摘要
机械零件自动分类识别算法,在智能工业、自动化加工等领域具有广阔地应用前景。针对汽车发动机主轴承盖零件自动分类时,存在特征多表面分布和光照敏感等难点问题,提出多分支特征融合卷积神经网络(MFF-CNN)。MFF-CNN具有2个子网络分支,分别提取主轴承盖2个表面的特征,经过特征融合,形成最终的零件分类特征。在网络结构设计上,MFF-CNN基于密集连接型卷积神经网络设计,通过增强网络层级间的特征重用,有效降低模型的参数量,缓解较小样本量条件下,深层网络的过拟合和梯度消失问题。实验结果表明,在实际采集的主轴承盖图像数据集上,MFF-CNN的识别率为91.6%,并对实际生产中的零件图像光照不均匀问题,具有良好的鲁棒性。
The automatic classification and recognition algorithm of mechanical parts has broad application prospects in the fields of intelligent industry and automatic processing.In the automatic classification of automobile engine main bearing cap parts,there are difficult problems such as multi-surface distribution of features and light sensitivity.A multi-branch feature fusion convolutional neural network(MFF-CNN)was designed.The two sub-network branches of the MFF-CNN can extract the features of the two surfaces of the main bearing cap respectively,and form the final part classification feature after feature fusion.In terms of network structure design,the MFF-CNN was based on a densely-connected convolutional neural network design.By enhancing the feature reuse between network layers,the parameter amount of the model was effectively reduced,and the problems of overfitting and gradient disappearance of deep networks can be alleviated under the condition of small sample size.The experimental results show that the MFF-CNN can attain the recognition rate of 91.6%on the image data set of the main bearing cap collected in practice,and it displays good robustness in terms of the problem of uneven illumination of the parts’images in actual production.
作者
张鹏飞
石志良
李晓垚
欧阳祥波
ZHANG Peng-fei;SHI Zhi-liang;LI Xiao-yao;OUYANG Xiang-bo(School of Mechanical and Electrical Engineering,Wuhan University of Technology,Wuhan Hubei 430070,China;School of Mechanical and Electrical Engineering,Guangdong University of Technology,Guangzhou Guangdong 510006,China)
出处
《图学学报》
CSCD
北大核心
2021年第4期572-580,共9页
Journal of Graphics
关键词
机械零件识别
卷积神经网络
细粒度图像分类
特征融合
mechanical part recognition
convolutional neural network
fine-grained image classification
feature fusion
作者简介
第一作者:张鹏飞(1993-),男,安徽合肥人,硕士研究生。主要研究方向为计算机视觉与图像识别。E-mail:zhangyingxiong@whut.edu.cn;通信作者:欧阳祥波(1973-),男,湖北荆州人,讲师,博士。主要研究方向为机器视觉。E-mail:oyxb@gdut.edu.cn。
