| 基于径向基函数神经网络的自由曲面重构 |
| |
| 引用本文： | 熊邦书,何明一,冯燕.基于径向基函数神经网络的自由曲面重构[J].南昌航空工业学院学报,2002,16(3):8-12. |
| |
| 作者姓名： | 熊邦书 何明一 冯燕 |
| |
| 作者单位： | [1]南昌航空工业学院，江西南昌330034 [2]西北工业大学，陕西西安710072 |
| |
| 基金项目： | 国家自然科学基金资助 (60 172 0 40 ) |
| |
| 摘 要： | 根据径向基函数神经网络（RBFNN）具有很强的非线性逼近能力的优点，本文采用RBF网络模型进行自由曲面重构，建立了适应于曲面重构的径向基函数网络模型，讨论了基函数对重构曲面连续性的影响，并与多自由曲面重构，建立了适应于曲面重构的径向基函数风络模型，讨论了基函数对重构曲面连续性的影响，并与多层感知器神经网络的性能进行对比。理论分析和仿真实验结果表明：常用的几种径向基函数重构的曲面都具有很好的连续性，径向基函数网络用于曲面重构，不论是在拟合精度，还是网络的训练速度都明显优于多层感知器网络，具有一定的实用价值。
|
| 关 键 词： | 径向基函数 曲面重构 神经网络 |
| 文章编号： | 1001-4926(2002)03-0008-05 |
Freeform surface reconstruction by RBF neural network |
| |
| XIONG Bang shu ,HE Ming yi ,FENG Yan.Freeform surface reconstruction by RBF neural network[J].Journal of Nanchang Institute of Aeronautical Technology(Natural Science Edition),2002,16(3):8-12. |
| |
| Authors: | XIONG Bang shu HE Ming yi FENG Yan |
| |
| Institution: | XIONG Bang shu 1,2,HE Ming yi 2,FENG Yan 2 |
| |
| Abstract: | A novel method for surface reconstruction by radial basis function (RBF) neural network is proposed. An appropriate RBFNN model is constructed. The relationship between basis function and property of constructed surface is discussed. Theory analysis and the experiment results show that the surface constructed by some commonly used basis function is smooth. The precision and the training speed of RBF for surface reconstruction are superior to that of MLP. This approach is valuable for practical application. |
| |
| Keywords: | Radial basis function Surface reconstruction Neural network |
| 本文献已被 CNKI 维普 等数据库收录！ |
