Event Title

Development and Operational Use of Artificial Intelligence in In-Line MFL Pipeline Inspection

Location

Snowbird, UT, USA

Start Date

1-1-1999 12:00 AM

Description

The application of neural networks and artificial intelligence methods in NDE is progressively advancing. Utilisation of this technology has been particularly successful in finding qualitative and quantitative solutions were it involves complex and highly nonlinear phenomena [1–3]. Magnetic Flux Leakage (MFL) technology, which is widely accepted for the corrosion inspection of ferromagnetic pipelines, is such a phenomenon. In 1994 BJ Pipeline Inspection Services entered into this corrosion inspection industry with the development of a high-resolution MFL pipeline inspection tool family. In examining corrosion sizing methods, neural networks were found to be quite advantageous and successful in dealing with the nature of MFL defect signals. The successful development and application of neural networks for daily operations in commercial NDE in is presented here for the pipeline in-line inspection industry.

Book Title

Review of Progress in Quantitative Nondestructive Evaluation

Volume

18A

Chapter

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

Section

Classification Techniques

Pages

851-856

DOI

10.1007/978-1-4615-4791-4_109

Language

en

File Format

application/pdf

This document is currently not available here.

Share

COinS
 
Jan 1st, 12:00 AM

Development and Operational Use of Artificial Intelligence in In-Line MFL Pipeline Inspection

Snowbird, UT, USA

The application of neural networks and artificial intelligence methods in NDE is progressively advancing. Utilisation of this technology has been particularly successful in finding qualitative and quantitative solutions were it involves complex and highly nonlinear phenomena [1–3]. Magnetic Flux Leakage (MFL) technology, which is widely accepted for the corrosion inspection of ferromagnetic pipelines, is such a phenomenon. In 1994 BJ Pipeline Inspection Services entered into this corrosion inspection industry with the development of a high-resolution MFL pipeline inspection tool family. In examining corrosion sizing methods, neural networks were found to be quite advantageous and successful in dealing with the nature of MFL defect signals. The successful development and application of neural networks for daily operations in commercial NDE in is presented here for the pipeline in-line inspection industry.