Location

La Jolla, CA

Start Date

1-1-1983 12:00 AM

Description

This paper describes a new approach for classifying NDE waveforms. Using this approach a set of matched filters is constructed one for each category of waveform, based on parameters from autoregressive models. The method offers advantages in terms of hardware implementation over conventional pattern recognition approaches. Feasibility is shown using computer generated data. Results are then presented for real data from acoustic emission experiments.

Book Title

Review of Progress in Quantitative Nondestructive Evaluation

Volume

2B

Chapter

Section 18: Applications of Inverse Scattering

Pages

1117-1126

DOI

10.1007/978-1-4613-3706-5_72

Language

en

File Format

application/pdf

Share

COinS
 
Jan 1st, 12:00 AM

Classification of NDE Waveforms with Autoregressive Models

La Jolla, CA

This paper describes a new approach for classifying NDE waveforms. Using this approach a set of matched filters is constructed one for each category of waveform, based on parameters from autoregressive models. The method offers advantages in terms of hardware implementation over conventional pattern recognition approaches. Feasibility is shown using computer generated data. Results are then presented for real data from acoustic emission experiments.