Data fusion for NDE signal characterization

Abstract

The quality of this reproduction is dependent upon the quality of the copy submitted. Broken or indistinct print, colored or poor quality illustrations and photographs, print bleedthrough, substandard margins, and improper alignment can adversely affect reproduction. In the unlikely event that the author did not send UMI a complete manuscript and there are missing pages, these will be noted. Also, if unauthorized copyright material had to be removed, a note will indicate the deletion. Oversize materials (e.g., maps, drawings, charts) are reproduced by sectioning the original, beginning at the upper left-hand comer and continuing from left to right in equal sections with small overlaps. Photographs included in the original manuscript have been reproduced xerographically in this copy. Higher quality 6" x 9" black and white photographic prints are available for any photographs or illustrations appearing in this copy for an additional charge. Contact UMI directly to order.

An improved genetic local search algorithm for defect reconstruction from MFL signals

“…The selected member is perturbed according to the Gaussian probabilistic distribution function by a simulated-annealing technique. The perturbation of the i th component of the selected member can be written as (2) where ∆ x i is the amount of perturbation on parameter x i . With the use of the simulated-annealing technique, the amount of perturbation can be expressed as (3) where rand(0, 1) is a Gaussian random number with the zero mean and unit variance, x i max and x i min denote the extreme values of the parameter x i in the search…”

“…However, iterative methods using the numerical-based forward models are computationally expensive. Neural networks are utilized for solving inverse problems in NDE [1][2][3][4] and used to represent the forward process in iterative methods [1]. Huang et al [3] described the use of a wavelet-basis-function neural network to predict three-dimensional defect profiles.…”

2D defect reconstruction from MFL signals by a genetic optimization algorithm

“…However, iterative methods using the numerical-based forward models are computationally expensive. Neural networks are utilized for solving inverse problems in NDE [1][2][3][4] and used to represent the forward process in iterative methods [1]. In neural networks, the solution of an inverse problem is to estimate unknown weights or parameters from a set of input-output examples during learning.…”

Defect Reconstruction from MFL Signals Using An Improved Genetic Local Search Algorithm

“…However, iterative methods using the numerical-based forward models are computationally expensive. Neural networks are utilized for solving inverse problems in NDE [ 1,2,3,4] and used to represent the forward process in the iterative methods [1]. Huang et al [3] described the use of a wavelet basis function (WBF) neural network to predict three-dimensional defect profiles.…”

“…The selected member is perturbed according to the Gaussian probabilistic distribution function (GPDF) using a simulated annealing technique. The perturbation of the ith component of the selected member can be written as x =x +Ax (2) where Axi is the amount of perturbation on the parameter xi. Using the simulated annealing technique, the amount of perturbation can be expressed as…”