Title :
Recognition of a Sucker Rod´s Defect with SVM
Author_Institution :
Northeastern Univ., Shenyang, China
Abstract :
In order to improve the recognition rate of a sucker rod´s defect and reduce the rapture possibility of the rod, the mixed characters include of wavelet packet energy character and the peak value in the time-domain were used to input a recognition network, and support vector machines (SVM) were used. Tested results with lots of data acquired in laboratory showed that SVM based on the mixed characters can enhance recognition rate of the sucker rod´s defect.
Keywords :
drilling machines; failure analysis; oil drilling; pattern recognition; production engineering computing; rods (structures); support vector machines; SVM; defect recognition; rod rapture possibility; sucker rod; support vector machines; time-domain analysis; wavelet packet energy character; Character recognition; Corrosion; Energy measurement; Frequency; Histograms; Noise reduction; Pattern recognition; Support vector machines; Time domain analysis; Wavelet packets;
Conference_Titel :
Measuring Technology and Mechatronics Automation (ICMTMA), 2010 International Conference on
Print_ISBN :
978-1-4244-5001-5
Electronic_ISBN :
978-1-4244-5739-7
DOI :
10.1109/ICMTMA.2010.356
