Paper Title:
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.

  Info
Periodical
Advanced Materials Research (Volumes 301-303)
Chapter
Chapter 1: Material Science and Technology
Edited by
Riza Esa and Yanwen Wu
Pages
329-333
DOI
10.4028/www.scientific.net/AMR.301-303.329
Citation
H. C. Sun, "Pattern Recognition of the Steel Rod Based on Artificial Neural Network and SVM", Advanced Materials Research, Vols. 301-303, pp. 329-333, 2011
Online since
July 2011
Authors
Export
Price
$32.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.

Authors: Hui Zhen Yang, Wen Guang Zhao, Wei Chen, Xu Quan Chen
Chapter 8: System Modeling and Simulation
Abstract:Wavelet Neural Network (WNN) is a new form of neural network combined with the wavelet theory and artificial neural network. The wavelet...
4847
Authors: Shu Yan Zhao, Qi Wang
Chapter 1: Mechatronics Materials
Abstract:The sensor fault diagnosis method based on wavelet packet characteristic entropy and relevance vector machine are researched, which is used...
3
Authors: Xiao Li Xu, Zhang Lei Jiang, Yun Bo Zuo
Chapter 2: Materials Science and Engineering
Abstract:Chinese wind power industry is in the ascendant. The hidden fault development trend prediction technology will become increasingly important...
1154
Authors: Xiao Yun Gong, Jie Han, Hong Chen, Wen Ping Lei
Chapter 5: Control and Detection Technology
Abstract:Wavelet envelope demodulation method can distinguish the fault information from complex bearing vibration signal. However, traditional signal...
873
Authors: Jia Jun Zhang, Li Juan Liang
Chapter 1: Computing, Industrial Engineering and Technology
Abstract:The background noise influences the face image recognition greatly. It is crucial to remove the noise signals prior to the face image...
74