NDT identification of a crack using ANNs with stochastic gradient descent

Author

Arkadan, A.A. ; Chen, Y. ; Subramanian, Sivaraman ; Hoole, S.R.H.

Author_Institution

Dept. of Electr. & Comput. Eng., Marquette Univ., Milwaukee, WI, USA

Volume

31

Issue

3

fYear

1995

fDate

5/1/1995 12:00:00 AM

Firstpage

1984

Lastpage

1987

Abstract

Nondestructive testing (NDT) is used to identify the anomalies and defects in inaccessible locations. Various techniques of optimization are used in NDT. In this work, the artificial neural networks (ANNs) are applied with NDT to identify a crack in a conducting medium. In general, deterministic techniques are used with the back propagation algorithm (BP) to train the neural networks. The ANNs which are trained by a deterministic method have a tendency to get trapped in local minima. In this paper a stochastic version of the gradient descent is applied to train the ANNs and it overcomes the difficulties-of local minima caused by the sinusoidal fields. The stochastic version used in this approach is based on the Metropolis algorithm which is frequently used in the simulated annealing

Keywords

backpropagation; crack detection; feedforward neural nets; mesh generation; simulated annealing; ANNs; Metropolis algorithm; NDT identification; back propagation algorithm; conducting medium; crack; deterministic method; deterministic techniques; simulated annealing; stochastic gradient descent; Artificial neural networks; Educational institutions; Neural networks; Nondestructive testing; Permeability; Simulated annealing; Steel; Stochastic processes; Topology; Tunneling;

fLanguage

English

Journal_Title

Magnetics, IEEE Transactions on

Publisher

ieee

ISSN

0018-9464

Type

jour

DOI

10.1109/20.376431

Filename

376431