基于SDFSN-HiFuse网络的减速器工件分类

打开文本图片集

关键词：减速器工件分类；深度学习；注意力机制；多尺度膨胀卷积中图分类号：TP18；TH132.46 文献标识码：Adoi：10.37188/OPE.20253319.3093 CSTR：32169.14.OPE.20253319.3093

Abstract：Accurate classification of visually similar reducer parts is essential for precise assembly.Exist ing 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 smallinter-class variance.A multi-branch spatially adaptive dilation-rate selection mechanism is introduced to enable auto matic 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， SDFSNHiFuse 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 3OO.39 frame/s.

Key words： reducer workpiece classification； deep learning；attention mechanism；multi-scale dilated convolution

1引言

减速器工件是机械产品制造中的基础和关键组成部分，科学构建其多维分类体系直接影响生产线的传动效率与结构创新。（剩余14897字）