Event Title

Flaw Characterization in Tubes by Inversion of Eddy Current Signals Using Neural Networks Trained by Finite Element Model-Based Synthetic Data

Location

Snowbird, UT, USA

Start Date

1-1-1999 12:00 AM

Description

Interpretation of eddy current signal for flaw characterization in tubes is corresponding to solving the inverse problem of eddy current testing. Approaches that have been proposed for the inversion of eddy current signal can be classified into two categories; phenomenological approaches and empirical approaches [1]. Phenomenological approaches which are based on models have been reported with very limited success due to the various barriers. Practical inversion skills that can be found in the current field applications are the second type of approaches, empirical approaches [2,3], can be called the ‘eddy current pattern recognition.

Book Title

Review of Progress in Quantitative Nondestructive Evaluation

Volume

18A

Chapter

Chapter 3: Simulations, Signal Processing, Tomography, and Holography

Section

Inversion, Reconstruction, Imaging

Pages

881-888

DOI

10.1007/978-1-4615-4791-4_113

Language

en

File Format

application/pdf

This document is currently not available here.

Share

COinS
 
Jan 1st, 12:00 AM

Flaw Characterization in Tubes by Inversion of Eddy Current Signals Using Neural Networks Trained by Finite Element Model-Based Synthetic Data

Snowbird, UT, USA

Interpretation of eddy current signal for flaw characterization in tubes is corresponding to solving the inverse problem of eddy current testing. Approaches that have been proposed for the inversion of eddy current signal can be classified into two categories; phenomenological approaches and empirical approaches [1]. Phenomenological approaches which are based on models have been reported with very limited success due to the various barriers. Practical inversion skills that can be found in the current field applications are the second type of approaches, empirical approaches [2,3], can be called the ‘eddy current pattern recognition.