The Applied Research of System Subtractive Clustering RBF Algorithm in Eddy Current Testing on the Conductive Structure Defect

Ban Teng Liu; Ping Jie Huang; Guang Xin Zhang

doi:10.4028/www.scientific.net/AMR.712-715.2030

Paper Titles

A Two Dimension Signal Parameter Estimation Method Based on Super Resolution Technology
p.2007

Review on Meteorological Detector in Highway Mechanical and Electrical Engineering
p.2015

Design of Alarm Controllers in Detection and Alarm Systems for Gases
p.2021

A New Approach to Improve the Probability of Detection of Eddy Current Inspection
p.2026

The Applied Research of System Subtractive Clustering RBF Algorithm in Eddy Current Testing on the Conductive Structure Defect
p.2030

Quantitative Estimation with Lift-Off Effect in Conductive Structure
p.2035

Research of Benzoyl Peroxide Residues in Flour by Terahertz Spectroscopy Technology
p.2039

Study on Fault-Tolerant Technique Based on Knowledge Modules of Hydraulic Fault Theory
p.2043

Overview of Ultrasound Imaging Algorithms Based on Synthetic Aperture Focusing Technique
p.2051

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 712-715The Applied Research of System Subtractive...

The Applied Research of System Subtractive Clustering RBF Algorithm in Eddy Current Testing on the Conductive Structure Defect

Abstract:

According the problem of defect type discrimination and quantitative detection of defect depth in eddy current testing (ECT) on the conductive structure defect. The text proposes a RBF optimization algorithm based on system subtractive clustering (SISCA),first of all, according to the likelihood of the data ,it uses the system clustering method to estimate the number of clustering center, and improves mathematical model of subtractive clustering to determine the clustering scheme, then takes the minimum of the largest distance variance in the cluster as evaluation index to obtain the optimal clustering information to provide the critical initial value for training RBF network. The facts proves improved RBF algorithm takes higher accuracy and more effectiveness in the experiment of ECT.

You might also be interested in these eBooks

Advances in Manufacturing Science and Engineering

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 712-715)

Pages:

2030-2034

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.712-715.2030

Citation:

Cite this paper

Online since:

June 2013

Authors:

Ban Teng Liu, Ping Jie Huang, Guang Xin Zhang

Keywords:

Eddy Current Testing, RBF, Subtractive Clustering

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] A Leonardis, H Bischof. An efficient MDL-based construction of RBF networks [J]. Neural Networks, 1998,11(8): 963-973.

DOI: 10.1016/s0893-6080(98)00051-3

Google Scholar

[2] Dae-Won Kim , KiYoung Lee , Doheon Lee, ect. A kernel-based subtractive clustering method[J]. Pattern Recognition Letters 26 (2005) 879–891

DOI: 10.1016/j.patrec.2004.10.001

Google Scholar

[3] Wen Xin.Design of MATLAB application in neural networks [M].Beijing: Science Press, 2000.

Google Scholar

[4] Haralambos Sarimveis, Alex Alexandridis, George Bafas. A fast training algorithm for RBF networks basedon subtractive clustering[D], Neurocomputing 51 (2003) 501-505.

DOI: 10.1016/s0925-2312(03)00342-4

Google Scholar

[5] Li Guohou, Kang Xusheng, et. al. Thickness measuring of multilayer conductor based on eddy current testing[C], Proceedings of 2009 Chinese Control and Decision Conference, 2009:3284-3287.

DOI: 10.1109/ccdc.2009.5192475

Google Scholar