锻压技术

基于卷积神经网络的三维沉孔特征识别及关键参数提取

英文标题：3D countersink hole feature recognition and key parameter extraction based on convolutional neural network

作者：沈大为向华庄新村赵震

单位：上海交通大学塑性成形技术与装备研究院上海交通大学模具CAD国家工程研究中心

分类号：TG386

出版年,卷(期):页码：2022,47(11):78-86

摘要：

精冲零件的工艺特征识别和关键参数提取是实现精冲工艺设计智能化的关键。针对典型精冲工艺特征——沉孔，构建了一个以三维CAD模型为输入的特征识别和参数提取模型。利用改进的自适应体素化算法，将基于参数驱动批量生成的沉孔CAD模型转化为体素化模型，建立模型样本数据集；采用两步法，分别以工艺特征体素化模型为输入建立基于三维卷积神经网络的沉孔特征识别模型和以沉孔中心截面图像为输入建立基于二维卷积神经网络的参数提取模型，依次实现了3类主要沉孔特征的分类识别和参数提取。经过验证和评估，所建模型对于沉孔特征类型识别与关键参数提取均有较高的准确率，可以为精冲工艺的智能化工艺设计提供有力支撑。

Process feature recognition and key parameter extraction of fine blanking parts are the key point to realize intelligent process design for fine blanking. Therefore, for the typical fine blanking feature of countersink hole, a model for feature recognition and parameter extraction was constructed with 3D CAD model as input. Then, using the improved adaptive voxelization algorithm, the CAD model of countersink hole generated in batches based on parameter-driven was converted into a voxelized model, and a data set of model sample was established. Furthermore, the two-step method was used by using the voxelization model of process features as input to establish a countersink hole feature recognition model based on 3D convolutional neural network and using the center cross-section image of countersink hole as input to establish a parameter extraction model based on 2D convolutional neural network, respectively, and the classification recognition and parameter extraction for three main types of countersink hole features were realized in turn. The results show that after verification and evaluation, the established model has high accuracy for the recognition of countersink hole feature types and the extraction of key parameters, which can provide strong support for the intelligent process design of fine blanking process.

基金项目：

国家自然科学基金资助项目(51875351)

作者简介：沈大为（1998-），男，硕士研究生，E-mail：shdw0120@sjtu.edu.cn；通信作者：赵震（1972-），男，博士，教授，E-mail：zzhao@sjtu.edu.cn

参考文献：

[1]涂光祺. 精冲技术[M]. 北京：机械工业出版社，2005.

Tu G Q. Fineblanking Technology[M]. Beijing: China Machine Press,2005.

[2]杨泽亚, 杜贵江, 李佳盈, 等. 精冲技术研究现状及发展趋势[J].锻造与冲压, 2020,(16):16,18-20.

Yang Z Y, Du G J, Li J Y, et al. Status and development trend of research on fineblanking technology[J]. Forging & Metalforming, 2020,(16):16,18-20.

[3]Zheng Q D, Zhuang X C, Zhao Z. State-of-the-art and future challenge in fine-blanking technology[J]. Production Engineering, 2019, 13(1): 61-70.

[4]Wang Y L, Long H C. A feature-based process planning approach for fineblanking-forming-stamping parts[J]. Advanced Materials Research, 2011, 308-310: 816-819.

[5]曾顺, 张璐, 周雄辉. 箱体类零件的特征识别和CAD/CAPP集成[J].模具技术, 2013，(4):12-16.

Zeng S，Zhang L，Zhou X H. Feature recognition for box-type parts and CAD/CAPP integration[J]. Die & Mould Technology，2013，(4):12-16.

[6]吕祝星，宋燕利，兰箭，等. 基于STL三角网格的汽车覆盖件特征识别方法[J].塑性工程学报，2017，24 (4): 124-132.

Lyu Z X，Song Y L，Lan J，et al. Feature recognition applied to automobile panels based on STL triangular mesh[J].Journal of Plasticity Engineering，2017，24 (4): 124-132.

[7]李正旭，章志兵，张勋，等.基于成形过程的钣金特征识别与工序排配[J].精密成形工程，2020，12(2)：31-36.

Li Z X，Zhang Z B，Zhang X，et al. Sheet metal feature recognition and process arrangement based on forming process[J]. Journal of Netshape Forming Engineering，2020，12(2)：31-36.

[8]张禹，董小野，李东升，等. 基于STEP和改进神经网络的STEP-NC制造特征识别方法[J].航空学报，2019，60（7）：422687.

Zhang Y，Dong X Y，Li D S，et al. Method for STEP-NC manufacturing feature recognition based on STEP and improved neural network[J]. Acta Aeronautica et Astronautica Sinica，2019，60（7）：422687.

[9]Zhang Z B, Jaiswal P, Rai R. FeatureNet: Machining feature recognition based on 3D convolution neural network[J]. Computer-Aided Design, 2018,101:12-22.

[10]张航，张树生，杨磊. 基于深度学习的孔特征可制造性分析方法[J].图学学报，2021，42(1)：117-123.

Zhang H，Zhang S S，Yang L. Deep learning based manufacturability analysis approach for hole features[J]. Journal of Graphics，2021，42(1)：117-123.

[11]Schmidt R A, Birzer F, Hofel P, et al. Cold Forming and Fineblanking, a Handbook on Cold Processing, Steel Material Properties, Part Design[M]. Munchen: Carl Hanser Verlag, 2007.

[12]周开华. 简明精冲手册[M]. 2版.北京：国防工业出版社, 1993.

Zhou K H. Fine Blanking Handbook[M].2nd Edition. Beijing: National Defense Industry Press，1993.

服务与反馈：

【本网站尚未开通全文下载服务】【加入收藏】