NSSC OpenIR  > 空间技术部
基于SVM的实时自动超声钢轨伤损检测分类系统(英文)
Alternative TitleAutomatic real-time SVM-based ultrasonic rail flaw detection and classif ication system
郝炜; 李成桐; 北京8701信箱
Department空间综合电子技术研究室
Source Publication中国科学院研究生院学报
2009
Volume26Issue:4Pages:517-521
ISSN1002-1175
Language中文
Keyword模式识别 超声波钢轨探伤 支持向量机 Dsp实时信号处理
Abstract介绍了一个更有效的基于支持向量机的实时超声波钢轨伤损自动检测分类系统.根据钢轨伤损的特点提取特征量,利用基于支持向量机的分类预测算法实现钢轨伤损的实时检测分类,并基于统计处理的计算伤损尺寸.在嵌入式系统DSP中利用该机器学习算法实现了伤损的实时处理和测试.实现了钢轨伤损实时报警、显示伤损类型、所处轨内位置及程度.
Other AbstractThis paper describes a more efficient real time SVM(support vector machine)-based ultrasonic rail defect detection and classification system. Feature extraction is achieved based on the attribute of ultrasonic rail defect and then SVM classification prediction algorithm and statistical processing are used to realize classification and calculating the size of the rail defect . This machine learning algorithm is tested in DSP and the type , grade and location of the defects are displayed in real-time.
Indexed ByCSCD
Funding Project中国科学院空间科学与应用研究中心
Citation statistics
Document Type期刊论文
Identifierhttp://ir.nssc.ac.cn/handle/122/786
Collection空间技术部
Corresponding Author北京8701信箱
Recommended Citation
GB/T 7714
郝炜,李成桐,北京8701信箱. 基于SVM的实时自动超声钢轨伤损检测分类系统(英文)[J]. 中国科学院研究生院学报,2009,26(4):517-521.
APA 郝炜,李成桐,&北京8701信箱.(2009).基于SVM的实时自动超声钢轨伤损检测分类系统(英文).中国科学院研究生院学报,26(4),517-521.
MLA 郝炜,et al."基于SVM的实时自动超声钢轨伤损检测分类系统(英文)".中国科学院研究生院学报 26.4(2009):517-521.
Files in This Item:
File Name/Size DocType Version Access License
2009264517.pdf(305KB) 开放获取CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[郝炜]'s Articles
[李成桐]'s Articles
[北京8701信箱]'s Articles
Baidu academic
Similar articles in Baidu academic
[郝炜]'s Articles
[李成桐]'s Articles
[北京8701信箱]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[郝炜]'s Articles
[李成桐]'s Articles
[北京8701信箱]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.