|
|||||
|
|
| 裂纹源的支持向量机与神经网络定位对比研究 | |
| 引用本文： | 毛汉颖,黄振峰,王向红.裂纹源的支持向量机与神经网络定位对比研究[J].广西大学学报(自然科学版),2009,34(3). |
| 作者姓名： | 毛汉颖 黄振峰 王向红 |
| 作者单位： | 1. 广西工学院,广西柳州,542506 2. 广西大学机械学院,广西,南宁,530004 3. 上海交通大学机械学院,上海,200030 |
| 基金项目： | 国家自然科学基金资助项目 |
| 摘 要： | 利用声发射技术检测水轮机叶片裂纹的产生位置.针对水轮机结构复杂及裂纹位置比较集中等特点,提出利用支持向量机的分类与回归功能对水轮机转轮叶片的裂纹进行定位.结果表明,与BP(误差反向传播)神经网络相比,支持向量机在叶片区域的识别率为100%,高于BP网络;裂纹源到焊缝的距离的预测精度也稍高于BP网络,因而支持向量机是一种适合复杂结构的定位方法,特别是在样本量不大的场所. |
| 关 键 词： | 支持向量机 源定位 声发射 |
Damage localization in turbine runner blades using support vector machines and Neural Networks |
|
| MAO Han-ying,HUANG Zhen-feng,WANG Xiang-hong.Damage localization in turbine runner blades using support vector machines and Neural Networks[J].Journal of Guangxi University(Natural Science Edition),2009,34(3). | |
| Authors: | MAO Han-ying HUANG Zhen-feng WANG Xiang-hong |
| Institution: | 1.Guangxi University of Technology;Liuzhou 542506;China;2.College of Mechanical Engineering;Guangxi University;Nanning 530004;3.School of Mechanical Engineering;Shanghai Jiaotong University;Shanghai 200030;China |
| Abstract: | Acoustic emission(AE) technique was used to detect cracks and their locations in turbine blades.Turbine runner has a complex structure and cracks occurred on some special regions.The source location of cracks in turbine runner blades was researched using classfication and regression functions of support vector machines(SVM).The results show that the SVM technique has 100 percent of recognition rate in crack region,which is higher than back propagation neural network(BPNN),and that estimating precision of di... |
| Keywords: | support vector machines source location acoustic emission |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |