Journal of University of Chinese Academy of Sciences >
Automatic real-time SVM-based ultrasonic rail flaw detection and classification system
Revised date: 2009-04-13
Online published: 2009-07-15
This 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.
HAO Wei , LI Cheng-Tong . Automatic real-time SVM-based ultrasonic rail flaw detection and classification system[J]. Journal of University of Chinese Academy of Sciences, 2009 , 26(4) : 517 -521 . DOI: 10.7523/j.issn.2095-6134.2009.4.013
[1] Ma Y P,Zeng R Z. Rail defect detection work . China Railway Industry Book Concern, 2005.
[2] TMS320C5510, DIGITAL SIGNAL PROCESSORS Texas Instrument Incorporated, l999.
[3] Jiao S X,Stephen Brian Wong. Development of an automated ultrasonic testing system
[J]. Nanyang Technological University, Singapore, Proceedings SPIE (International Society of Optical Engineers)Singapore, 2004, 5852: 480-486.
[4] Khelil M,Boudraa M,Kechida A, et al. Classification of defects by the SVM method and the principal component analysis(PCA)
[J]. Transactions on Engineering, Computing and Technology,2005,9:226-231.
[5] Chang C C,Lin C J. LIBSVM: a library for support vector machines . .http://www.csie.ntu.edu.tw/~cjlin/papers/libsvm.pdf. ６] Hsu C W,Chang C C,Lin C J.A practical guide to support vector classification . .http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf.
/
| 〈 |
|
〉 |