Please wait a minute...
浙江大学学报(工学版)
J4  2009, Vol. 43 Issue (5): 877-883    DOI: 10.3785/j.issn.1008-973X.2009.05.018
动力与机械工程     
基于形态分布图与BP神经网络的三维模型检索方法
徐敬华,张树有
（浙江大学 机械与能源工程学院,浙江 杭州 310027）
Shape retrieval method of 3D models based on shape  distribution graph and BP neural network
XU Jing-hua, ZHANG Shu-you
(College of Mechanical and Energy Engineering, Zhejiang University, Hangzhou 310027, China)
 全文: PDF(2511 KB)  
摘要：

为实现已有设计实例的重用,满足对设计基元层次相似搜索的要求,提出了一种三维模型检索方法.在模型B-Rep数据结构基础上,通过构造离散曲面获取三维模型的离散点集.利用正态分布种子作为索引,对离散点集进行随机选取,计算任意两点之间的欧氏距离获得三维模型的欧氏距离序列.通过分治快速排序和概率分布统计获得三维模型的形态分布图,将其作为三维模型的检索索引,并进行了鲁棒性分析.使用BP神经网络对不同模型的形态分布图进行非线性映射,通过比较三维模型的形态分布图获得其形状相似度,实现了设计基元的检索.开发了原型系统,以机械零件的不同粒度设计基元为重点进行验证和应用,实验结果表明,该方法具有较好的可计算性和较高的检测精度,对于实现已有设计重用及提高产品设计效率具有重要意义.
关键词： 三维模型;  形态分布;  BP神经网络;  相似度;  形状检索    
Abstract:

A shape retrieval method of 3D models was put forward to realize the reuse of existing design cases and satisfy the need of hierarchy similarity searching of design primitives. On the basis of the B-Rep data structure of 3D models, the discrete points set is obtained through constructing the discrete surfaces of solid models. The elements of the points set are selected at random via seeds which belong to normal distribution. The Euclidean distance sequence is acquainted by calculating the Euclidean distance  between  arbitrary two points from the selected points. The shape distribution graph (SDG) is then obtained via the quick sorting based on the divide-and-conquer algorithm and  the distribution possibility statistics of the Euclidean distance sequence, then the SDG is defined as the shape retrieval index after robustness analysis. The nonlinear mapping  of the SDG of 3D models is achieved by means of BP neural network. The shape similarity between solid models is obtained via the comparison between the SDGs, and the retrieval  of design primitives is realized. A prototype system was developed to verify the proposed method focusing on the design primitives with different granularities of mechanical  parts. The test results proved that the computability and precision of the method are favorable enough for practical requirements. The method has important significance to  realize the design reuse and improve the design efficiency．
Key words: 3D model    shape distribution    BP neural networks    similarity    shape retrieval
出版日期: 2009-06-01
:  TP391  
基金资助:

国家“863”高技术研究发展计划资助项目（2006AA04Z114）；国家自然科学基金资助项目（50775201）.
通讯作者: 张树有，男，教授，博导.     E-mail: zsy@zju.edu.cn
作者简介: 徐敬华（1979-），男，山东胶南人，博士生，主要从事CAD/CAE/KBE研究.
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
徐敬华
张树有

引用本文:

徐敬华, 张树有. 基于形态分布图与BP神经网络的三维模型检索方法[J]. J4, 2009, 43(5): 877-883.

XU Jing-hua, ZHANG Shu-you. Shape retrieval method of 3D models based on shape  distribution graph and BP neural network. J4, 2009, 43(5): 877-883.

链接本文:

http://www.zjujournals.com/xueshu/eng/CN/10.3785/j.issn.1008-973X.2009.05.018    或    http://www.zjujournals.com/xueshu/eng/CN/Y2009/V43/I5/877

［1］ MAHMOUDI S, DAOUDI M. A probabilistic approach for 3D shape retrieval by characteristic views ［J］. Pattern Recognition Letters, 2007, 28(13): 17051718．
［2］ IP C Y, LAPADAT D, SIEGER L, et al. Using shape distributions to compare solid models ［C］∥ Proceedings of the Seventh ACM Symposium on Solid Modeling and Applications.  Saarbrücken: ACM, 2002: 7380．
［3］ JAIN V, ZHANG H. A spectral approach to shape-based retrieval of articulated 3D models ［J］. Computer-Aided Design, 2007, 39(5): 398407．
［4］ IYER S, NAGI R. Automated retrieval and ranking of similar parts in agile manufacturing ［J］. IIE Transactions on Design and Manufacturing, 1997, 29(10): 859876．
［5］ TSAI C Y, CHANG C A. A two-stage fuzzy approach to feature-based design retrieval ［J］. Computer in Industry, 2005, 56(5): 439505.
［6］ IYER N, JAYANTI S, LOU K, et al. Shape-based searching for product lifecycle applications ［J］. Computer-Aided Design, 2005, 37(13): 14351446．
［7］ GAO W, GAO S M, LIU Y S, et al. Multiresolutional similarity assessment and retrieval of solid models based on DBMS ［J］. Computer-Aided Design, 2006, 38(9): 9851001．
［8］ DMITRIY B, REGLI W C, SHOKOUFANDEH A. Local feature extraction and matching partial objects ［J］. Computer Aided Design, 2006, 38(10): 10201037．
［9］ IYER N, JAYANTI S, LOU K, et al. Three-dimensional shape searching: state-of-the-art review and future trends ［J］. Computer-Aided Design, 2005, 37(5): 509530．
［10］ HONG T, LEE K, KIM S. Similarity comparison of mechanical parts to reuse existing designs ［J］. Computer-Aided Design, 2006, 38(9): 973984．
[1] 谢杰, 黄筱调, 方成刚, 周宝仓, 陆宁. 磨齿机电主轴热特性及热误差建模[J]. 浙江大学学报(工学版), 2018, 52(2): 247-254.
[2] 尤海辉, 马增益, 唐义军, 王月兰, 郑林, 俞钟, 吉澄军. 循环流化床入炉垃圾热值软测量[J]. 浙江大学学报(工学版), 2017, 51(6): 1163-1172.
[3] 蒋卓华, 蒋焕煜, 童俊华. 穴盘苗自动移栽机末端执行器的优化设计[J]. 浙江大学学报(工学版), 2017, 51(6): 1119-1125.
[4] 景瑶, 郭斌, 王柱, 於志文, 周兴社. 基于群体智能挖掘的个性化商品评论呈现方法[J]. 浙江大学学报(工学版), 2017, 51(4): 675-681.
[5] 戴彩艳, 陈崚, 李斌, 陈伯伦. 复杂网络中的抽样链接预测[J]. 浙江大学学报(工学版), 2017, 51(3): 554-561.
[6] 巫江虹, 薛志强, 金鹏, 李会喜. 电动汽车热泵空调微通道换热器温度分布特性[J]. 浙江大学学报(工学版), 2016, 50(8): 1537-1544.
[7] 沈腾, 王炅, 黄刘. 离心环境下毛细被动阀的理论与实验[J]. 浙江大学学报(工学版), 2016, 50(8): 1578-1584.
[8] 刘磊,杨鹏,刘作军. 基于多源信息和粒子群优化算法的下肢运动模式识别[J]. 浙江大学学报(工学版), 2015, 49(3): 439-447.
[9] 白帆, 郑慧峰, 沈平平, 王成, 喻桑桑. 基于花朵特征编码归类的植物种类识别方法[J]. 浙江大学学报(工学版), 2015, 49(10): 1902-1908.
[10] 崔光茫, 赵巨峰, 冯华君, 徐之海, 李奇, 陈跃庭. 非均匀介质退化图像快速仿真模型的建立[J]. J4, 2014, 48(2): 303-311.
[11] 蒋湛,姚晓明,林兰芬. 基于特征自适应的本体映射方法[J]. J4, 2014, 48(1): 76-84.
[12] 扈中凯， 郑小林， 吴亚峰， 陈德人. 基于用户评论挖掘的产品推荐算法[J]. J4, 2013, 47(8): 1475-1485.
[13] 黄晓烁,何衍,蒋静坪. 基于互联网无刷直流电机传动系统的控制策略[J]. J4, 2013, 47(5): 831-836.
[14] 许琦, 顾新建. 一种基于Subject-Action-Object三元组的知识基因提取方法[J]. J4, 2013, 47(3): 385-399.
[15] 童水光, 王相兵, 钟崴, 张健. 基于BP-HGA的起重机刚性支腿动态优化设计[J]. J4, 2013, 47(1): 122-130.