A New Flaw Identification Model of Ultrasonic Signals Based on EMD and Possibility SVM


Article Preview

Automatic identification of flaws is very important for ultrasonic nondestructive testing and evaluation of large shafts. A novel automatic identification model of defects is presented. Empirical Model decomposition (EMD) is applied to feature extraction of ultrasonic signals, and possibility Support Vector Machine (SVM) with Dempster-Shafer (DS) theory to perform the identification task. Meanwhile, comparative study on convergent velocity and classified effect is done among SVM and artificial neural network (ANN) with DS models. To validate the method, some experiments are performed and the results show the proposed system has very high identification performance for large shafts and the possibility SVM processes better classification performance and spreading potential than ANN with DS model under the small study sample condition.



Advanced Materials Research (Volumes 189-193)

Edited by:

Zhengyi Jiang, Shanqing Li, Jianmin Zeng, Xiaoping Liao and Daoguo Yang




X. F. Zhao et al., "A New Flaw Identification Model of Ultrasonic Signals Based on EMD and Possibility SVM", Advanced Materials Research, Vols. 189-193, pp. 2764-2769, 2011

Online since:

February 2011




[1] Song Shou-peng, Que Pei-wen, Wavelet based noise supression technique and its application to ultrasonic flaw detection, Ultrasonics, 2006(44): 188~193.

DOI: https://doi.org/10.1016/j.ultras.2005.10.004

[2] Acciani G, Brunetti G, Fornarelli G, et al. Neural network classification of flaws in pipes using ultrasonic waveforms [J]. WSEAS Transactions on Circuits and Systems, 2005, 4(10): 1387-1394.

[3] Fei C, Han Zh, Dong J. An ultrasonic flaw-classification system with wavelet-packet decomposition, a mutative scale chaotic genetic algorithm, and a support vector machine and its application to petroleum-transporting pipelines [J]. Russian Journal of Nondestructive Testing, 2006, 42(3): 190-197.

DOI: https://doi.org/10.1134/s1061830906030077

[4] Bettayeb Fairouz, Rchedi Tarek, Benbaartaoui Hamid. An Improved Automated Ultrasonic NDE System by Wavelet and Neuron Networks [J]. Ultrasonics, 2004, 42(1-9): 853-858.

DOI: https://doi.org/10.1016/j.ultras.2004.01.064

[5] Lin HT, Lin CJ, Weng RC. A note on Platt's probabilistic outputs for support vector machines [J]. Machine Learning, 2007, 68(3): 267-276.

DOI: https://doi.org/10.1007/s10994-007-5018-6

Fetching data from Crossref.
This may take some time to load.