基于STEP和改进神经网络的STEP-NC制造特征识别方法

doi:10.7527/S1000-6893.2018.22687

材料工程与机械制造

本期目录 | 过刊浏览 | 高级检索

前一篇 | 后一篇

基于STEP和改进神经网络的STEP-NC制造特征识别方法

张禹^1,2, 董小野¹, 李东升¹, 曾奇峰¹, 杨树华², 巩亚东¹

1. 东北大学机械工程与自动化学院, 沈阳 110819;
2. 沈阳鼓风机集团股份有限公司, 沈阳 110869

收稿日期:2018-09-18 修回日期:2018-10-18 出版日期:2019-07-15 发布日期:2018-12-19
通讯作者: 张禹 E-mail:zy4097534@126.com
基金资助:
国家自然科学基金（51205054）；中国博士后科学基金（2017M611245）；中央高校基本科研业务费专项资金（N180313010，N160304009）；东北大学博士后基金

Method for STEP-NC manufacturing feature recognition based on STEP and improved neural network

ZHANG Yu^1,2, DONG Xiaoye¹, LI Dongsheng¹, ZENG Qifeng¹, YANG Shuhua², GONG Yadong¹

1. School of Mechanical Engineering and Automation, Northeastern University, Shenyang 110819, China;
2. Shenyang Blower Works Group Corporation, Shenyang 110869, China

Received:2018-09-18 Revised:2018-10-18 Online:2019-07-15 Published:2018-12-19
Supported by:
National Natural Science Foundation of China (51205054);China Postdoctoral Science Foundation(2017M611245); the Fundamental Research Funds for the Central Universities (N180313010, N160304009); Postdoctoral Fund of Northeastern University

摘要/Abstract

摘要： 特征识别是实施STEP-NC重要的一步，也是实现开放式、智能化和网络化STEP-NC数控系统的关键。本文提出了一种基于STEP和改进神经网络的STEP-NC制造特征识别方法。该方法首先在对STEP AP203中性文件进行几何拓扑信息提取后，基于边的凹凸性判断构建了零件最小子图。然后，将混沌算法、遗传算法与BP神经网络算法有机相结合提出了改进的BP神经网络。最后，通过将获得的零件模型最小子图信息数据输入到改进的BP神经网络，实现了对STEP-NC制造特征高效精准地识别。通过实例验证了该方法的有效性和可行性。

关键词: STEP-NC, 特征识别, STEP AP203文件, 最小子图, 改进BP神经网络

Abstract: Feature recognition is an important step to implement STEP-NC theory and a key to realize the open, intelligent and networked STEP-NC CNC system. A feature recognition method based on STEP and improved neural network for STEP-NC manufacturing features is presented in this paper. This method first extracts the geometric and topological information from the STEP AP203 file of a part, and builds the minimum subgraph of the part based on the judgment of the convexity of edges. Then, an improved BP neural network is proposed by combining the chaos algorithm, the genetic algorithm, and the BP neural network algorithm. Finally, by inputting the information data from the minimum subgraph of the part to the improved BP neural network, efficient and accurate feature recognition for STEP-NC manufacturing features in the part is achieved. The validity and feasibility of the proposed method are verified by two case studies.

Key words: STEP-NC, feature recognition, STEP AP203 file, minimum subgraph, improved (BP) neural network

中图分类号:

V26
TH166

张禹, 董小野, 李东升, 曾奇峰, 杨树华, 巩亚东. 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): 422687-422687.

ZHANG Yu, DONG Xiaoye, LI Dongsheng, ZENG Qifeng, YANG Shuhua, GONG Yadong. Method for STEP-NC manufacturing feature recognition based on STEP and improved neural network[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2019, 40(7): 422687-422687.

参考文献

[1] RAUCH M, LAGUIONIE R, HASCOET J Y, et al. An advanced STEP-NC controller for intelligent machining processes[J]. Robotics & Computer Integrated Manufacturing, 2012, 28(3):375-384.
[2] HARDWICK M, ZHAO Y F, PROCTOR F M, et al. A roadmap for STEP-NC-enabled interoperable manufacturing[J]. International Journal of Advanced Manufacturing Technology, 2013, 68(5-8):1023-1037.
[3] JOSHI S, CHANG T C. Graph-based heuristics for recognition of machined features from a 3D solid model[J]. Computer-Aided Design, 1988, 20(2):56-66.
[4] 韩娟, 张发平, 高博, 等. 基于图和规则的混合式特征识别技术[J]. 机械设计与制造, 2013(3):97-100. HAN J, ZHANG F P,GAO B, et al. The hybrid characteristics identification technology based on the diagram and rules[J]. Machinery Design & Manufacture, 2013(3):97-100(in Chinese).
[5] 谢飞,, 郭宇, 张红蕾, 等. 基于图和子图同构算法的制造特征识别方法[J]. 南京航空航天大学学报, 2018, 50(3):390-396. XIE F, GUO Y, ZHANG H L, et al. Manufacturing feature recognition based on graph and subgraph isomorphism algorithm[J]. Journal of Nanjing University of Aeronautics & Astronautics, 2018, 50(3):390-396(in Chinese).
[6] VANDENBRANDE J H, REQUICHA A A G. Spatial reasoning for the automatic recognition of machinable features in solid models[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 1993, 15(12):1269-1285.
[7] GAO S, SHAH J J. Automatic recognition of interacting machining features based on minimal condition subgraph[J]. Computer-Aided Design, 1998, 30(9):727-739.
[8] 赵鹏, 盛步云. 基于切削体分解组合策略的工艺特征识别方法[J]. 华南理工大学学报(自然科学版), 2011, 39(8):30-35. ZHAO P,SHENG B Y. Recognition method of process feature based on delta-volume decomposition and combination strategy[J]. Journal of South China University of Technology (Natural Science Edition), 2011, 39(8):30-35(in Chinese).
[9] 刘长青, 李迎光, 王鹏程, 等. 复杂结构件数控编程加工特征用户自定义方法[J]. 航空学报, 2017, 38(6):248-257. LIU C Q, LI Y G,WANG P C, et al. A user defined method for machining features in NC programming of complex structural parts[J]. Acta Aeronautica et Astronautica Sinica, 2017, 38(6):248-257(in Chinese).
[10] 吴晓东, 韩祖行. 基于属性邻接图的STEP-NC制造特征识别实现[J]. 机械设计与制造工程, 2013, 42(7):13-16. WU X D, HAN Z X. Implementation of STEP-NC manufacturing feature recognition based on attribute adjacent graph[J]. Machine Design & Manufacturing Engineering,2013, 42(7):13-16(in Chinese).
[11] 李梅竹, 陈荣. 基于痕迹对STEP文件进行特征识别的研究[J]. 陕西科技大学学报, 2011, 29(4):57-62. LI M Z, CHEN R. A study of feature recognition based on hint from STEP files[J]. Journal of Shaanxi University of Science and Technology, 2011, 29(4):57-62(in Chinese).
[12] 王军, 欧道江, 舒启林, 等. 基于STEP-NC的相交特征识别技术[J]. 计算机集成制造系统, 2014, 20(5):1051-1061. WANG J, OU D J, SHU Q L, et al. Interacting feature recognition technology based on STEP-NC[J]. Computer Integrated Manufacturing Systems, 2014, 20(5):1051-1061(in Chinese).
[13] 孙军, 王军, 王宛山, 等. 基于STEP-NC的制造特征识别方法研究[C]//孙铁珩, 汝信. 自主创新振兴东北高层论坛暨第二届沈阳科学学术年会论文集. 沈阳:沈阳出版社, 2005:222-228. SUN J,WANG J, WANG W S, et al. Research on manufacturing feature recognition method based on STEP-NC[C]//SUN T H, RU X. Independent Innovation and Revitalization of the Northeast High-level Forum and the 2nd Shenyang Science Academic Conference. Shenyang:Shenyang Press, 2005:222-228(in Chinese).
[14] POBOZ·NIAK J. Algorithm for ISO 14649(STEP-NC) feature recognition[J]. Management & Production Engineering Review, 2013, 4(4):50-58.
[15] ZHANG X, NASSEHI A, NEWMAN S T. Feature recognition from CNC part programs for milling operations[J]. International Journal of Advanced Manufacturing Technology, 2014, 70(1-4):397-412.
[16] ZHANG Y, XUN X, LIU Y X, et al. Service-oriented, cross-platform and high-level machining simulation[J]. International Journal of Computer Integrated Manufacturing, 2012, 25(3):280-295.
[17] INTERNATIONAL O F S. Industrial automation systems and integration-physical device control-data model for computerized numerical controllers-part 01:Overview and fundamental principles:ISO 14649-1[S]. Switzerland:International Organization for Standards, 2003.
[18] XU X W, WANG H, MAO J, et al. STEP-compliant NC research:the search for intelligent CAD/CAPP/CAM/CNC integration[J]. International Journal of Production Research, 2005, 43(17):3703-3743.
[19] DIPPER T, XU X, KLEMM P. Defining recognizing and representing feature interactions in a feature-based data model[J]. Robotics & Computer Integrated Manufacturing, 2011, 27(1):101-114.
[20] 陶建华, 杨晓琴,刘晓初,等. 基于工艺特征识别技术的数控自动编程方法研究[J]. 计算机工程与设计, 2011, 32(10):3548-3552. TAO J H, YANG X Q, LIU X C, et al. Research of NC automatic programming based on technological feature recognition[J]. Computer Engineering and Design, 2011, 32(10):3548-3552(in Chinese).
[21] LIU Y. An improved AHP and BP neural network method for service quality evaluation of city bus[J]. International Journal of Computer Applications in Technology, 2018, 58(1):37-44.
[22] 熊青春, 王家序, 周青华. 融合机床精度与工艺参数的铣削误差预测模型[J]. 航空学报, 2018, 39(8):421713. XIONG Q C, WANG J X, ZHOU Q H. Prediction model of machining errors based on precision and process parameters of machine tools[J]. Acta Aeronautica et Astronautica Sinica, 2018, 39(8):421713(in Chinese).
[23] LU H J, ZHANG H M, MA L H. A new optimization algorithm based on chaos[J]. Journal of Zhejiang University-Science A:Applied Physics & Engineering, 2006, 7(4):539-542.
[24] OKAMOTO T, HIRATA H. Global optimization using a multipoint type quasi-chaotic optimization method[J]. Applied Software Computing, 2013, 13(2):1247-1264.
[25] 赵燕. 基于遗传算法与评估模型的飞行载荷实测研究[J]. 航空学报, 2014, 35(9):2506-2512. ZHAO Y. Flight load measurement based on genetic algorithm and evaluating model[J]. Acta Aeronautica et Astronautica Sinica, 2014, 35(9):2506-2512(in Chinese).
[26] LI Y Q, WANG R X, LIU Y, et al. Satellite range scheduling with the priority constraint:An improved genetic algorithm using a station ID encoding method[J]. Chinese Journal of Aeronautics, 2015, 28(3):789-803.
[27] LI J, CHENG J H, SHI J Y, et al. Brief Introduction of back propagation (BP) neural network algorithm and its improvement[J]. Advances in Intelligent and Soft Computing, 2012, 169(2):553-558.
[28] 许同乐, 侯蒙蒙, 蔡道勇, 等. FastICA遗传神经网络算法[J]. 北京邮电大学学报, 2014, 37(4):25-28. XU T L,HOU M M,CAI D Y, et al. FastICA genetic neural networks method[J]. Journal of Beijing University of Posts and Telecommunications, 2014, 37(4):25-28(in Chinese).

E-mail：hkxb@buaa.edu.cn

关于我们

期刊社服务

专业学科

封面文章

友情链接

主管单位：中国科学技术协会主办单位：中国航空学会北京航空航天大学

基于STEP和改进神经网络的STEP-NC制造特征识别方法

Method for STEP-NC manufacturing feature recognition based on STEP and improved neural network

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	石叶楠, 郑国磊. 三种用于加工特征识别的神经网络方法综述[J]. 航空学报, 2019, 40(9): 22840-022840.
[2]	沈梅;何小朝;张铁昌. 设计特征模型中的装配特征识别[J]. 航空学报, 2000, 21(6): 567-570.
[3]	何小朝;沈梅;蒋谢明;张铁昌. 设计特征模型中的加工特征识别[J]. 航空学报, 1998, 19(6): 46-51.