Presenter Information

S. F. Burch, Harwell Laboratory

Location

Williamsburg, VA

Start Date

1-1-1988 12:00 AM

Description

Computer-based methods for analysing ultrasonic data to distinguish between different defect types have been based on a variety of techniques such as adaptive learning [1], artificial intelligence [2] and statistical pattern recognition [3]. The uncertain classification reliability of these techniques when applied to a range of realistic defect types has, however, often been a significant practical limitation to their use.

Book Title

Review of Progress in Quantitative Nondestructive Evaluation

Volume

7B

Chapter

Chapter 7: Characterization of Materials

Section

Ferromagnetic Materials and Weldments

Pages

1495-1502

DOI

10.1007/978-1-4613-0979-6_74

Language

en

File Format

application/pdf

Share

COinS
 
Jan 1st, 12:00 AM

Objective Ultrasonic Characterization of Welding Defects Using Physically Based Pattern Recognition Techniques

Williamsburg, VA

Computer-based methods for analysing ultrasonic data to distinguish between different defect types have been based on a variety of techniques such as adaptive learning [1], artificial intelligence [2] and statistical pattern recognition [3]. The uncertain classification reliability of these techniques when applied to a range of realistic defect types has, however, often been a significant practical limitation to their use.