Pattern Recognition of the Steel Rod Based on Artificial Neural Network and SVM

Hong Chun Sun

doi:10.4028/www.scientific.net/AMR.301-303.329

Paper Titles

Using Perturbation FEM Compute the IC Interconnect Parasitic Capacitances Considering Process Variation
p.303

Mercerizing Lye Concentration Online Measurement and Control
p.310

Fractal Prediction Model of Friction Coefficient in Dry Friction Pair
p.315

Combustion Kinetics of Pellets Made by Sewage Sludge, Pulverized Fuel Ash and River Sludge
p.321

Pattern Recognition of the Steel Rod Based on Artificial Neural Network and SVM
p.329

Efficient Terahertz Surface-Emitted Difference Frequency Generation in Periodically-Inverted GaAs Crystals
p.334

Experimental Study on Strength Characteristics of Cement-Soil under Fixed Spherical Pressure Condition
p.338

Effect of Voids on Moisture Absorption of CFRP Laminates in Hygrothermal Environment
p.342

Cloning, Expression and Characterization of β-Glucosidase from L. Delbrueckii Subsp. Delbrueckii in Escherichia coli
p.347

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 301-303Pattern Recognition of the Steel Rod Based on...

Pattern Recognition of the Steel Rod Based on Artificial Neural Network and SVM

Abstract:

The steel rod is an important part for project fields , and it is large-scale to be used. it is apt to crack, corrosion and so on in the poor working conditions. In order to recognize correctly the type of defects, a method was presented to extract frequency band energy feature by using wavelet package decomposition. In the meantime, to extract the peak-peak value in the time-domain and make the mixed feature vector. With the way of pattern recognition, the best recognition way was got by comparing the BP artificial neural network(ANN), PNN(probability neural network) artificial neural network and "one-versus-one" support vector machine(SVM).The result showed that the recognition rate of SVM was more suitable for defects’ identification in steel rod.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 301-303)

Pages:

329-333

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.301-303.329

Citation:

Cite this paper

Online since:

July 2011

Authors:

Hong Chun Sun

Keywords:

Artificial Neural Network (ANN), Pattern Recognition, Steel Rod, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Rubini R. : Application of the Envolope and Wavelet Transform A-nalysis for the Diagnosis of Incipient Faults in Ball Bearings. Mechanical Systems and Signal Processing,. 15, 287-302(2001).

DOI: 10.1006/mssp.2000.1330

Google Scholar

[2] Daubechies I. : Orthonormal Bases of Compactly Supported Wavelets. Communications on Pure and Applied Mathematics. 41, 909-996(1998).

DOI: 10.1002/cpa.3160410705

Google Scholar

[3] Nikolaou N G , Antoniadis I A.: Rolling element bearing fault diagnosis using wavelet packet. NDT&E International. 35, 197-205( 2002).

DOI: 10.1016/s0963-8695(01)00044-5

Google Scholar

[4] Lin J, Qu L. : Feature extraction based on Morlet wavelet and its application for mechanical fault diagnosis . Journal of Sound and Vibration. 234, 135-48( 2000).

DOI: 10.1006/jsvi.2000.2864

Google Scholar

[5] Forster F. : New findings in the field of nondestructive magnetic leakage field inspection. NDT international. 19, 657-673(1986).

Google Scholar

[6] Owston, C. N. : The magnetic flux leakage technique of NDT. British Journal of NDT. 20, 162-168(1977).

Google Scholar

[7] O Déniz, M Castrillón, M Hernández: Face recognition using independent component analysis and support vector machines. pattern Recognition Letters. 24, 2153-2157(2003).

DOI: 10.1016/s0167-8655(03)00081-3

Google Scholar