| 基于直流电位法的泡沫金属定量无损检测方法 |
| |
| 引用本文： | 解社娟,陈振茂,张东利,耿强. 基于直流电位法的泡沫金属定量无损检测方法[J]. 无损检测, 2008, 30(8) |
| |
| 作者姓名： | 解社娟 陈振茂 张东利 耿强 |
| |
| 作者单位： | 西安交通大学,强度与振动教育部重点实验室,西安,710049 |
| |
| 基金项目： | 国家重点基础研究发展计划(973计划)，国家自然科学基金，教育部跨世纪优秀人才培养计划 |
| |
| 摘 要： | 提出一种基于直流电位法的泡沫金属定量无损检测方法。该方法采用主元分析前馈神经网络求解逆问题,对内部缺陷进行定量。正问题求解采用有限元方法。为解决三维直流电场分析中庞大的节点数及神经网络所需大量训练数据带来的计算资源问题,开发了一种基于知识库的快速直流电位分布计算方法。算例结果表明,神经网络可有效用于泡沫金属的定量无损检测;所提出的快速算法可大大缩短计算时间且具有较高计算精度。
|
| 关 键 词： | 泡沫金属 定量无损检测 神经网络 快速算法 |
Quantitative NDT of Metallic Foam Based on Direct Current Potential Drop |
| |
| XIE She-Juan,CHEN Zhen-Mao,ZHANG Dong-Li,GENG Qiang. Quantitative NDT of Metallic Foam Based on Direct Current Potential Drop[J]. Nondestructive Testing, 2008, 30(8) |
| |
| Authors: | XIE She-Juan CHEN Zhen-Mao ZHANG Dong-Li GENG Qiang |
| |
| Affiliation: | XIE She-Juan; CHEN Zhen-Mao; ZHANG Dong-Li; GENG Qiang(MOE Key Laboratory for Strength and Vibration; Xi an Jiaotong University; Xi an 710049; China); |
| |
| Abstract: | A numerical method of quantitative nondestructive testing(NDT) of metallic foam was developed on the basis of the direct current potential drop(DCPD). A feed forward neural network(NN) was applied for the inverse mapping to quantify the inner flaw in addition with a principal component analysis process. Solving of obverse problem utilizes finite element method(FEM). To cope with the huge computer burden necessary to generate training data for NN of three dimensions of giant nodes in DC field, a novel fast f... |
| |
| Keywords: | Metallic foam Quantitative nondestructive testing Neural networks Fast solver |
| 本文献已被 维普 万方数据 等数据库收录！ |
