|
|||||
|
|
| 基于挠度的铁路双线简支钢桁梁桥杆件损伤程度识别研究 | |
| 引用本文： | 梁滨波,任剑莹,苏木标.基于挠度的铁路双线简支钢桁梁桥杆件损伤程度识别研究[J].铁道标准设计通讯,2014(11). |
| 作者姓名： | 梁滨波 任剑莹 苏木标 |
| 作者单位： | 1. 河北省电力勘测设计研究院土建部,石家庄,050031 2. 石家庄铁道大学工程力学系,石家庄,050043 3. 石家庄铁道大学大型结构健康诊断与控制研究所,石家庄,050043 |
| 基金项目： | 国家自然科学基金，河北省自然科学基金，河北省教育厅基金 |
| 摘 要： | 以梁桥节点最大位移改变率作为损伤程度伤识别指标,分别采用广义回归神经网络(GRNN)算法和ε-支持向量回归机(ε-SVR)算法,进行损伤程度识别研究。通过对一座铁路双线简支钢桁梁桥某杆件的损伤程度识别研究发现:(1)GRNN损伤程度识别模型具有一定的抗噪能力,不具有泛化性。(2)SVR损伤程度识别模型具有很强的抗噪能力和很好的泛化性。(3)以桥梁节点最大位移改变率作为损伤程度识别指标时,数据回归算法不能采用GRNN算法,应采用ε-SVR算法。 |
| 关 键 词： | 铁路桥 钢桁梁桥 损伤程度识别 GRNN ε-SVR |
Damage Degree Identification of Railway Double-track Simply Supported Steel Truss Bridge Based on Deflection |
|
| Liang Bibo,Ren Jianying,Su Mubiao.Damage Degree Identification of Railway Double-track Simply Supported Steel Truss Bridge Based on Deflection[J].Railway Standard Design,2014(11). | |
| Authors: | Liang Bibo Ren Jianying Su Mubiao |
| Institution: | ,Civil Engineering Department,Hebei Electric Power Design & Research Institute,Department of Engineering Mechanics,Shijiazhuang Tiedao University,Structural Health Monitoring and Control Institute,Shijiazhuang Tiedao University |
| Abstract: | Using the bridge node maximum displacement change percentages as the damage degree identification indexes and the intelligent algorithm of Generalized Regression Neural Network(GRNN)and ε-Supported Vector Regression(ε-SVR),this paper studies the damage degree identification.Taking a railway double-track simply supported steel truss bridge as study example,the results show that:(1) GRNN model has a certain anti-noise capacity,but hasn't generalization;(2) SVR model has good anti-noise capacity and generalization;(3) When the node maximum displacement changes are taken as damage degree identification indexes,the intelligent algorithm should use ε-SVR instead of GRNN. |
| Keywords: | Railway bridge Steel truss bridge Damage degree identification GRNN ε-SVR |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |