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

Magnetic flux leakage techniques are used extensively to detect and charact erize defects in natural gas transmission pipelines. This paper presents a novel approach for training a multiresolution, hierarchical wavelet basis f unction (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 dya dic expansion scheme and a k-means clustering algorithm. The results indica te that significant advantages over other neural network based defect chara cterization schemes could be obtained, in that the accuracy of the predicte d defect profile can be controlled by the resolution of the network. The fe asibility of employing a WBF neural network is demonstrated by predicting d efect profiles from both simulation data and experimental magnetic flux lea kage signals. (C) 2000 Published by Elsevier Science Ltd.