Characterization of gas pipeline inspection signals using wavelet basis function neural networks

TY - JOUR

T1 - Characterization of gas pipeline inspection signals using wavelet basis function neural networks

AU - Hwang, K.

AU - Mandayam, S.

AU - Udpa, S. S.

AU - Udpa, L.

AU - Lord, W.

AU - Atzal, M.

N1 - Funding Information: The work described in this paper was supported by the Gas Research Institute, 8600 West Byrn Mawr Avenue, Chicago, IL. Magnetic flux leakage signals were provided by Tuboscope Vetco Pipelines Inc., Houston, TX. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.

PY - 2000/12

Y1 - 2000/12

N2 - Magnetic flux leakage techniques are used extensively to detect and characterize defects in natural gas transmission pipelines. This paper presents a novel approach for training a multiresolution, hierarchical wavelet basis function (WBF) neural network for the three-dimensional characterization of defects from magnetic flux leakage signals. Gaussian radial basis functions and Mexican hat wavelet frames are used as scaling functions and wavelets respectively. The centers of the basis functions are calculated using a dyadic expansion scheme and a k-means clustering algorithm. The results indicate that significant advantages over other neural network based defect characterization schemes could be obtained, in that the accuracy of the predicted defect profile can be controlled by the resolution of the network. The feasibility of employing a WBF neural network is demonstrated by predicting defect profiles from both simulation data and experimental magnetic flux leakage signals.

AB - Magnetic flux leakage techniques are used extensively to detect and characterize defects in natural gas transmission pipelines. This paper presents a novel approach for training a multiresolution, hierarchical wavelet basis function (WBF) neural network for the three-dimensional characterization of defects from magnetic flux leakage signals. Gaussian radial basis functions and Mexican hat wavelet frames are used as scaling functions and wavelets respectively. The centers of the basis functions are calculated using a dyadic expansion scheme and a k-means clustering algorithm. The results indicate that significant advantages over other neural network based defect characterization schemes could be obtained, in that the accuracy of the predicted defect profile can be controlled by the resolution of the network. The feasibility of employing a WBF neural network is demonstrated by predicting defect profiles from both simulation data and experimental magnetic flux leakage signals.

UR - http://www.scopus.com/inward/record.url?scp=0034540049&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034540049&partnerID=8YFLogxK

U2 - 10.1016/S0963-8695(00)00008-6

DO - 10.1016/S0963-8695(00)00008-6

M3 - Article

SN - 0963-8695

VL - 33

SP - 531

EP - 545

JO - NDT and E International

JF - NDT and E International

IS - 8

ER -