Paper Title:
Automated Multichannel Signal Classification Systems for Ultrasonic Nondestrucitve Evaluation
  Abstract

A key requirement in most ultrasonic weld inspection systems is the ability for rapid automated analysis to identify the type of flaw. Incorporation of spatial correlation information from adjacent A-scans can improve performance of the analysis system. This paper describes two neural network based classification techniques that use correlation of adjacent A-scans. The first method relies on differences in individual A-scans to classify signals using a trained neural network, with a post-processing mechanism to incorporate spatial correlation information. The second technique transforms a group of spatially localized signals using a 2-dimensional transform, and principal component analysis is applied to the transform coefficients to generate a reduced dimensional feature vectors for classification. Results of applying the proposed techniques to data obtained from weld inspection are presented, and the performances of the two approaches are compared.

  Info
Periodical
Key Engineering Materials (Volumes 321-323)
Edited by
Seung-Seok Lee, Joon Hyun Lee, Ik Keun Park, Sung-Jin Song, Man Yong Choi
Pages
1266-1269
DOI
10.4028/www.scientific.net/KEM.321-323.1266
Citation
J. Kim, P. Ramuhalli, L. Udpa, S. Udpa, "Automated Multichannel Signal Classification Systems for Ultrasonic Nondestrucitve Evaluation", Key Engineering Materials, Vols. 321-323, pp. 1266-1269, 2006
Online since
October 2006
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: Bo Dai, Ming Lu Ma
Chapter 5: Measurements, Monitoring and Sensor
Abstract:The measurement of wall thickness of pipelines is an important procedure of pipeline corrosion inspection. This procedure can be done...
1427
Authors: Zhi Hao Liu, Chao Lu
Chapter 3: Measurements, Mechatronics, Control and Automation
Abstract:Ultrasonic phased array imaging detection technology combinating the focused beam and array probe movement can get powerful test information....
799