Information Extraction Method of Part Machining Features Based on Image Deep Learning

doi:10.3969/j.issn.1004-132X.2022.03.011

Abstract

Abstract: Aiming at the information integration problems for machining features of various part models based on model definition（MBD）， a holographic information extraction method of machining features was proposed based on multi-level extraction architecture. Through the analysis of structural characteristics of parts， the machining features were classified with the simplest features that had manufacturing semantics and could not be split. Based on elaborating the extraction strategy， a machining feature classifier was built by deep learning image recognition technology. Based on the characteristics of MBD model information annotation， the machining feature topology structure was quickly located and extracted. A multi-view capture dimensionality reduction method was used to make the machining feature color image. And then a comprehensive analysis method for multi-angle image recognition of machining features was designed. Based on the query views， the annotation information of the MBD models was filtered， and a double-layer filtering extraction method for machining feature geometric information was constructed. Finally， a holographic information extraction software for machining features was established， and experimental results of key parts of marine diesel engines show the effectiveness of the method.

Key words: , holographic information, deep learning, image processing, feature recognition, filter extraction

摘要： 针对各类基于模型定义（MBD）的零件模型加工特征的信息集成问题，提出一种多层次提取架构的加工特征全息信息提取方法。通过对零件的结构特点进行分析，以具有制造语义且无法拆分的最简化特征实现加工特征的分类；在阐述提取策略的基础上，构建了基于深度学习图像识别技术的加工特征分类器；依据MBD模型信息标注的特点快速定位、抽取加工特征的拓扑结构，并利用多角度捕捉降维方法将加工特征彩色图像化，在此基础上设计了加工特征多角度图像识别综合分析方法；基于查询视图对MBD模型的标注信息进行过滤，构建了加工特征几何信息双层过滤式提取方法。最后开发了加工特征全息信息提取软件，并以船用柴油机关键件为实例验证了该方法的有效性。

关键词: 全息信息, 深度学习, 图像化处理, 特征识别, 过滤式提取

CLC Number:

TP391

ZHANG Shengwen, ZHOU Xi, LI Bincheng, CHENG Dejun, CHEN Wendi. Information Extraction Method of Part Machining Features Based on Image Deep Learning[J]. China Mechanical Engineering, 2022, 33(03): 348-355.

张胜文, 周曦, 李滨城, , 程德俊, , 陈文笛. 基于图像深度学习的零件加工特征信息提取方法[J]. 中国机械工程, 2022, 33(03): 348-355.

References

［1］高曙明. 自动特征识别技术综述［J］. 计算机学报， 1998， 21（3）：281-288.
GAO Shuming. A Survey of Automatic Feature Recognition［J］. Chinese Journal of Computers， 1998， 21（3）：281-288.
［2］MOKHTAR A， XU X， LAZCANOTEGUI I. Dealing with Feature Interactions for Prismatic Parts in STEP-NC［J］. Journal of Intelligent Manufacturing， 2009， 20（4）：431-445.
［3］LOCKETT H L， GUENOV M D. Graph-based Feature Recognition for Injection Moulding Based on a Mid-surface Approach［J］. Computer-Aided Design， 2005， 37（2）：251-262.
［4］BABIC B， NESIC N， MILJKOVIC Z. A Review of Automated Feature Recognition with Rule-based Pattern Recognition［J］. Computers in Industry， 2008， 59（4）：321-337.
［5］ABOUELNASR E S， KAMRANI A K. A New Methodology for Extracting Manufacturing Features from CAD System［J］. Computers & Industrial Engineering， 2006， 51（3）：389-415.
［6］RAHMANI K， AREZOO B. A Hybrid Hint-based and Graph-based Framework for Recognition of Interacting Milling Features［J］. Computers in Industry， 2007， 58（4）：304-312.
［7］成彬，任振华. 基于AAG扩展及痕迹法的相交特征识别［J］. 图学学报， 2017， 38（4）：469-475.
CHENG Bin， REN Zhenhua. Interacting Feature Recognition Based on AAG Expansion and Hint［J］. Journal of Graphics， 2017， 38（4）：469-475.
［8］郭付龙，孙根正，周竞涛. 基于图二次分解的加工特征识别算法［J］. 机械设计制与制造， 2013（5）：56-59.
GUO Fulong， SUN Genzheng， ZHOU Jingtao. Machining Feature Recognition Based on Graph Twice Decomposition［J］. Machinery Design & Manufacture， 2013（5）：56-59.
［9］田富君，田锡天，耿俊浩，等. 基于轻量化模型的加工特征识别技术［J］. 中国机械工程， 2010， 21（18）：2212-2217.
TIAN Fujun， TIAN Xitian， GENG Junhao， et al. Machining Feature Recognition Based on Lightweight Model［J］. China Mechanical Engineering， 2010， 21（18）：2212-2217.
［10］刘雪梅，贾勇琪，陈祖瑞，等. 缸体类零件加工特征识别方法［J］. 计算机集成制造统， 2016， 22（5）：1197-1204.
LIU Xuemei， JIA Yongqi， CHEN Zurui， et al. Recognition of Machining Feature for Engine Cylinder Blocks［J］. Computer Integrated Manufacturing Systems， 2016， 22（5）：1197-1204.
［11］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， 40（7）：422687.
ZHANG Yu， DONG Xiaoye， LI Dongsheng， et al. Method for STEP-NC Manufacturing Feature Recognition Based on STEP and Improved Network［J］. Acta Aeronautica et Astronautica Sinica， 2019， 40（7）：422687.
［12］WANG Q， YU X. Ontology Based Automatic Feature Recognition Framework［J］. Computers in Industry， 2014， 65（7）：1041-1052.
［13］刘晓军，倪中华，程亚龙，等. 面向版腔类零件机加工艺的加工特征识别方法［J］. 计算机集成制造系统， 2013， 19（12）：3130-3138.
LIU Xiaojun， NI Zhonghua， CHENG Yalong， et al. Machining Feature Recognition Method for Machining Process Facing Plate Parts［J］. Computer Integrated Manufacturing Systems， 2013， 19（12）：3130-3138.
［14］VANDENBRANDE J H， REQUICHA A A G. Spatial Reasoning for the Automatic Recognition of Machinable Features in Solid Model［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 1993， 15（12）：1269-1285.
［15］SUNIL V B， AGARWAL R， PANDE S S. An Approach to Recognize Interacting Features from B-Rep CAD Models of Prismatic Machined Parts Using a Hybrid（Graph and Rule Based）Technique［J］. Computers in Industry， 2010， 61（7）：686-701.
［16］魏涛，张丹，左敦稳，等. 面向薄壁多腔类结构件加工特征识别方法［J］. 计算机集成制造系统， 2017， 23（12）：2683-2691.
WEI Tao， ZHANG Dan， ZUO Dunwen， et al. Machining Feature Recognition Method for Thin-walled and Multi-cavity Structural Parts［J］. Computer Integrated Manufacturing Systems， 2017， 23（12）：2683-2691.
［17］WOO Y， SAKURAI H. Recognition of Maximal Features by Volume Decomposition［J］. Computer-Aided Design， 2002， 34（3）：195-207.
［18］ZHANG Z， JAISWAL P， RAI R. FeatureNet：Machining Feature Recognition Based on 3D Convolution Neural Network［J］. Computer-Aided Design， 2018， 101（3）：12-22.

[1]	REN Zongjin, LI Yang, XU Tianguo, LYU Jiangshan, HONG Ji. Research on Multi-point Measurement of Pneumatic Multi-dimensional Forces under Combined Support Mode [J]. China Mechanical Engineering, 2022, 33(02): 170-175,186.
[2]	TIAN Mingrui, , YANG Hao, HU Yongbiao. Large-field and High-precision Dynamic Positioning Method of Indoor Mobile Robots [J]. China Mechanical Engineering, 2022, 33(02): 194-201.
[3]	SHI Mingjie, CHENG Ming, ZHANG Shihong, VLADIMIR Petrenko, GRAZHINA Valerievna Kozhevnikova. Research on Flat CWR Mill for Precision-forming of Hard-to-deform Materials [J]. China Mechanical Engineering, 2022, 33(02): 209-216.
[4]	TANG Kun, SHU Yong, LI Dianyu, KONG Minghui, LUO Hong, YU Jianwu, ZHANG Mingjun, MAO Cong. Precision GHP Mold Manufacturing for Dual Aspherical Chalcogenide GlassLens with Small Aperture [J]. China Mechanical Engineering, 2022, 33(02): 217-225.
[5]	LI Huan, HUANG Chaowang, ZHOU Kang, ZHANG Changxin, ZENG Caiyou. Numerical Simulation and Experimental Verification of High-power Ultrasonic Welding of Al/Steel Joints [J]. China Mechanical Engineering, 2022, 33(02): 226-233.
[6]	LI Song, YANG Xinle, LI Weikang, TANG Meiling. Influence Laws of Blade Gradient Angle on Natural Frequency of Compressor Impellers [J]. China Mechanical Engineering, 2022, 33(02): 243-251.
[7]	YAN Sheng, ZHANG Runfeng, YANG Shaoqiong, , NIU Wendong, ZHANG Yuhang, LI Baoyu, . Modelling and Control Optimization for Underwater Gliders of Variable Buoyancy Processes in Vertical Plane [J]. China Mechanical Engineering, 2022, 33(01): 109-117.
[8]	ZHOU Feng, ZHENG Lixia, SHEN Yechao, JIN Bo. Ultra-thin Diamond Wire Tension Control System Based on Adaptive Backstepping [J]. China Mechanical Engineering, 2021, 32(24): 2995-3000，3007.
[9]	HOU Xiang, LIU Yixin, ZHONG Mengjie, LIN Sai, LIU Yang, LUO Ronghuang, LUO Xuetao, ZHANG Sa, . Research on Dry Etching Processes on PSSs [J]. China Mechanical Engineering, 2021, 32(24): 3001-3007.
[10]	CHEN Ni, WEI Jiawei, ZHANG Xinlei, LI Liang, HE Ning. Research on Machinability of Laser Modified AlN Substrates [J]. China Mechanical Engineering, 2021, 32(23): 2817-2882.
[11]	YAN Jieqiong, ZHOU Laishui, HU Shaoqian, WEN Siyang. Feature-preserving Denoising Method for Aero-engine Profile Point Cloud [J]. China Mechanical Engineering, 2021, 32(23): 2850-2860，2889.
[12]	CUI Haihua, XU Zhenlong, YANG Yapeng, MENG Yayun, WANG Baojun. A Circular Target Stability Detection Method Based on Deep Learning Image Super-resolution [J]. China Mechanical Engineering, 2021, 32(23): 2861-2867.
[13]	JI Aihong, LIU Rongxing, CHEN Hui, SUN Ke. Kinematics Analysis and Teleoperation Technology of Multi-joint Continuum Robots [J]. China Mechanical Engineering, 2021, 32(23): 2883-2889.
[14]	WANG Kun, NI Xiaobo, LI Honggeng, HE Jiayang, HUANG Yuanyi, HOU Gaojie. Development of Booming Performance of Rear-drive Vehicles Based on Multi-body Dynamics Models [J]. China Mechanical Engineering, 2021, 32(22): 2765-2771.
[15]	ZHANG Jianxun, YAO Bin, DAI Yu, XIA Guangming, . A Review of Force Sensing Technology in Robot-assisted Laparoscopic Surgery [J]. China Mechanical Engineering, 2021, 32(21): 2521-2531.