| 基于支持向量机和神经网络方法的应力腐蚀裂纹定量重构 |
| |
| 引用本文： | 耿强,田淑侠,黄太回,陈振茂. 基于支持向量机和神经网络方法的应力腐蚀裂纹定量重构[J]. 电工技术学报, 2010, 0(10) |
| |
| 作者姓名： | 耿强 田淑侠 黄太回 陈振茂 |
| |
| 作者单位： | 西安交通大学强度与振动教育部重点实验室; |
| |
| 基金项目： | 国家自然科学基金(50677049,50977070); 国家973计划(2006CB601206,2007CB707702)资助项目 |
| |
| 摘 要： | 应力腐蚀裂纹具有类似于树枝分叉的复杂微观结构,其无损定量检测非常困难。提出了利用神经网络和支持向量机方法的涡流检测应力腐蚀裂纹定量重构方案并进行了有效性验证。首先将应力腐蚀裂纹等效为部分导电的半椭圆形平面裂纹,利用FEM-BEM混合法程序建立了涡流检测训练信号集;其次,针对所选神经网络和支持向量机方法分别提出了相应的裂纹参数化和阻抗信号特征提取方案,建立了应力腐蚀裂纹重构策略,在此基础上分别对模拟应力腐蚀裂纹进行了重构。计算结果表明支持向量机方法对含噪声信号的反演效果明显好于神经网络,该法对于应力腐蚀裂纹的定量重构更为有效。
|
| 关 键 词： | 应力腐蚀裂纹 神经网络方法 支持向量机 数字建模 定量重构 |
Reconstruction of Stress Corrosion Crack Using Neural Network and Support Vector Machine Techniques |
| |
| Geng Qiang Tian Shuxia Huang Taihui Chen Zhenmao. Reconstruction of Stress Corrosion Crack Using Neural Network and Support Vector Machine Techniques[J]. Transactions of China Electrotechnical Society, 2010, 0(10) |
| |
| Authors: | Geng Qiang Tian Shuxia Huang Taihui Chen Zhenmao |
| |
| Affiliation: | Geng Qiang Tian Shuxia Huang Taihui Chen Zhenmao(MOE Key Laboratory for Strength , Vibration Xi'an Jiaotong University Xi'an 710049 China) |
| |
| Abstract: | Stress corrosion crack(SCC) has a complex micro-structure similar with bifurcated tree branches and its non-destructive quantitative evaluation is difficult.In this paper,reconstruction schemes based on artificial neural networks(ANN) and support vector machine(SVM) are proposed based on a conductive crack model.ECT signals from a pancake coil probe scanned just over the crack are taken as the source signals for the crack reconstruction.A lot of sample ECT signals are generated using a FEM-BEM hybrid code a... |
| |
| Keywords: | SCC artificial neural networks support vector machine numerical modeling reconstruction |
| 本文献已被 CNKI 等数据库收录！ |
