Paper Titles
A Study on the Evaluation Methods of Running Safety for Railway Vehicle
p.1499
Statistical Analysis of Casting Defects in Microstructure for Understanding the Effect on Fatigue Property of 17-4PH Stainless Steel
p.1503
Consideration of Uncertainty in Diagnosis for Railway Arrester
p.1507
Detection and Image Processing of Interfacial Micro-Delamination in the Thin-Layered Structure by Using Nonlinear Ultrasonic Effect
p.1513
Application of Ultrasonic Test System for Test Performance Improvement of Welding Flaw
p.1517
Failure Analysis and Evaluation of Strength Properties for Brazed Joints
p.1522
Risk Assessment of Axially Loaded Single Piles using RSM-based Reliability Method
p.1526
Formulation of Reliability-Based Fatigue Assessment of a Car Body for a High Speed Train Passing Through Tunnels
p.1530
Reliability Assessment Approach Using Failure Mode Analysis in Machining Center
p.1535

Application of Ultrasonic Test System for Test Performance Improvement of Welding Flaw

Article Preview

Abstract:

In this research, we used nondestructive test based on ultrasonic test as inspection method, and made up inspection robot in order to control of ultrasonic probe on the SWP surface, and programmed to signal processing code and pattern classifying code by user made programming code. For evaluation of flaw signal is reflected on welding flaw, user-made program codes are composed of signal processing and probability neural network (PNN) and backpropagation neural network (BPNN). And then, we actually confirmed to the theoretical advantage of each neural network method compared probability neural network with backpropagation neural network for classification and recognition rate. For the application of classifier to SWP inspection system, BPNN classifier is adequate in the first stage. And then, the application of PNN classifier is adequate as the next stage. Because of PNN application need enough sample data that is due to probabilistic density function.

You might also be interested in these eBooks
Advanced Nondestructive Evaluation I View Preview

Info:

Periodical:

Key Engineering Materials (Volumes 321-323)

Pages:

1517-1521

DOI:

https://doi.org/10.4028/www.scientific.net/KEM.321-323.1517

Citation:

Cite this paper

Online since:

October 2006

Authors:

Chang Hyun Kim, Jae Yeol Kim, Kyung Seok Song, Yong Hoon Cha

Keywords:

2-Axes Inspection System, BP Neural Network (BPNN), Classification, Feature Variable, Probability Neural Network, Recognition, Spiral Weld Pipe, Weld Flaw

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

© 2006 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

References

[1] David. Broek : Elementary Engineering Fracture Mechanics, (Martinus Nij hoff Publishers, 1986) pp.33-116.

Google Scholar

[2] Rose, J. L : Element of a Feature-based Ultrasonic Inspection system, (Materials Evaluation, 1984) Vol. 42 pp.210-218.

Google Scholar

[3] Serabian, S. : Ultrasonic Size Determinations of Inclined Flaw-Use of Response Envelope Width, (British J. of NDT, 1981) Vol. 23 pp.281-285.

Google Scholar