields for deformed regions of workpieces. A two-stage geometric–local collaborative attention mechanism provides stepwise fine-grained guidance to features from each dilation branch, dynamically reweighting features and enhancing discrimination of salient regions via a coarse-to-fine refinement process. A deformable geometric graph is employed to model geometric topology flexibly, overcoming the constraints of traditional fixed grids. Following deformable convolution, a curvature gating mechanism preserves adaptive geometric deformation features, substantially improving responsiveness and representation accuracy on complex curved surfaces. On a custom dataset, SDFSN-HiFuse achieves a 3.57% absolute improvement in accuracy and a 2.99% increase in precision over the baseline, while meeting real-time requirements with a processing rate of 300.39 frame/s.
ZHANG J , LI C C , DENG C J , et al . Toward digital twins for intelligence manufacturing: Self-adaptive control in assisted equipment through multi-sensor fusion smart tool real-time machine condition monitoring [J]. Journal of Manufacturing Systems , 2025 , 82 : 301 - 318 . doi: 10.1016/j.jmsy.2025.06.020 http://dx.doi.org/10.1016/j.jmsy.2025.06.020
GAO P F , LI X S , YAN X G , et al . Digital twin-driven intelligent spinning technique for curved surface parts [J]. Journal of Industrial Information Integration , 2025 , 45 : 100848 . doi: 10.1016/j.jii.2025.100848 http://dx.doi.org/10.1016/j.jii.2025.100848
REAL C , TORRES Y . Effect of changes in the sequence of assembly operations on error rates: a case study from the car manufacturing industry [J]. IEEE Access , 2024 , 12 : 34644 - 34655 . doi: 10.1109/access.2024.3371980 http://dx.doi.org/10.1109/access.2024.3371980
BREIMAN L . Random forests [J]. Machine Learning , 2001 , 45 ( 1 ): 5 - 32 . doi: 10.1023/a:1010933404324 http://dx.doi.org/10.1023/a:1010933404324
CORTES C , VAPNIK V . Support-vector networks [J]. Machine Learning , 1995 , 20 ( 3 ): 273 - 297 . doi: 10.1007/bf00994018 http://dx.doi.org/10.1007/bf00994018
KRIZHEVSKY A , SUTSKEVER I , HINTON G E . ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM , 2017 , 60 ( 6 ): 84 - 90 . doi: 10.1145/3065386 http://dx.doi.org/10.1145/3065386
LECUN Y , BOTTOU L , BENGIO Y , et al . Gradient-based learning applied to document recognition [J]. Proceedings of the IEEE , 1998 , 86 ( 11 ): 2278 - 2324 . doi: 10.1109/5.726791 http://dx.doi.org/10.1109/5.726791
HE K M , ZHANG X Y , REN S Q , et al . Deep residual learning for image recognition [C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 27-30,2016 , Las Vegas, NV, USA. IEEE , 2016 : 770 - 778 . doi: 10.1109/cvpr.2016.90 http://dx.doi.org/10.1109/cvpr.2016.90
SZEGEDY C , LIU W , JIA Y Q , et al . Going deeper with convolutions [C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 7-12,2015 , Boston, MA, USA. IEEE , 2015 : 1 - 9 . doi: 10.1109/cvpr.2015.7298594 http://dx.doi.org/10.1109/cvpr.2015.7298594
HOWARD A G , ZHU M , CHEN B , et al . Mobilenets: efficient convolutional neural networks for mobile vision applications [J/OL]. arXiv , preprint arXiv: 1704 . 04861 , 2017 . https://arxiv.org/abs/1704.04861 https://arxiv.org/abs/1704.04861 .
ZOPH B , VASUDEVAN V , SHLENS J , et al . Learning transferable architectures for scalable image recognition [C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . 18-23,2018 , Salt Lake City, UT, USA . IEEE , 2018 : 8697 - 8710 . doi: 10.1109/cvpr.2018.00907 http://dx.doi.org/10.1109/cvpr.2018.00907
MOHAN C , SABER T , NALLATHAMBI P J . Recognition of industrial spare parts using an optimized convolutional neural network model [J]. Information , 2024 , 15 ( 12 ): 793 . doi: 10.3390/info15120793 http://dx.doi.org/10.3390/info15120793
LIU Y X , DUAN S H , SHEN Z P , et al . Grasp and inspection of mechanical parts based on visual image recognition technology [J]. Journal of Theory and Practice of Engineering Science , 2023 , 3 ( 12 ): 22 - 28 . doi : 10.53469/jtpes.2023.03(12).04 http://dx.doi.org/10.53469/jtpes.2023.03(12).04
王琳毅 , 白静 , 李彦梅 , 等 . 面向工业目标检测的密集控制阀零件数据集 [J]. 光学 精密工程 , 2024 , 32 ( 8 ): 1241 - 1251 . doi: 10.37188/ope.20243208.1241 http://dx.doi.org/10.37188/ope.20243208.1241
WANG L Y , BAI J , LI Y M , et al . Dense control valve parts dataset for industrial object detection [J]. Opt. Precision Eng. , 2024 , 32 ( 8 ): 1241 - 1251 . (in Chinese) . doi: 10.37188/ope.20243208.1241 http://dx.doi.org/10.37188/ope.20243208.1241
RAJAGOUNDER R . A machine vision system for inspecting mechanical parts [J]. Machine Graphics and Vision , 2025 , 34 ( 1 ): 75 - 86 . doi: 10.22630/mgv.2025.34.1.4 http://dx.doi.org/10.22630/mgv.2025.34.1.4
洪存存 , 王雪琨 , 于文文 , 等 . 基于改进双边滤波的皮革缺陷检测 [J]. 激光技术 , 2021 , 45 ( 3 ): 373 - 377 .
HONG C C , WANG X K , YU W W , et al . Leather defect detection based on improved bilateral filtering [J]. Laser Technology , 2021 , 45 ( 3 ): 373 - 377 . (in Chinese)
梁礼明 , 龙鹏威 , 卢宝贺 , 等 . 改进GBS-YOLOv7t的钢材表面缺陷检测 [J]. 光电工程 , 2024 , 51 ( 5 ): 240044 .
LIANG L M , LONG P W , LU B H , et al . Improvement of GBS-YOLOv7t for steel surface defect detection [J]. Opto-Electronic Engineering , 2024 , 51 ( 5 ): 240044 . (in Chinese)
盛彬 , 王晨升 . 基于深度学习的装配零部件识别与定位方法 [J]. 制造技术与机床 , 2024 ( 6 ): 44 - 51 .
SHENG B , WANG CH SH . An assembly part identification and localization method based on deep learning [J]. Manufacturing Technology & Machine Tool , 2024 ( 6 ): 44 - 51 . (in Chinese)
余永维 , 韩鑫 , 杜柳青 . 基于Inception-SSD算法的零件识别 [J]. 光学 精密工程 , 2020 , 28 ( 8 ): 1799 - 1809 .
YU Y W , HAN X , DU L Q . Target part recognition based inception-SSD algorithm [J]. Opt. Precision Eng. , 2020 , 28 ( 8 ): 1799 - 1809 . (in Chinese)
HUO X Z , SUN G , TIAN S W , et al . HiFuse: Hierarchical multi-scale feature fusion network for medical image classification [J]. Biomedical Signal Processing and Control , 2024 , 87 : 105534 . doi: 10.1016/j.bspc.2023.105534 http://dx.doi.org/10.1016/j.bspc.2023.105534
YU F , KOLTUN V . Multi-scale context aggregation by dilated convolutions [J/OL]. arXiv preprint arXiv : 1511 . 07122 , 2015 . https://arxiv.org/abs/1511.07122 https://arxiv.org/abs/1511.07122 .
LUONG M T , PHAM H , MANNING C D . Effective approaches to attention-based neural machine translation [J/OL]. arXiv preprint arXiv : 1508 . 04025 , 2015 . https://arxiv.org/abs/1508.04025 https://arxiv.org/abs/1508.04025 .
KRIZHEVSKY A , SUTSKEVER I , HINTON G E . ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM , 2017 , 60 ( 6 ): 84 - 90 . doi: 10.1145/3065386 http://dx.doi.org/10.1145/3065386
SANDLER M , HOWARD A , ZHU M L , et al . MobileNetV2: inverted residuals and linear bottlenecks [C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . 18-23,2018 , Salt Lake City, UT, USA . IEEE , 2018 : 4510 - 4520 . doi: 10.1109/cvpr.2018.00474 http://dx.doi.org/10.1109/cvpr.2018.00474
ZHANG X Y , ZHOU X Y , LIN M X , et al . ShuffleNet: an extremely efficient convolutional neural network for mobile devices [C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . 18-23,2018 , Salt Lake City, UT, USA . IEEE , 2018 : 6848 - 6856 . doi: 10.1109/cvpr.2018.00716 http://dx.doi.org/10.1109/cvpr.2018.00716
TAN M , LE Q . Efficientnetv2: smaller models and faster training [C]. International conference on machine learning. ICML , 2021 : 10096 - 10106 .
WOO S , DEBNATH S , HU R H , et al . ConvNeXt V2: co-designing and scaling ConvNets with masked autoencoders [C]. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 17-24,2023 , Vancouver, BC, Canada. IEEE , 2023 : 16133 - 16142 . doi: 10.1109/cvpr52729.2023.01548 http://dx.doi.org/10.1109/cvpr52729.2023.01548
LIU Z , LIN Y T , CAO Y , et al . Swin transformer: hierarchical vision transformer using shifted windows [C]. 2021 IEEE/CVF International Conference on Computer Vision (ICCV). 10-17,2021 , Montreal, QC, Canada. IEEE , 2021 : 9992 - 10002 . doi: 10.1109/iccv48922.2021.00986 http://dx.doi.org/10.1109/iccv48922.2021.00986
0
浏览量
3
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621
