Crack detection in supported beams based on neural network and support vector machine

Authors:
Long Liu;Guang Meng
Affiliations:
State Key Laboratory of Vibration, Shock and Noise, Shanghai Jiaotong University, Shanghai, China;State Key Laboratory of Vibration, Shock and Noise, Shanghai Jiaotong University, Shanghai, China
Venue:
ISNN'05 Proceedings of the Second international conference on Advances in Neural Networks - Volume Part III
Year:
2005

Citing 2
Cited 1

Estimation of Dependences Based on Empirical Data: Springer Series in Statistics (Springer Series in Statistics)

Estimation of Dependences Based on Empirical Data: Springer Series in Statistics (Springer Series in Statistics)
LIBSVM: A library for support vector machines

ACM Transactions on Intelligent Systems and Technology (TIST)

Detection of Cracks and Corrosion for Automated Vessels Visual Inspection

Proceedings of the 2010 conference on Artificial Intelligence Research and Development: Proceedings of the 13th International Conference of the Catalan Association for Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

A study is presented to compare the performance of crack detection using neural network(NN) and support vector machine (SVM) based on natural frequencies. The SVM is a machine learning algorithm based on statistical learning theory, and it is also a class of regression method with the good generalization ability. Firstly, the basic theory of the back-propagation neural network and support vector regression is briefly reviewed. Then the feasibility of the crack detection using these methods are investigated by locating and sizing cracks in supported beams for which a few natural frequencies are available. It is observed that crack's location and depth can be estimated with a relatively small size error. The results show that the SVM is a powerful and effective method for crack identification.