| 基于均匀设计和NN-GA的CAD模型多目标直接优化方法 |
| |
| 引用本文： | 隋天中,林文强,郑晓昕,闻邦椿. 基于均匀设计和NN-GA的CAD模型多目标直接优化方法[J]. 中国机械工程, 2008, 19(2): 222-225 |
| |
| 作者姓名： | 隋天中 林文强 郑晓昕 闻邦椿 |
| |
| 作者单位： | 东北大学,沈阳,110004 |
| |
| 基金项目： | 国家自然科学基金 , 辽宁省博士科研项目 |
| |
| 摘 要： | 提出了一种基于试验数据的多目标直接优化方法，该方法采用均匀设计原理安排试验方案，利用三维CAD模型的参数化驱动特点，完成虚拟试验过程和数据获取，以试验数据为训练样本，建立了CAD模型参数与目标之间的非线性映射关系的神经网络模型，运用Pareto遗传进化算法和小生境技术对CAD模型进行多目标参数优化，可在指定区域内找出CAD模型的Pareto最优解集。
|
| 关 键 词： | 多目标优化 均匀设计 神经网络 Pareto遗传算法 CAD模型 |
| 文章编号： | 1004-132X（2008）02-0222-04 |
| 收稿时间： | 2006-10-19 |
| 修稿时间： | 2007-10-23 |
Multi-Objective Direct Optimization Method for CAD Model Based on Uniform Design and NN-GA |
| |
| Sui Tianzhong,Lin Wenqiang,Zheng Xiaoxin,Wen Bangchun. Multi-Objective Direct Optimization Method for CAD Model Based on Uniform Design and NN-GA[J]. China Mechanical Engineering, 2008, 19(2): 222-225 |
| |
| Authors: | Sui Tianzhong Lin Wenqiang Zheng Xiaoxin Wen Bangchun |
| |
| Abstract: | A multi-objective direct optimization method based on uniform design and NN-GA was proposed. This method dealed with test project using uniform design principle, utilizing drive characteristics about 3D CAD model, accomplished virtual testing course and data collecting. On the basis of this, taking these data as training sample, a neural network model of nonlinear mapping rela tions between parameter and object of CAD model was established. Applying Pareto genetic algorithm and niche technique, Multi-Objective Parameters Optimization of CAD model was done. A Paretooptimal set of CAD model can be found in specific extent. |
| |
| Keywords: | multi-objective optimization uniform design neural network Pareto genetic algorithm CAD model |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《中国机械工程》浏览原始摘要信息 |
|
点击此处可从《中国机械工程》下载免费的PDF全文 |
