| 基于薄板翻边回弹试验的RBF神经网络模型 |
| |
| 引用本文： | 刘克进,杨沿平,钟志华.基于薄板翻边回弹试验的RBF神经网络模型[J].汽车工程,2005,27(4):492-494,491. |
| |
| 作者姓名： | 刘克进 杨沿平 钟志华 |
| |
| 作者单位： | 湖南大学现代车身教育部重点实验室,长沙,410082 |
| |
| 基金项目： | 国家自然科学基金福特专项（50122154）资助. |
| |
| 摘 要： | 对薄板内凹、外凸翻边进行了回弹试验，借助混合水平的正交试验设计方法从试验数据中选择训练样本，建立了同弹的径向基函数神经网络模型。分析了训练样本集的大小对模型误差的影响，指出在训练样本不少于14个的情况下，模型具有较高的顶测精度。
|
| 关 键 词： | 回弹 试验 神经网络 训练样本集 神经网络模型 回弹试验 翻边 薄板 RBF 径向基函数 |
| 收稿时间： | 2004-06-30 |
| 修稿时间： | 2004-06-302004-09-10 |
Modelling of Springback with RBF Neural Network Based on Experiments in Flanging Operation |
| |
| Liu Kejin,Yang Yanping,Zhong Zhihua.Modelling of Springback with RBF Neural Network Based on Experiments in Flanging Operation[J].Automotive Engineering,2005,27(4):492-494,491. |
| |
| Authors: | Liu Kejin Yang Yanping Zhong Zhihua |
| |
| Abstract: | Experiments on springback in concave and convex edge flanging are carried out. Method of the mixed-level orthogonal test design is used to select the training sets from experiment data, and a radial basis function (RBF) neural network model for springback is developed. The effect of training set size on the error of neural network model is analyzed. The results show that the model has reasonable accuracy when the training set size is not less than 14. |
| |
| Keywords: | Springback Experiment Neural network Training set |
| 本文献已被 维普 万方数据 等数据库收录！ |
