CIMS论文的天地

 

RESEARCH ON COMPUTER–AIDED CREATIVE CONCEPTUAL DESIGN METHOD 

注意:本论文已在 Proceedings of the 5th International Conference on Frontiers of Design and Manufacturing (ICFDM'2002)》发表
使用者请注明论文出处
(ISTP收录本文)

LAI Chaoan, SUN Yanming,  HUANG Ping, ZHENG Shixiong
Institute of Mechanical Engineering, South China University of Technology, Post Code 510640

ABSTRACT:According to the model of multilevel rhombus thought (MRT), the drawbacks in CBR and GA were analyzed and it was pointed out that the fundamental reason to their drawbacks was their deviating from the model of MRT. Cluster analysis method was applied with a view to bind CBR, cluster analysis and GA together to simulate a MRT process. It was pointed out that mapping times from customer needs to physical structure should be reduced in order to guarantee the effect of first convergence. The definition of similarity and the arithmetic formula of similarity measure for physical structure were put forth in order to carry out cluster analysis. Above method improves the effect of case retrieval and the performance of GA and aid in the design of creative artifacts. 
Keywords: Creative designing; Case-Based Reasoning (CBR); Cluster analysis; Genetic Algorithms (GA)

计算机辅助创新概念设计方法研究

赖朝安 孙延明 黄平 郑时雄
(华南理工大学 机械工程学院 广州 510640)

摘 要: 依据多级菱形思维模型,分析基于实例的推理、遗传算法的不足并指出其深层原因是不符合多级菱形思维模型。提出引入聚类分析方法,用实例检索、聚类分析与遗传算法优化模拟多级菱形思维过程。通过减少从用户需求到产品结构的映射次数以保证第一次收敛的效果,定义产品结构相似性并推导出相似度计算公式以实现聚类分析,并依此改进实例检索效果与遗传算法性能来促进创新设计。
关键词:创新设计;基于实例的推理(CBR);聚类分析(CA);遗传算法(GA)
中图分类号:TH122 文献标识码:A

作者简介:赖朝安,男, 1973年出生,博士。主要研究方向为数据挖掘,虚拟设计

1浏览PDF格式全文需要使用软件--Abode Acrobat(由于软件较大并常见,我站不提供下载)

2、下载论文全文请点击(32KB)

 


作者点评:

   根据产品设计师的思维过程,运用了基于实例推理、聚类分析、遗传算法来模拟,得出了有趣的结果。2003年11月5日

欢迎您参加讨论,发表您对此论文及其研究领域的看法!
(请在发言时在标题中使用所点评的论文的题目或研究方向,这样方便大家浏览!)

返回首页 | CIMS论文 | 并行工程 | 虚拟制造 | 敏捷制造 | 其他论文 | 项目开发 | 学术资源 | 站内全文搜索 | 免费论文网站大全 |

line.gif (4535 字节)

为了更好的为大家服务,欢迎您参加本站的投票调查

>>>>参加更多投票调查请点击!

本站永久域名:http://www.cimspaper.com欢迎访问

注意:本站内容未经书面允许不得转载

All rights reserved, all contents copyright 2000-2019
本站自2000年3月总网页访问量为