Adaptive Wavelets for Characterizing Magnetic Flux Leakage Signals from Pipeline inspection

Abstract

This paper presents an iterative inversion scheme using radial basis function neural network (RBFNN) for predicting the depth profile of a defect in the pipe-wall from the information in the magnetic flux leakage (MFL) signal. Due to the high dimensionality of the data the method uses a multi-resolution approach with adaptive wavelets. The algorithm is fast and provides full three dimensional profile of the defect in the pipewall which is important for predicting the remaining life of the pipe.